# Roark Docs > Roark is the quality platform for voice and chat AI. Simulate every scenario before launch, monitor every production call, and score them with audio-native metrics. - [Welcome to Roark](https://docs.roark.ai/documentation/getting-started/introduction.md): The quality platform for voice and chat AI - [API Keys](https://docs.roark.ai/documentation/getting-started/api-keys.md): Generate and manage authentication keys for Roark APIs - [Overview](https://docs.roark.ai/documentation/simulation-testing/overview.md): Pressure-test your voice AI agents before your customers do - [Customer Flows](https://docs.roark.ai/documentation/simulation-testing/customer-flows.md): Define the customer conversations your agents should handle, and get graded against - [Personas](https://docs.roark.ai/documentation/simulation-testing/personas.md): The callers your simulations run as - [Environments](https://docs.roark.ai/documentation/simulation-testing/environments.md): The background noise a simulated customer calls from, and how loud it plays - [Templates](https://docs.roark.ai/documentation/simulation-testing/templates.md): Start a simulation run from a goal: each template ships preset metrics, Pass/Fail checks, and its own configuration panel - [Flow adherence](https://docs.roark.ai/documentation/simulation-testing/templates/flow-adherence.md): Check your agent follows the flows you authored, step by step, and reaches the outcome each one expects - [Conversation quality](https://docs.roark.ai/documentation/simulation-testing/templates/conversation-quality.md): Measure how natural, empathetic and helpful your agent sounds across realistic, unscripted conversations - [Multilingual](https://docs.roark.ai/documentation/simulation-testing/templates/multilingual.md): Run your flows across languages and check your agent detects, understands and answers in the caller’s language - [Tool call accuracy](https://docs.roark.ai/documentation/simulation-testing/templates/tool-call-accuracy.md): Check your agent calls the right tools, with the right arguments, at the right point in the call - [Knowledge base grounding](https://docs.roark.ai/documentation/simulation-testing/templates/knowledge-base-grounding.md): Ask questions your knowledge base answers, and check your agent stays faithful to it - [Red teaming](https://docs.roark.ai/documentation/simulation-testing/templates/red-teaming.md): Probe your agent adversarially for jailbreaks, leaked data, off-scope answers and made-up facts - [Accent handling](https://docs.roark.ai/documentation/simulation-testing/templates/accent-handling.md): Run one flow with callers from every region and find where your agent stops understanding - [Caller age handling](https://docs.roark.ai/documentation/simulation-testing/templates/age-handling.md): Run one flow with child, teenage, adult and elderly callers and find which your agent understands worst - [Background noise robustness](https://docs.roark.ai/documentation/simulation-testing/templates/background-noise-robustness.md): Run one flow through every background a caller could be in, from silence to a construction site - [Emotion handling](https://docs.roark.ai/documentation/simulation-testing/templates/emotion-handling.md): Run one flow with callers who are angry, anxious, confused or rushed and find which moods your agent handles worst - [Gender handling](https://docs.roark.ai/documentation/simulation-testing/templates/gender-handling.md): Run one flow with callers of each voice gender and find whether your agent understands and treats them the same - [Interruption handling](https://docs.roark.ai/documentation/simulation-testing/templates/interruption-handling.md): Run one flow with callers who never interrupt, who only make listening noises, and who talk over your agent - [Speech pace handling](https://docs.roark.ai/documentation/simulation-testing/templates/speech-pace-handling.md): Run one flow with callers who rush and callers who drag, and find what pace costs your agent - [Voicemail testing](https://docs.roark.ai/documentation/simulation-testing/templates/voicemail-testing.md): Check your agent notices it has reached voicemail, leaves a usable message, and hangs up - [Call screening](https://docs.roark.ai/documentation/simulation-testing/templates/call-screening.md): Check your outbound agent recognises a call screener, answers it directly, and saves its pitch for a person - [Load testing](https://docs.roark.ai/documentation/simulation-testing/templates/load-testing.md): Run many simulations in parallel to surface latency, dropped calls and concurrency limits - [Health check](https://docs.roark.ai/documentation/simulation-testing/templates/health-check.md): A minimal probe call on a schedule that verifies your agent answers, speaks and stays responsive - [Live Bench](https://docs.roark.ai/documentation/simulation-testing/templates/live-bench.md): Roark’s standard voice-agent benchmark: task completion, turn-taking, latency and robustness in realistic conditions - [Run Plans](https://docs.roark.ai/documentation/simulation-testing/run-plans.md): Save simulation configurations as reusable test suites you can run on demand, on a schedule, or via API - [Running Simulations](https://docs.roark.ai/documentation/simulation-testing/running-simulations.md): Trigger runs, watch them live, and read the settled report - [Variables](https://docs.roark.ai/documentation/simulation-testing/variables.md): Feed dynamic values into customer flows and run plans with {{variable}} placeholders - [Schedules](https://docs.roark.ai/documentation/simulation-testing/schedules.md): Put a plan on a schedule so it runs itself: hourly, daily, weekly, monthly, or once at a future time - [CI/CD](https://docs.roark.ai/documentation/simulation-testing/ci-cd.md): Gate your pipeline on a simulation: the run is judged against the success criteria on its plan and the build fails when your agent falls short - [Inbound vs Outbound](https://docs.roark.ai/documentation/simulation-testing/inbound-vs-outbound.md): Understanding simulation testing directions - [WebRTC Simulations](https://docs.roark.ai/documentation/simulation-testing/webrtc.md): Run simulations over WebRTC instead of a phone line - [Chat Simulations](https://docs.roark.ai/documentation/simulation-testing/chat-simulations.md): Test text-based AI agents the same way you test voice agents - [Identifying Simulations](https://docs.roark.ai/documentation/simulation-testing/identifying-simulations.md): Verify simulation calls and retrieve simulation details from your agent - [Enriched Simulations](https://docs.roark.ai/documentation/simulation-testing/enriched-simulations.md): Get richer call data in simulations by sending your agent call to Roark - [Best Practices](https://docs.roark.ai/documentation/simulation-testing/best-practices.md): Guidelines for getting the most out of Roark simulations - [Overview](https://docs.roark.ai/documentation/observability/overview.md): Monitor and analyze your voice AI conversations in real-time - [Live Monitoring](https://docs.roark.ai/documentation/observability/live-monitoring.md): Browse, search, and analyze every voice AI call - [Traces](https://docs.roark.ai/documentation/observability/traces.md): Send OpenTelemetry traces to Roark for full visibility into your Voice AI agent - [Reports](https://docs.roark.ai/documentation/observability/reports.md): Analytics dashboards and insights for voice AI performance - [Dashboards](https://docs.roark.ai/documentation/observability/dashboards.md): Organize multiple reports into a single view for comprehensive monitoring - [Query analytics](https://docs.roark.ai/documentation/observability/analytics-api.md): Ask Roark for aggregate numbers over your calls and metrics from code, an agent, or the CLI: the same data behind your dashboards - [Overview](https://docs.roark.ai/documentation/metrics/overview.md): Understand what metrics are and how to use them across monitoring and simulations - [System Metrics Reference](https://docs.roark.ai/documentation/metrics/system-metrics.md): Complete reference for all built-in system metrics powered by specialized models - [Custom Metrics](https://docs.roark.ai/documentation/metrics/custom-metrics.md): Measure what matters to your business with LLM judges, patterns, formulas, and API checks - [LLM Judge](https://docs.roark.ai/documentation/metrics/custom-metrics/llm-judge.md): Describe what to measure in plain language and let Roark score every call against it - [Patterns](https://docs.roark.ai/documentation/metrics/custom-metrics/patterns.md): Detect when one thing happens and another follows it, line by line through the call - [Formulas](https://docs.roark.ai/documentation/metrics/custom-metrics/formulas.md): Compute a metric from other metrics with math and comparisons - [API Checks](https://docs.roark.ai/documentation/metrics/custom-metrics/api-checks.md): Ask your own backend whether a call did what it should - [Studio](https://docs.roark.ai/documentation/metrics/studio.md): Author, test, and evaluate metrics in one workbench before they run on live traffic - [Collectors](https://docs.roark.ai/documentation/metrics/metric-collectors.md): Run a set of metrics automatically on every conversation that matches - [Thresholds](https://docs.roark.ai/documentation/metrics/thresholds.md): Define pass/fail criteria for your metrics - [Datasets](https://docs.roark.ai/documentation/metrics/datasets.md): Group calls or chats into named collections for evaluation, comparison, and analysis - [Collection Jobs](https://docs.roark.ai/documentation/metrics/metric-collection-jobs.md): Run metrics on demand for specific calls via the API - [Tool Invocations](https://docs.roark.ai/documentation/tool-invocations.md): Submit and track tool calls as part of post-call analysis - [Overview](https://docs.roark.ai/documentation/autoimprove/overview.md): Give Roark an objective and it improves your voice agent for you: it stages a copy, builds a test suite, changes the configuration, and proves the improvement with real simulated calls before you promote it - [Running a job](https://docs.roark.ai/documentation/autoimprove/running-a-job.md): The full Autoimprove lifecycle over the CLI and API: create a job, watch the worklog, steer and answer, then promote or dismiss - [Code-first agents (LiveKit, Pipecat)](https://docs.roark.ai/documentation/autoimprove/code-first-agents.md): Run Autoimprove on agents you built in code: externalize the tunable surface into a Roark-managed config, and Roark improves it against your real production deployment - [Tool Call Testing](https://docs.roark.ai/documentation/recipes/tool-call-testing.md): Test your voice agent's tool calls: safely, deterministically, and graded automatically - [Accent Detection & TTS Drift Monitoring](https://docs.roark.ai/documentation/recipes/accent-detection.md): Detect accents and flag when your agent's TTS voice drifts mid-call - [Testing Call Screeners](https://docs.roark.ai/documentation/recipes/call-screener-testing.md): Check your outbound agent recognises a gatekeeper, answers it directly, and saves its pitch for a person - [Exporting to Snowflake](https://docs.roark.ai/documentation/integrations/exporting-to-snowflake.md): Sync your Roark call analysis into a data warehouse to join it against your own operational data - [Overview](https://docs.roark.ai/documentation/integrations/overview.md): Every platform Roark connects to, and exactly which capabilities each one supports - [VAPI](https://docs.roark.ai/documentation/integrations/vapi.md): Sync VAPI assistants and analyze voice AI conversations - [Pipecat](https://docs.roark.ai/documentation/integrations/pipecat.md): Instrument a Pipecat voice agent with the roark_analytics[pipecat] observer, self-hosted or on Pipecat Cloud - [Retell AI](https://docs.roark.ai/documentation/integrations/retell.md): Sync Retell agents and analyze voice AI conversations - [ElevenLabs](https://docs.roark.ai/documentation/integrations/elevenlabs.md): Sync ElevenLabs conversational AI agents and run voice and chat simulations - [Leaping](https://docs.roark.ai/documentation/integrations/leaping.md): Sync Leaping AI agents and analyze voice conversations - [LiveKit Cloud](https://docs.roark.ai/documentation/integrations/livekit.md): Connect LiveKit Cloud for real-time voice communication monitoring - [LiveKit (self-hosted)](https://docs.roark.ai/documentation/integrations/livekit-self-hosted.md): Instrument a self-hosted LiveKit Agents worker with the roark-analytics[livekit] SDK - [Bland AI](https://docs.roark.ai/documentation/integrations/bland.md): Sync Bland AI agents and analyze voice AI conversations - [Google CES](https://docs.roark.ai/documentation/integrations/google-ces.md): Run chat simulations against Google Customer Engagement Suite apps - [Kore AI](https://docs.roark.ai/documentation/integrations/kore.md): Run chat simulations against Kore AI Agent Platform apps - [Custom Integrations](https://docs.roark.ai/documentation/integrations/custom-integrations.md): Send calls from any platform using our API and SDKs - [Okta SSO + SCIM](https://docs.roark.ai/documentation/integrations/okta.md): Sign your team into Roark with Okta, and optionally push-provision and deprovision users via SCIM - [IP Whitelisting](https://docs.roark.ai/documentation/integrations/ip-whitelisting.md): Whitelist Roark Analytics production IPs for firewalls, webhooks, and presigned URLs - [Usage & Cost Reporting](https://docs.roark.ai/documentation/enterprise/usage-reporting.md): Pull billable usage and cost per project, per call, and per simulation run, over the API or as a CSV - [Data Retention](https://docs.roark.ai/documentation/enterprise/data-retention.md): Control how long Roark keeps your call data, and whether expired data is hidden or permanently deleted - [PII Redaction](https://docs.roark.ai/documentation/observability/pii-redaction.md): Mask sensitive caller information in transcripts before it reaches your team or metrics - [Support](https://docs.roark.ai/documentation/resources/support.md): Get help with Roark - [Glossary](https://docs.roark.ai/documentation/resources/glossary.md): Key terms and concepts used in Roark - [Troubleshooting](https://docs.roark.ai/documentation/resources/troubleshooting.md): Solutions to common issues when using Roark - [Overview](https://docs.roark.ai/documentation/config-as-code/overview.md): Define your Roark agents, personas, flows, metrics, collectors, simulation plans and groups, alerts and dashboards as YAML in git and deploy them with one apply - [Run a simulation](https://docs.roark.ai/documentation/config-as-code/run-a-simulation.md): Zero to a scored simulation with config as code: define an agent and a plan, apply, run it, read the result, and gate CI on it - [TypeScript](https://docs.roark.ai/documentation/config-as-code/typescript.md): Define the same Roark resources in TypeScript with define* builders, then apply them with the CLI or Node SDK, a typed alternative to YAML - [Agents](https://docs.roark.ai/documentation/config-as-code/agents.md): Define voice agents as config - [Tools](https://docs.roark.ai/documentation/config-as-code/tools.md): Define an agent tool as config: its parameters, when it should fire, and how Roark grades and mocks it - [HTTP request definitions](https://docs.roark.ai/documentation/config-as-code/http-request-definitions.md): Define the HTTP request Roark fires to place outbound calls through your own system - [Personas](https://docs.roark.ai/documentation/config-as-code/personas.md): Define the simulated caller as config - [Flows](https://docs.roark.ai/documentation/config-as-code/flows.md): Define simulation flows as config (improv and scripted) - [Metrics](https://docs.roark.ai/documentation/config-as-code/metrics.md): Define custom LLM judges and API checks as config - [Collectors](https://docs.roark.ai/documentation/config-as-code/collectors.md): Decide which metrics get collected on which conversations - [Simulation plans](https://docs.roark.ai/documentation/config-as-code/simulation-plans.md): Declare a saved, repeatable simulation run - [Simulation groups](https://docs.roark.ai/documentation/config-as-code/simulation-groups.md): Run several simulation plans together and send one combined report to email and Slack - [Alerts](https://docs.roark.ai/documentation/config-as-code/alerts.md): Define alerts (monitors) as config: threshold, event, and simulation triggers - [Dashboards](https://docs.roark.ai/documentation/config-as-code/dashboards.md): Define dashboards and their widgets in YAML, versioned and reviewed like the rest of your config - [Organizations & Projects](https://docs.roark.ai/documentation/config-as-code/organizations.md): Declare your projects, their members, and each project’s resources as config and provision your whole organization from one git repo - [Node.js SDK](https://docs.roark.ai/documentation/sdks/node-sdk.md): Upload calls, run metrics, and execute simulations using Node.js - [Python SDK](https://docs.roark.ai/documentation/sdks/python-sdk.md): Upload calls, run metrics, and execute simulations using Python - [CLI](https://docs.roark.ai/documentation/sdks/cli.md): Drive Roark from your terminal and your CI pipeline - [MCP Server](https://docs.roark.ai/documentation/sdks/mcp-server.md): Connect AI agents and coding assistants to the Roark API using the Model Context Protocol - [Agent Skills](https://docs.roark.ai/documentation/sdks/skills.md): Teach any coding agent to test voice and chat AI agents with Roark - [Webhooks](https://docs.roark.ai/documentation/integrations/webhooks.md): Receive real-time notifications when call analysis completes or fails - [Introduction](https://docs.roark.ai/api-reference/introduction.md): Integrating with the Roark API - [Authorization](https://docs.roark.ai/api-reference/authorization.md): How to authenticate API requests - [Get API health status](https://docs.roark.ai/api-reference/health/get-api-health-status.md): Returns the health status of the API and its dependencies - [Exchange a CLI authorization code for an API key](https://docs.roark.ai/api-reference/cli-auth/exchange-a-cli-authorization-code-for-an-api-key.md): Completes the CLI browser-login flow: verifies the single-use authorization code and its PKCE code_verifier, then mints and returns the approved API key exactly once. - [Run a free simulation against a prospect agent](https://docs.roark.ai/api-reference/prospect-simulation/run-a-free-simulation-against-a-prospect-agent.md): Public endpoint: provisions a per-prospect project, runs a canned scenario template against the submitted phone number, and returns a report token to poll. The teaser report is also emailed when ready. - [Read a prospect simulation teaser report](https://docs.roark.ai/api-reference/prospect-simulation/read-a-prospect-simulation-teaser-report.md): Public endpoint scoped by the unguessable report token. Returns a truncated teaser once the debrief is ready; the full report is gated behind claiming an account. - [Mint a live observer WebSocket URL for a prospect call](https://docs.roark.ai/api-reference/prospect-simulation/mint-a-live-observer-websocket-url-for-a-prospect-call.md): Public endpoint scoped by the report token. Returns a short-lived, self-authenticating WebSocket URL for watching a prospect call live, but only while that call is actually in flight; otherwise wsUrl is null. Pass `callId` (from the live progress list) to pick one of the parallel calls; without it t… - [Describe the current credential](https://docs.roark.ai/api-reference/me/describe-the-current-credential.md): Returns the scope of the credential making the request, the organization it acts in, its default project (if any) and the permissions it was granted. Works for both project-scoped API keys and user-scoped credentials from the CLI or an MCP connector. - [List your personal credentials](https://docs.roark.ai/api-reference/me/list-your-personal-credentials.md): Returns the credentials that act as you: the ones created in the dashboard, from `roark auth login`, and MCP connectors. Requires a personal credential; a project API key is refused. Defaults to ACTIVE, pass ?status=REVOKED to see revoked ones. The key value itself is never returned. - [Create a personal credential](https://docs.roark.ai/api-reference/me/create-a-personal-credential.md): Mints a credential that acts as you, for a CLI or an automation. The key value is returned exactly once, in the `key` field: capture it now, it is unreadable afterwards. Requires a personal credential (a project API key is refused) and admin on the project the credential defaults to. The new credent… - [Revoke one of your personal credentials](https://docs.roark.ai/api-reference/me/revoke-one-of-your-personal-credentials.md): Revokes a credential that acts as you. It stops working immediately. A credential may revoke itself, which is what `roark auth logout` does. Repeating the call is safe; an unknown id, or one belonging to someone else, answers 404. - [List projects available to this credential](https://docs.roark.ai/api-reference/project/list-projects-available-to-this-credential.md): Returns every project the calling credential may act on, with the permissions it holds in each. A project-scoped API key returns the single project it is bound to. A user-scoped credential returns the projects in its organization where the holder is an active member. Use the returned id in the X-Roa… - [List agent endpoints](https://docs.roark.ai/api-reference/agent-endpoint/list-agent-endpoints.md): Returns a paginated list of agent endpoints for the authenticated project. - [Create a new agent endpoint](https://docs.roark.ai/api-reference/agent-endpoint/create-a-new-agent-endpoint.md): Creates a new agent endpoint for the authenticated project. - [Get agent endpoint by ID](https://docs.roark.ai/api-reference/agent-endpoint/get-agent-endpoint-by-id.md): Returns a specific agent endpoint by its ID. - [Update an agent endpoint](https://docs.roark.ai/api-reference/agent-endpoint/update-an-agent-endpoint.md): Updates an existing agent endpoint by its ID. Only environment and outboundDialType can be modified. - [List an agent's prompts](https://docs.roark.ai/api-reference/agent/list-an-agents-prompts.md): Returns the agent's prompt lineages. Each lineage is an independent version history, labelled by its `source` (USER, API, CONFIG, or a provider integration). `prompt` is the current content. - [Set an agent's prompt](https://docs.roark.ai/api-reference/agent/set-an-agents-prompt.md): Sets the agent's API-managed prompt. This is its own version history (`source: API_MANAGED`), separate from prompts observed on calls, edited in the app, or managed by config-as-code. Setting the same content twice is a no-op (no new version). Roark does not run your agent and no metric reads this p… - [List a prompt's versions](https://docs.roark.ai/api-reference/agent/list-a-prompts-versions.md): Returns the full version history of a single prompt lineage, newest first. - [List an agent's versions](https://docs.roark.ai/api-reference/agent/list-an-agents-versions.md): The open draft first, if there is one, then published versions newest first. Paginated: pass `pagination.nextCursor` as `after` for the next page. - [Get an agent version](https://docs.roark.ai/api-reference/agent/get-an-agent-version.md): One version with every setting, plus the issues that stop it from running, if any. - [Roll an agent back to a version](https://docs.roark.ai/api-reference/agent/roll-an-agent-back-to-a-version.md): Publishes a new version, numbered after the latest, with this version's settings and makes it live. History stays append-only. An open draft started before this is kept but can no longer be published (409 `agent_draft_base_changed`); discard it or start a new one. Pass `expectedLiveVersionId` to be… - [Get an agent's draft](https://docs.roark.ai/api-reference/agent/get-an-agents-draft.md): The agent's open draft, with the issues that would stop it from being published. - [Edit the draft](https://docs.roark.ai/api-reference/agent/edit-the-draft.md): Changes settings on the draft. Omitted settings stay as they are. Pass the revision you read as expectedRevision to fail with 409 if anyone edited the draft since, instead of applying on top of their edit. - [Start a draft](https://docs.roark.ai/api-reference/agent/start-a-draft.md): Opens the agent's one shared draft, a copy of the live version or of an older published version. Fails with 409 when a draft is already open. - [Discard the draft](https://docs.roark.ai/api-reference/agent/discard-the-draft.md): Throws the open draft away and returns it. The live version is unchanged. - [Publish the draft](https://docs.roark.ai/api-reference/agent/publish-the-draft.md): Makes the draft the live version, numbered v1, v2, ... Fails with 409 if the draft was edited after expectedRevision, if another version was published since the draft started, or if it changes nothing; with 400 and the issues if the version cannot run. - [List agents](https://docs.roark.ai/api-reference/agent/list-agents.md): Returns a paginated list of agents for the authenticated project. - [Create a new agent](https://docs.roark.ai/api-reference/agent/create-a-new-agent.md): Creates a new agent for the authenticated project. - [Get agent by ID](https://docs.roark.ai/api-reference/agent/get-agent-by-id.md): Returns a specific agent by its ID. - [Update an agent](https://docs.roark.ai/api-reference/agent/update-an-agent.md): Updates an existing agent by its ID. - [Delete an agent](https://docs.roark.ai/api-reference/agent/delete-an-agent.md): Soft-deletes an agent by its ID. The agent is hidden from all reads and stops being attributed to new calls, but its record and history are retained. Fails with 409 if the agent is still referenced by simulation run plans: cancel those run plans first. Note: if the agent syncs from a provider integr… - [Build a Roark-hosted agent](https://docs.roark.ai/api-reference/agent/build-a-roark-hosted-agent.md): Creates a new Roark-hosted agent from a one-line job description. Roark authors the system prompt and hosts the config, so the agent is live and self-improvable from creation. - [List phone numbers](https://docs.roark.ai/api-reference/phone-number/list-phone-numbers.md): Returns the phone numbers the project owns, oldest first, with the agent each is assigned to. - [Buy a phone number](https://docs.roark.ai/api-reference/phone-number/buy-a-phone-number.md): Buys a number from the carrier for this project: the one named by e164, or one Roark picks to match autoPick (trying the next match if the carrier has just sold one). Free inside the plan allowance; past it, the first month of rent is charged now and monthly after that. - [Search available phone numbers](https://docs.roark.ai/api-reference/phone-number/search-available-phone-numbers.md): Returns US or Canadian numbers the carrier has for sale, local or toll-free, narrowed by area code or by digits the number must contain. When an area code has no numbers, nearby ones are returned flagged bestEffort; an empty list means nothing matched. Buy one with POST /v1/phone-number, or let Roar… - [Get the phone number allowance](https://docs.roark.ai/api-reference/phone-number/get-the-phone-number-allowance.md): Returns how many numbers the organization gets for free, how many it holds, what a paid number costs a month, and whether a purchase would be admitted right now. - [Update a phone number](https://docs.roark.ai/api-reference/phone-number/update-a-phone-number.md): Relabels a number or changes which agent it is assigned to. A field left out is untouched; null clears it. - [Release a phone number](https://docs.roark.ai/api-reference/phone-number/release-a-phone-number.md): Gives the number back to the carrier. This cannot be undone: rent stops today and nothing is refunded. - [List calls](https://docs.roark.ai/api-reference/call/list-calls.md): Returns a paginated list of calls for the authenticated project. - [Create a call](https://docs.roark.ai/api-reference/call/create-a-call.md): Create a new call with recording, transcript, agents, and customers - [Get a call by ID](https://docs.roark.ai/api-reference/call/get-a-call-by-id.md): Retrieve an existing call by its unique identifier - [Delete a call](https://docs.roark.ai/api-reference/call/delete-a-call.md): Deletes a call by its ID. The call, its metrics and its analysis are hidden from every read, and any analysis still running on it is cancelled. Returns 404 when the call does not exist in this project or was already deleted. - [Delete calls in batch](https://docs.roark.ai/api-reference/call/delete-calls-in-batch.md): Deletes up to 100 calls by ID in one request. Each deleted call, its metrics and its analysis are hidden from every read, and any analysis still running on it is cancelled. IDs that do not exist in this project, or were already deleted, are returned in notFoundCallIds and left untouched. The request… - [List call sentiment runs](https://docs.roark.ai/api-reference/call/list-call-sentiment-runs.md): Fetch detailed sentiment analysis results for a specific call, including emotional tone, key phrases, and sentiment scores. - [List call metrics](https://docs.roark.ai/api-reference/call/list-call-metrics.md): Fetch all call-level metrics for a specific call, including both system-generated and custom metrics. Only returns rows from the **latest** metric-collection job per metric — if the same metric has been recomputed, prior runs are excluded and remain in the metric history. By default returns only suc… - [Get call transcript](https://docs.roark.ai/api-reference/call/get-call-transcript.md): Fetch the full transcript for a specific call. Optionally specify a transcription source; otherwise the best available source is used automatically. - [Append tool invocations to a call](https://docs.roark.ai/api-reference/call/append-tool-invocations-to-a-call.md): Attach tool invocations that fired during a call to an already-existing call, asynchronously after the call was created. Use this when the tool-call data becomes available later than the call itself (e.g. a Roark simulation, or a call submitted via POST /v1/call before its tools were ready). Writes… - [Update the properties of a call](https://docs.roark.ai/api-reference/call/update-the-properties-of-a-call.md): Add, overwrite or remove custom properties on an already-existing call. Use this for data that becomes available after the call was created, e.g. an outcome your system validates a few minutes later. Merge semantics: a value adds or overwrites the property, null removes it, and properties left out a… - [Get call cost](https://docs.roark.ai/api-reference/call/get-call-cost.md): The billable spend attributed to one call, split by cost type, with every cost line behind it. Simulated calls include the costs their simulation incurred before the call connected. Amounts are billable spend only, in exact micro-dollars (`*UsdMicros`) and dollars (`*Usd`, for display). Requires an… - [List chats](https://docs.roark.ai/api-reference/chat/list-chats.md): Returns a paginated list of chats for the authenticated project. - [Create a chat](https://docs.roark.ai/api-reference/chat/create-a-chat.md): Create a new chat with segments (messages and tool invocations) - [Get a chat by ID](https://docs.roark.ai/api-reference/chat/get-a-chat-by-id.md): Retrieve an existing chat by its unique identifier - [Get chat transcript](https://docs.roark.ai/api-reference/chat/get-chat-transcript.md): Fetch the full transcript (messages) for a specific chat. - [List chat metrics](https://docs.roark.ai/api-reference/chat/list-chat-metrics.md): Fetch all metrics for a specific chat, including both system-generated and custom metrics. Only returns rows from the **latest** metric-collection job per metric — if the same metric has been recomputed, prior runs are excluded and remain in the metric history. By default returns only successfully c… - [List metric definitions](https://docs.roark.ai/api-reference/metric/list-metric-definitions.md): Fetch metric definitions available in the project, including both system-generated and custom metrics. Results are ordered by immutable definition ID; pass `nextCursor` to retrieve the following page. - [Create custom metric definition](https://docs.roark.ai/api-reference/metric/create-custom-metric-definition.md): Create a new metric definition. The `calculationType` field selects the variant: LLM_JUDGE (LLM-evaluated), FORMULA (computed from a math expression over other metrics), or PATTERN (detects a trigger→outcome pattern within a window). To create a threshold on top of an existing metric, use `POST /met… - [Get a metric definition](https://docs.roark.ai/api-reference/metric/get-a-metric-definition.md): Fetch a single metric definition by its UUID or its stable `slug` (e.g. `customer_satisfaction`). Resolution is scoped to the project — a project-owned metric wins over an org-wide one, which wins over a system metric of the same `slug`. - [Update a metric definition](https://docs.roark.ai/api-reference/metric/update-a-metric-definition.md): Update the editable subset of a custom metric definition, addressed by its UUID or its stable `slug`. Only the supplied fields are changed; omitted fields are left unchanged. Every update creates a new immutable version; the response carries the advanced `versionId`. Immutable fields (scope, outputT… - [Delete a metric definition](https://docs.roark.ai/api-reference/metric/delete-a-metric-definition.md): Archives (soft-deletes) a custom metric definition, addressed by its UUID or its stable `slug`. The metric is hidden from all reads and stops being collected, but its record and previously collected values are retained. System metrics cannot be deleted. Fails with 409 if the metric is still used as… - [Create a threshold on a metric](https://docs.roark.ai/api-reference/metric/create-a-threshold-on-a-metric.md): Create a boolean threshold derived from an existing metric. The source metric is addressed by its UUID or its stable `slug`. The threshold fires when the source metric meets the comparison condition. Scope and supported contexts are inherited from the source metric. - [List a metric’s variants](https://docs.roark.ai/api-reference/metric/list-a-metric’s-variants.md): Every configuration of this metric your organization can use: Roark’s own variants and any your organization has added or forked. `isDefault` marks the one the metric is scored with when nothing pins another; pass any variant’s `id` as `sourceVariantId` to pin it on a derived metric. - [Create a metric variant](https://docs.roark.ai/api-reference/metric/create-a-metric-variant.md): Add a configuration of this metric for your organization, seeded from its Default. Edit it with PUT to change what it measures, then pin it where you want it used. - [Get a metric variant](https://docs.roark.ai/api-reference/metric/get-a-metric-variant.md): One configuration of this metric, by id. - [Update a metric variant](https://docs.roark.ai/api-reference/metric/update-a-metric-variant.md): Rename a variant, change its configuration, or both. Every configuration change creates a new immutable version and advances `versionId`; the response carries the advanced value. - [Delete a metric variant](https://docs.roark.ai/api-reference/metric/delete-a-metric-variant.md): Remove one of your organization’s variants. Anything pinned to it falls back to the Default, so deleting a fork of a Roark variant returns you to Roark’s configuration. - [Http request metric](https://docs.roark.ai/api-reference/metric/http-request-metric.md): What an HTTP request metric sends to your endpoint, and the answer it expects. Roark sends it once per call the metric grades, live or simulated, after the call is analysed. - [List metric policies](https://docs.roark.ai/api-reference/metric-policy/list-metric-policies.md): Returns a paginated list of metric policies for the project, including system policies. - [Create a metric policy](https://docs.roark.ai/api-reference/metric-policy/create-a-metric-policy.md): Creates a new metric policy. Policies define which metrics to collect and under what conditions. - [Get metric policy by ID](https://docs.roark.ai/api-reference/metric-policy/get-metric-policy-by-id.md): Returns a specific metric policy with its conditions and metrics. - [Update a metric policy](https://docs.roark.ai/api-reference/metric-policy/update-a-metric-policy.md): Updates an existing metric policy. System policies cannot be modified. - [Delete a metric policy](https://docs.roark.ai/api-reference/metric-policy/delete-a-metric-policy.md): Soft-deletes a metric policy. System policies cannot be deleted. - [List metric collection jobs](https://docs.roark.ai/api-reference/metric-collection-job/list-metric-collection-jobs.md): Returns a paginated list of metric collection jobs for the project. - [Create and run a metric collection job](https://docs.roark.ai/api-reference/metric-collection-job/create-and-run-a-metric-collection-job.md): Creates a metric collection job for the specified calls or chats and metrics, then triggers processing. Provide exactly one of callIds or chatIds. Pass policyId to score with a metric policy’s settings (for example to re-score past calls after changing which properties Property Verification checks);… - [Get metric collection job by ID](https://docs.roark.ai/api-reference/metric-collection-job/get-metric-collection-job-by-id.md): Returns a specific metric collection job with progress information. - [Retry a metric collection job](https://docs.roark.ai/api-reference/metric-collection-job/retry-a-metric-collection-job.md): Creates a new metric collection job using the same conversations and metrics as a previous job, then triggers processing. The previous job must be in a terminal state (COMPLETED, FAILED, or CANCELED). Returns the newly created job — track its id for downstream fetches. - [Cancel a metric collection job](https://docs.roark.ai/api-reference/metric-collection-job/cancel-a-metric-collection-job.md): Stops a metric collection job that has not finished. No further conversations are processed and the job ends in CANCELED. - [Get metric values produced by a metric collection job](https://docs.roark.ai/api-reference/metric-collection-job/get-metric-values-produced-by-a-metric-collection-job.md): Returns the metric values produced by the specified job, grouped by metric definition. Unlike `GET /v1/call/:callId/metrics` (which returns the latest values on a call, regardless of which job computed them), this endpoint returns exactly the values *this* job produced — including for calls whose li… - [List personas](https://docs.roark.ai/api-reference/simulation-persona/list-personas.md): Returns a paginated list of personas for the authenticated project. - [Create a new persona](https://docs.roark.ai/api-reference/simulation-persona/create-a-new-persona.md): Creates a new persona for the authenticated project. - [Get persona by ID](https://docs.roark.ai/api-reference/simulation-persona/get-persona-by-id.md): Returns a specific persona by its ID. - [Update a persona](https://docs.roark.ai/api-reference/simulation-persona/update-a-persona.md): Updates an existing persona by its ID. - [Delete a persona](https://docs.roark.ai/api-reference/simulation-persona/delete-a-persona.md): Soft-deletes a persona by its ID. The persona is hidden from all reads and stops being available to new simulations, but its record and history are retained. System personas cannot be deleted. - [Run a simulation](https://docs.roark.ai/api-reference/simulation/run-a-simulation.md): Starts a simulation and returns the run. - [List run groups](https://docs.roark.ai/api-reference/simulation/list-run-groups.md): Returns the run groups in the project, newest first, with their runs and where each group report stands. Read a report document from GET /v1/simulation/run-group/{groupId}. - [Create a run group](https://docs.roark.ai/api-reference/simulation/create-a-run-group.md): Groups several simulation runs so they read as one, and starts generating the group report: one document across every run, with a scorecard summed across them and the issues found, each merged from the per-run debriefs. - [Get a run group](https://docs.roark.ai/api-reference/simulation/get-a-run-group.md): Returns a run group with its runs in group order and its latest group report, including the report document once READY. - [Delete a run group](https://docs.roark.ai/api-reference/simulation/delete-a-run-group.md): Deletes a run group. Its runs, and their results, are untouched. - [Regenerate a run group report](https://docs.roark.ai/api-reference/simulation/regenerate-a-run-group-report.md): Generates the group report again over the latest state of its runs. Returns the report generation; if one is already in flight it is returned instead of starting another. Poll GET /v1/simulation/run-group/{groupId} until `latestReport.status` is READY. - [List simulation groups](https://docs.roark.ai/api-reference/simulation/list-simulation-groups.md): Returns the saved simulation groups in the project, most recently edited first, each with its plans in run order and notification settings. - [Create a simulation group](https://docs.roark.ai/api-reference/simulation/create-a-simulation-group.md): Saves a named set of plans to run together, again and again. Nothing runs yet: POST /v1/simulation/group/{groupId}/run starts one run of every plan and groups them into a run group with one combined report. - [Get a simulation group](https://docs.roark.ai/api-reference/simulation/get-a-simulation-group.md): Returns a saved simulation group with its plans in run order and notification settings. - [Update a simulation group](https://docs.roark.ai/api-reference/simulation/update-a-simulation-group.md): Edits a saved simulation group. Omitted fields keep their current value; `notifications`, when sent, replaces the settings as a whole. Run groups it already started keep theirs. - [Delete a simulation group](https://docs.roark.ai/api-reference/simulation/delete-a-simulation-group.md): Deletes a saved simulation group and any schedules that run it. Run groups it already started, and their reports, stay. A group managed by config as code returns 409. - [Run a simulation group](https://docs.roark.ai/api-reference/simulation/run-a-simulation-group.md): Starts one run of every plan in the group, exactly as POST /v1/simulation/plan/{planId}/job would for each, and groups the runs into a run group whose combined report is announced through the group's notification settings once it is ready. This places real calls. Config-managed groups can be run her… - [Mock a tool call during a test call](https://docs.roark.ai/api-reference/simulation/mock-a-tool-call-during-a-test-call.md): The server half of the tool guard for code-first agents. When a guarded tool fires during a Roark test call, send the invocation here instead of executing it: Roark answers with a simulated backend response that is valid JSON, shaped by the tool contract you pass, consistent with the test scenario,… - [List tool fixtures](https://docs.roark.ai/api-reference/simulation/list-tool-fixtures.md): All deterministic tool responses configured for this project, optionally filtered by tool. - [Set a tool fixture](https://docs.roark.ai/api-reference/simulation/set-a-tool-fixture.md): Create-or-replace by scope: one fixture per tool project-wide, plus one per (tool, flow variant). Setting the same scope twice replaces the response, so CI can apply fixtures idempotently. During Roark test calls the tool guard answers with the fixture verbatim instead of generating a response; real… - [Update a tool fixture](https://docs.roark.ai/api-reference/simulation/update-a-tool-fixture.md): Change the response, description, or enabled state of an existing fixture. - [Delete a tool fixture](https://docs.roark.ai/api-reference/simulation/delete-a-tool-fixture.md): The tool goes back to scenario-aware generated responses in test calls. - [List environments](https://docs.roark.ai/api-reference/simulation-environment/list-environments.md): Returns a paginated list of environments: the project's own plus the environments Roark curates and shares across every project. Reference one by id when setting a customer flow variant's environment. - [Create an environment](https://docs.roark.ai/api-reference/simulation-environment/create-an-environment.md): Creates an environment for the project: a noise bed and the level it plays at. Reference it by id when setting a customer flow variant's environment. Roark's curated presets always play at the default level, so this is how a project gets the same bed louder or quieter. - [Get environment by ID](https://docs.roark.ai/api-reference/simulation-environment/get-environment-by-id.md): Returns a single environment by its ID. - [Update an environment](https://docs.roark.ai/api-reference/simulation-environment/update-an-environment.md): Updates one of the project's environments. Only the fields sent are changed. Runs already built keep the snapshot they were built with. Roark-curated environments cannot be edited (403). - [Delete an environment](https://docs.roark.ai/api-reference/simulation-environment/delete-an-environment.md): Soft-deletes one of the project's environments. It disappears from reads and cannot be picked for new runs; runs already built keep their snapshot. Refused (409) while a live customer flow variant still uses it: move those variants first. Roark-curated environments cannot be deleted (403). - [List run plans](https://docs.roark.ai/api-reference/simulation-run-plan/list-run-plans.md): Returns a paginated list of simulation run plans. Optionally filter by search text or agent ID. - [Create a run plan](https://docs.roark.ai/api-reference/simulation-run-plan/create-a-run-plan.md): Creates a new simulation run plan. - [Get run plan by ID](https://docs.roark.ai/api-reference/simulation-run-plan/get-run-plan-by-id.md): Returns a specific simulation run plan by its ID. - [Update a run plan](https://docs.roark.ai/api-reference/simulation-run-plan/update-a-run-plan.md): Updates an existing simulation run plan by its ID. - [Delete a run plan](https://docs.roark.ai/api-reference/simulation-run-plan/delete-a-run-plan.md): Soft-deletes a simulation run plan by its ID. - [List simulation plan jobs](https://docs.roark.ai/api-reference/simulation-run-plan-job/list-simulation-plan-jobs.md): Returns a paginated list of simulation run plan jobs. Filter by status, plan ID, or label to find specific simulation batches. - [Get simulation plan job](https://docs.roark.ai/api-reference/simulation-run-plan-job/get-simulation-plan-job.md): Retrieve details of a simulation plan job including all associated simulation jobs (calls) - [Cancel a simulation plan job](https://docs.roark.ai/api-reference/simulation-run-plan-job/cancel-a-simulation-plan-job.md): Stops a run that has not finished yet. Already-finished runs are left alone. - [Run a simulation plan](https://docs.roark.ai/api-reference/simulation-run-plan-job/run-a-simulation-plan.md): Deprecated: use POST /v1/simulation/run, which does the same thing and can also take the plan configuration inline, so a one-off run does not have to create a plan first. - [Get simulation run results](https://docs.roark.ai/api-reference/simulation-run-plan-job/get-simulation-run-results.md): Everything the run report shows, in one request: the summary and score, the pass/fail verdict, per-metric aggregates, every simulation with its check results, breakdowns by agent and persona, the comparison against the previous run (or `compareToJobId`), the sweep attribution, and the written debrie… - [Generate simulation run debrief](https://docs.roark.ai/api-reference/simulation-run-plan-job/generate-simulation-run-debrief.md): Request the written debrief for a settled run: executive summary, failure themes and recommendations. Runs with graded calls get one automatically, so this is for regenerating one (`regenerate: true`) or retrying one that failed. - [Get simulation run cost](https://docs.roark.ai/api-reference/simulation-run-plan-job/get-simulation-run-cost.md): The billable spend for one simulation run (run plan job), split by cost type, with the spend of each simulated call in it. Safe to call while the run is in progress: totals reflect the costs recorded so far. Amounts are billable spend only, in exact micro-dollars (`*UsdMicros`) and dollars (`*Usd`,… - [List simulation templates](https://docs.roark.ai/api-reference/simulation-template/list-simulation-templates.md): Returns the built-in simulation templates, each resolved against this project: the metric and check definitions it collects, and the flows it runs with the variants it covers. - [Lookup by phone number](https://docs.roark.ai/api-reference/simulation-job/lookup-by-phone-number.md): Find the matching simulation using the number used by the Roark simulation agent. - [Get simulation by ID](https://docs.roark.ai/api-reference/simulation-job/get-simulation-by-id.md): Get a individual simulation run directly by its ID. This is generally part of a larger simulation run plan job. - [List mocked tool invocations](https://docs.roark.ai/api-reference/simulation-job/list-mocked-tool-invocations.md): Every guarded tool invocation Roark answered during this simulation: what the agent tried to call, with what arguments, and the simulated response it received. Use this to assert tool behavior in CI after a test call, with zero real side effects. Empty when the agent's tools are not guarded (see the… - [List customer flows](https://docs.roark.ai/api-reference/customer-flow/list-customer-flows.md): Returns a paginated list of customer flows with their agents, expectations, happy path and edge cases. The step graph is the one field omitted: reading it walks the project's whole step graph, so it comes back from the single-flow endpoint instead. Customer flows are how a project describes what to… - [Create a customer flow](https://docs.roark.ai/api-reference/customer-flow/create-a-customer-flow.md): Creates a customer flow. A SCRIPTED flow carries a step graph and gets one way of running it per path through the graph; an IMPROV flow carries the briefs you send. Customer flows replace the older simulation scenarios, so build a flow for anything new. - [Get customer flow by ID](https://docs.roark.ai/api-reference/customer-flow/get-customer-flow-by-id.md): Returns a customer flow with its happy path, edge cases, expectations and linked agents. Scripted flows also carry their step graph. - [Update a customer flow](https://docs.roark.ai/api-reference/customer-flow/update-a-customer-flow.md): Updates a flow's title, description, branching mode, linked agents or flow-level expectations. The step graph is replaced through PUT /graph. - [Delete a customer flow](https://docs.roark.ai/api-reference/customer-flow/delete-a-customer-flow.md): Soft-deletes a customer flow along with its edge cases, expectations and (for scripted flows) its step graph. Run plans that linked it drop it from their test cases. - [Replace a scripted flow's steps](https://docs.roark.ai/api-reference/customer-flow/replace-a-scripted-flows-steps.md): Replaces a scripted flow's conversation graph with the tree you send. This is a full replace, not a merge: a step you omit is removed. - [Update a flow's happy path](https://docs.roark.ai/api-reference/customer-flow/update-a-flows-happy-path.md): Updates the happy path's title, persona, environment, brief or expectations. Omitted fields are left alone; `additionalExpectations` replaces the set wholesale rather than appending. - [Duplicate a customer flow](https://docs.roark.ai/api-reference/customer-flow/duplicate-a-customer-flow.md): Deep-copies a flow into a new project-owned flow. The copy carries the source's description, branching mode, linked agents, flow-level expectations and flow-owned metrics. A scripted flow copies its whole step graph; an improv flow copies its variants (personas, briefs, expectations). Duplicating a… - [Add an edge case](https://docs.roark.ai/api-reference/customer-flow-edge-case/add-an-edge-case.md): Adds a variant to an IMPROV flow. - [Update an edge case](https://docs.roark.ai/api-reference/customer-flow-edge-case/update-an-edge-case.md): Updates an edge case's title, persona, environment, brief, preceded-by link or expectations. Omitted fields are left alone; `additionalExpectations` replaces the set wholesale rather than appending. Promoting it to the happy path is a separate call, since that also demotes the incumbent. - [Remove an edge case](https://docs.roark.ai/api-reference/customer-flow-edge-case/remove-an-edge-case.md): Soft-deletes a variant. On a scripted flow the path engine re-creates a variant for any path still in the graph, so remove the path through PUT /graph instead if that is what you meant. - [Promote an edge case to the happy path](https://docs.roark.ai/api-reference/customer-flow-edge-case/promote-an-edge-case-to-the-happy-path.md): Makes this edge case the flow's happy path, and the outgoing happy path an edge case. Its persona and environment are baked into it first, so edge cases that were inheriting keep the configuration they had. - [List HTTP request definitions](https://docs.roark.ai/api-reference/http-request-definition/list-http-request-definitions.md): Returns a paginated list of HTTP request definitions for the authenticated project. - [Create HTTP request definition](https://docs.roark.ai/api-reference/http-request-definition/create-http-request-definition.md): Creates a new HTTP request definition. The signing secret is only returned in this response and cannot be retrieved later. - [Get HTTP request definition by ID](https://docs.roark.ai/api-reference/http-request-definition/get-http-request-definition-by-id.md): Returns a specific HTTP request definition by its ID. - [Update HTTP request definition](https://docs.roark.ai/api-reference/http-request-definition/update-http-request-definition.md): Updates an existing HTTP request definition. - [List webhooks](https://docs.roark.ai/api-reference/webhook/list-webhooks.md): Returns a paginated list of webhooks with their event subscriptions. - [Create webhook](https://docs.roark.ai/api-reference/webhook/create-webhook.md): Creates a new webhook with event subscriptions. The signing secret is only returned in this response. - [Get webhook by ID](https://docs.roark.ai/api-reference/webhook/get-webhook-by-id.md): Returns a specific webhook with its event subscriptions. - [Delete webhook](https://docs.roark.ai/api-reference/webhook/delete-webhook.md): Deletes a webhook and all its event subscriptions. - [Event](https://docs.roark.ai/api-reference/webhook/event.md): Roark POSTs a JSON payload to every endpoint subscribed to one of the events listed below. Every payload uses the same envelope (`event`, `version`, `timestamp`, `data`); the `event` field is the discriminator that selects the matching `data` shape. - [List issues](https://docs.roark.ai/api-reference/issue/list-issues.md): Returns the project’s issues, ordered newest-first. Supports filtering by status, source, and severity, with offset pagination. - [Create issue](https://docs.roark.ai/api-reference/issue/create-issue.md): Opens a new issue with `source: API`. The supplied evidence (calls / chats) is attached in the same transaction; an invalid reference fails the whole request rather than leaving a half-created issue. - [Get issue by ID](https://docs.roark.ai/api-reference/issue/get-issue-by-id.md): Returns a single issue with its evidence rows. - [List Autoimprove jobs](https://docs.roark.ai/api-reference/autoimprove/list-autoimprove-jobs.md): List the Autoimprove jobs in this project, most recent first, capped at 100. - [Start an Autoimprove job](https://docs.roark.ai/api-reference/autoimprove/start-an-autoimprove-job.md): Commission Roark on an objective. It clones the agent into a staging shadow (or uses your designated staging agent), authors a validation suite of simulated callers, measures a baseline, changes the staging configuration, and re-tests until the objective metric passes its target. Production is never… - [Get an Autoimprove job](https://docs.roark.ai/api-reference/autoimprove/get-an-autoimprove-job.md): Fetch one job with its full worklog: every step Roark took, the validation batches with their pass-rate movement, any question it is waiting on, and its final report once concluded. - [Send guidance to a running job](https://docs.roark.ai/api-reference/autoimprove/send-guidance-to-a-running-job.md): Steer Roark mid-job. The message is folded into its next decision and is binding. Accepted while the job is live (RUNNING, NEEDS_INPUT, or PAUSED); a concluded job returns a conflict. - [Answer Roark's question](https://docs.roark.ai/api-reference/autoimprove/answer-roarks-question.md): Answer the question a job is blocked on. Only meaningful while the job status is NEEDS_INPUT (the open QUESTION entry carries the offered options; free text is also accepted). Otherwise returns a conflict. - [Cancel a job](https://docs.roark.ai/api-reference/autoimprove/cancel-a-job.md): Stop a live job. Production is never changed by a cancel; everything the job set up (the shadow agent, its phone number, authored test flows and run plan) is cleaned up automatically. - [Promote a verified job to production](https://docs.roark.ai/api-reference/autoimprove/promote-a-verified-job-to-production.md): Apply the verified staging changes to the PRODUCTION agent. Only a job in AWAITING_PROMOTE can be promoted. - [Dismiss a verified job](https://docs.roark.ai/api-reference/autoimprove/dismiss-a-verified-job.md): Discard a verified job without promoting: production stays untouched and the staging resources are cleaned up. Only a job in AWAITING_PROMOTE can be dismissed. - [Resolve config for a session](https://docs.roark.ai/api-reference/agent-config/resolve-config-for-a-session.md): The call your agent makes at session start. Returns the config JSON for this session, with per-session simulation recognition built in: when the session was originated by a Roark simulation (matched by caller number against the calls Roark has in flight), the STAGING revision is served for that sess… - [List managed configs](https://docs.roark.ai/api-reference/agent-config/list-managed-configs.md): List the managed agent configs in this project, most recent first. - [Get a managed config](https://docs.roark.ai/api-reference/agent-config/get-a-managed-config.md): Fetch one managed config with its channel pointers and recent revisions, newest first. - [Write a config revision](https://docs.roark.ai/api-reference/agent-config/write-a-config-revision.md): Write a new revision onto a channel. Writing production creates the key when it does not exist; writing staging stages a candidate that only Roark-recognized simulation sessions will read. Every write is a new revision; nothing is overwritten. - [Promote staging to production](https://docs.roark.ai/api-reference/agent-config/promote-staging-to-production.md): Point the production channel at the staging revision. Real traffic reads it from the next session onward; roll back by writing the prior revision id to production (the chain preserves every state). - [Discard the staging revision](https://docs.roark.ai/api-reference/agent-config/discard-the-staging-revision.md): Clear the staging channel. Production is untouched; recognized simulation sessions go back to reading production. - [List knowledge bases](https://docs.roark.ai/api-reference/knowledge-base/list-knowledge-bases.md): Returns a cursor-paginated list of knowledge bases for the authenticated project. Soft-deleted knowledge bases are excluded. - [Create a knowledge base](https://docs.roark.ai/api-reference/knowledge-base/create-a-knowledge-base.md): Creates a knowledge base. TEXT and JSON sources accept inline `content`. FILE sources require `filename`, `mimeType`, and base64-encoded `contentBase64` — the file is decoded server-side, stored in S3, and (for PDFs) text-extracted inline before the response returns. - [Get a knowledge base by ID](https://docs.roark.ai/api-reference/knowledge-base/get-a-knowledge-base-by-id.md): Returns metadata for a single knowledge base. Does not include content — content is read by metrics at evaluation time and is not exposed over the public API. - [Get the analytics schema](https://docs.roark.ai/api-reference/analytics/get-the-analytics-schema.md): Lists what can go into an analytics query for this project: every metric by slug with its output type, default aggregation and the aggregations it supports; the measure types; the filter and breakdown types with the properties each accepts; and the custom call properties seen in the project. Read th… - [Run an analytics query](https://docs.roark.ai/api-reference/analytics/run-an-analytics-query.md): Aggregates metric values and conversation counts over a time window and returns one series per measure, with a total for the window and per-interval buckets. The same query a dashboard widget runs, without saving anything. - [List dashboards](https://docs.roark.ai/api-reference/dashboard/list-dashboards.md): Lists the project's dashboards, the default first. GET /v1/dashboard/{dashboardId} returns the widgets. - [Create a dashboard](https://docs.roark.ai/api-reference/dashboard/create-a-dashboard.md): Creates a dashboard with its widgets. Each widget is an analytics query (see POST /v1/analytics/query) with a name unique on the dashboard, a `display` (LINE, NUMBER, RADAR, STACKED_BAR, TABLE) and a `size` (SMALL, MEDIUM, LARGE, EXTRA_LARGE). Widgets render top to bottom in the order given. - [Get a dashboard](https://docs.roark.ai/api-reference/dashboard/get-a-dashboard.md): Returns a dashboard with its widgets top to bottom, each in the shape POST /v1/dashboard accepts, so a dashboard can be read, edited and written back. - [Update a dashboard](https://docs.roark.ai/api-reference/dashboard/update-a-dashboard.md): Edits a dashboard. Omitted fields keep their current value. `widgets`, when sent, replaces the list: widgets are matched by name, so a widget that keeps its name keeps its id; a new name adds a widget and a name no longer listed removes it. To change one widget, PUT /v1/dashboard/{dashboardId}/widge… - [Delete a dashboard](https://docs.roark.ai/api-reference/dashboard/delete-a-dashboard.md): Deletes a dashboard and its widgets. If it was the default, another dashboard becomes the default. A dashboard managed by config as code returns 409. - [Get dashboard data](https://docs.roark.ai/api-reference/dashboard/get-dashboard-data.md): Runs every widget on the dashboard and returns each one's series, exactly as the dashboard shows them: over the dashboard's saved window and with its filters applied. Pass `from` (and optionally `to`) to read a different window, and `timezone` to align buckets to a zone. - [Add a widget](https://docs.roark.ai/api-reference/dashboard/add-a-widget.md): Adds a widget to the top of a dashboard. Its name must be unique on the dashboard. - [Replace a widget](https://docs.roark.ai/api-reference/dashboard/replace-a-widget.md): Replaces a widget's definition. It keeps its id and its place on the dashboard. - [Remove a widget](https://docs.roark.ai/api-reference/dashboard/remove-a-widget.md): Removes a widget from a dashboard. - [Get widget data](https://docs.roark.ai/api-reference/dashboard/get-widget-data.md): Runs one widget and returns its series, as it reads on its dashboard (the dashboard's window and filters). Accepts the same `from` / `to` / `timezone` overrides as GET /v1/dashboard/{dashboardId}/data. - [Diff a config bundle](https://docs.roark.ai/api-reference/config/diff-a-config-bundle.md): Dry run for an apply: returns the projected changes (create / update / delete) for the submitted bundle without writing anything. Works for both project and organization keys. - [Apply a config bundle](https://docs.roark.ai/api-reference/config/apply-a-config-bundle.md): Reconcile a config-as-code bundle. With a PROJECT API key, submit project-scoped resources (agents, personas, flows, collectors, metrics, ...). With an ORGANIZATION API key, submit `kind: project` resources, each optionally carrying its members and its own nested `resources`. Submit the full desired… - [List projects](https://docs.roark.ai/api-reference/organization-project/list-projects.md): List projects in the organization the API key belongs to. Paginated (max 101 per page): pass `page`/`limit` and keep paging until a page returns fewer than `limit` items. - [Create a project](https://docs.roark.ai/api-reference/organization-project/create-a-project.md): Create a new project in the organization. The project is provisioned with the default analysis packages, dashboard, and alerts, exactly as a UI-created project would be. The user who minted the API key becomes the initial project owner. - [Get a project](https://docs.roark.ai/api-reference/organization-project/get-a-project.md): Get a single project by id (must belong to the organization). - [Update a project](https://docs.roark.ai/api-reference/organization-project/update-a-project.md): Update a project name, description, or category. - [Delete a project](https://docs.roark.ai/api-reference/organization-project/delete-a-project.md): Soft-delete a project and pause its active schedules. Returns 409 when the project is the last one in the organization, has an active agent connection, or has a simulation running. - [List project members](https://docs.roark.ai/api-reference/organization-project-member/list-project-members.md): List active and pending-invite members of a project. - [Invite a member](https://docs.roark.ai/api-reference/organization-project-member/invite-a-member.md): Invite a user to the project by email with a role. If the user has no Roark account yet, an invite email is sent and the membership is INVITED until they accept; existing users are added directly. Use this for onboarding and for assigning users to projects. - [Update a member role](https://docs.roark.ai/api-reference/organization-project-member/update-a-member-role.md): Change a project member role. - [Remove a member](https://docs.roark.ai/api-reference/organization-project-member/remove-a-member.md): Remove a member from the project. The last owner/admin cannot be removed (409). - [List project API keys](https://docs.roark.ai/api-reference/organization-project-api-key/list-project-api-keys.md): List API keys for a project (key values are never returned after creation). - [Generate a project API key](https://docs.roark.ai/api-reference/organization-project-api-key/generate-a-project-api-key.md): Mint a new project-scoped API key. The raw key value is returned exactly once in the `key` field: capture it now, it is unreadable afterwards. Defaults to full project access with READ + WRITE scope; narrow with `permissions` / `scopes`. - [Revoke a project API key](https://docs.roark.ai/api-reference/organization-project-api-key/revoke-a-project-api-key.md): Revoke (deactivate) a project API key. Idempotent from the caller perspective. - [Get usage & cost](https://docs.roark.ai/api-reference/usage/get-usage-&-cost.md): Report billable usage and cost for the organization over a time window, broken down by project (highest spend first). Pass `from`/`to` as ISO 8601 timestamps; optionally pass `projectId` to scope the report to one project. Amounts are billable spend only (what we absorb is never included). Authentic… - [List benchmark suites](https://docs.roark.ai/api-reference/benchmark/list-benchmark-suites.md): Returns every benchmark suite with published results, along with the suite version the other endpoints default to. Start here: the suite name is a required parameter everywhere else and there is no other way to discover it. - [List benchmark metrics](https://docs.roark.ai/api-reference/benchmark/list-benchmark-metrics.md): Returns the metrics a suite version published, each with the direction that counts as better. Use it to pick a valid `sortBy` for the leaderboard: a metric key outside this list is rejected rather than silently ranking every target null. - [Get the benchmark leaderboard](https://docs.roark.ai/api-reference/benchmark/get-the-benchmark-leaderboard.md): Returns one ranked page of a suite version’s published targets, each with the metric cells it is judged on. Ranking happens in the database, so paging through the board is consistent. Every default the server applies (suite version, condition, sort metric, sort direction) is echoed on the response,… - [List score samples for a target](https://docs.roark.ai/api-reference/benchmark/list-score-samples-for-a-target.md): Returns the individual scored calls behind a target’s aggregate cells, each with the scorer’s rationale — the "why is this number what it is" read. Filter to one cell with `conditionKey` and `metricKey`. Metrics computed without a rationale (latencies, counts) contribute no samples. Returns reasonin… - [List a target’s published generations](https://docs.roark.ai/api-reference/benchmark/list-a-target’s-published-generations.md): Returns every sweep published for a target, newest first, including superseded ones. This is the trend read: it answers "did this model regress?" from Roark’s own published record. Metadata only — pass a row’s `publicationId` to GET /v1/benchmark/target/{targetKey} for that generation’s numbers. - [Get a benchmark target](https://docs.roark.ai/api-reference/benchmark/get-a-benchmark-target.md): Returns a target’s published sweep and every one of its aggregate cells: the overall rollup plus a set per condition. Defaults to the current sweep; pass `publicationId` from the history endpoint to read a superseded one, which is how a regression is compared generation to generation. Numbers only —… - [CLI Reference](https://docs.roark.ai/cli-reference/overview.md): Every roark command, generated from the same spec as the API - [roark health](https://docs.roark.ai/cli-reference/commands/health.md): Get API health status - [roark whoami](https://docs.roark.ai/cli-reference/commands/whoami.md): Describe the current credential - [roark agent build](https://docs.roark.ai/cli-reference/commands/agent-build.md): Build a Roark-hosted agent - [roark agent create](https://docs.roark.ai/cli-reference/commands/agent-create.md): Create a new agent - [roark agent get](https://docs.roark.ai/cli-reference/commands/agent-get.md): Get agent by ID - [roark agent list](https://docs.roark.ai/cli-reference/commands/agent-list.md): List agents - [roark agent update](https://docs.roark.ai/cli-reference/commands/agent-update.md): Update an agent - [roark agent draft create](https://docs.roark.ai/cli-reference/commands/agent-draft-create.md): Start a draft - [roark agent draft delete](https://docs.roark.ai/cli-reference/commands/agent-draft-delete.md): Discard the draft - [roark agent draft get](https://docs.roark.ai/cli-reference/commands/agent-draft-get.md): Get an agent's draft - [roark agent draft publish](https://docs.roark.ai/cli-reference/commands/agent-draft-publish.md): Publish the draft - [roark agent draft update](https://docs.roark.ai/cli-reference/commands/agent-draft-update.md): Edit the draft - [roark agent endpoint create](https://docs.roark.ai/cli-reference/commands/agent-endpoint-create.md): Create a new agent endpoint - [roark agent endpoint get](https://docs.roark.ai/cli-reference/commands/agent-endpoint-get.md): Get agent endpoint by ID - [roark agent endpoint list](https://docs.roark.ai/cli-reference/commands/agent-endpoint-list.md): List agent endpoints - [roark agent endpoint update](https://docs.roark.ai/cli-reference/commands/agent-endpoint-update.md): Update an agent endpoint - [roark agent prompt list](https://docs.roark.ai/cli-reference/commands/agent-prompt-list.md): List an agent's prompts - [roark agent prompt update](https://docs.roark.ai/cli-reference/commands/agent-prompt-update.md): Set an agent's prompt - [roark agent prompt version list](https://docs.roark.ai/cli-reference/commands/agent-prompt-version-list.md): List a prompt's versions - [roark agent version get](https://docs.roark.ai/cli-reference/commands/agent-version-get.md): Get an agent version - [roark agent version list](https://docs.roark.ai/cli-reference/commands/agent-version-list.md): List an agent's versions - [roark agent version rollback](https://docs.roark.ai/cli-reference/commands/agent-version-rollback.md): Roll an agent back to a version - [roark agent-config get](https://docs.roark.ai/cli-reference/commands/agent-config-get.md): Get a managed config - [roark agent-config list](https://docs.roark.ai/cli-reference/commands/agent-config-list.md): List managed configs - [roark agent-config promote](https://docs.roark.ai/cli-reference/commands/agent-config-promote.md): Promote staging to production - [roark agent-config resolve](https://docs.roark.ai/cli-reference/commands/agent-config-resolve.md): Resolve config for a session - [roark agent-config update](https://docs.roark.ai/cli-reference/commands/agent-config-update.md): Write a config revision - [roark agent-config staging delete](https://docs.roark.ai/cli-reference/commands/agent-config-staging-delete.md): Discard the staging revision - [roark analytics query](https://docs.roark.ai/cli-reference/commands/analytics-query.md): Run an analytics query - [roark analytics schema get](https://docs.roark.ai/cli-reference/commands/analytics-schema-get.md): Get the analytics schema - [roark autoimprove job answer](https://docs.roark.ai/cli-reference/commands/autoimprove-job-answer.md): Answer Roark's question - [roark autoimprove job cancel](https://docs.roark.ai/cli-reference/commands/autoimprove-job-cancel.md): Cancel a job - [roark autoimprove job create](https://docs.roark.ai/cli-reference/commands/autoimprove-job-create.md): Start an Autoimprove job - [roark autoimprove job dismiss](https://docs.roark.ai/cli-reference/commands/autoimprove-job-dismiss.md): Dismiss a verified job - [roark autoimprove job get](https://docs.roark.ai/cli-reference/commands/autoimprove-job-get.md): Get an Autoimprove job - [roark autoimprove job list](https://docs.roark.ai/cli-reference/commands/autoimprove-job-list.md): List Autoimprove jobs - [roark autoimprove job promote](https://docs.roark.ai/cli-reference/commands/autoimprove-job-promote.md): Promote a verified job to production - [roark autoimprove job guidance send](https://docs.roark.ai/cli-reference/commands/autoimprove-job-guidance-send.md): Send guidance to a running job - [roark benchmark leaderboard get](https://docs.roark.ai/cli-reference/commands/benchmark-leaderboard-get.md): Get the benchmark leaderboard - [roark benchmark metric list](https://docs.roark.ai/cli-reference/commands/benchmark-metric-list.md): List benchmark metrics - [roark benchmark suite list](https://docs.roark.ai/cli-reference/commands/benchmark-suite-list.md): List benchmark suites - [roark benchmark target get](https://docs.roark.ai/cli-reference/commands/benchmark-target-get.md): Get a benchmark target - [roark benchmark target history list](https://docs.roark.ai/cli-reference/commands/benchmark-target-history-list.md): List a target’s published generations - [roark benchmark target score-sample list](https://docs.roark.ai/cli-reference/commands/benchmark-target-score-sample-list.md): List score samples for a target - [roark call create](https://docs.roark.ai/cli-reference/commands/call-create.md): Create a call - [roark call delete](https://docs.roark.ai/cli-reference/commands/call-delete.md): Delete a call - [roark call get](https://docs.roark.ai/cli-reference/commands/call-get.md): Get a call by ID - [roark call list](https://docs.roark.ai/cli-reference/commands/call-list.md): List calls - [roark call batch delete](https://docs.roark.ai/cli-reference/commands/call-batch-delete.md): Delete calls in batch - [roark call cost get](https://docs.roark.ai/cli-reference/commands/call-cost-get.md): Get call cost - [roark call metric list](https://docs.roark.ai/cli-reference/commands/call-metric-list.md): List call metrics - [roark call property update](https://docs.roark.ai/cli-reference/commands/call-property-update.md): Update the properties of a call - [roark call sentiment-run list](https://docs.roark.ai/cli-reference/commands/call-sentiment-run-list.md): List call sentiment runs - [roark call tool-invocation append](https://docs.roark.ai/cli-reference/commands/call-tool-invocation-append.md): Append tool invocations to a call - [roark call transcript get](https://docs.roark.ai/cli-reference/commands/call-transcript-get.md): Get call transcript - [roark config apply](https://docs.roark.ai/cli-reference/commands/config-apply.md): Reconcile the project to a config directory (or bundle). Previews and confirms first. - [roark config diff](https://docs.roark.ai/cli-reference/commands/config-diff.md): Preview the changes a config directory (or bundle) would make. No writes. - [roark credential create](https://docs.roark.ai/cli-reference/commands/credential-create.md): Create a personal credential - [roark credential list](https://docs.roark.ai/cli-reference/commands/credential-list.md): List your personal credentials - [roark credential revoke](https://docs.roark.ai/cli-reference/commands/credential-revoke.md): Revoke one of your personal credentials - [roark customer-flow create](https://docs.roark.ai/cli-reference/commands/customer-flow-create.md): Create a customer flow - [roark customer-flow delete](https://docs.roark.ai/cli-reference/commands/customer-flow-delete.md): Delete a customer flow - [roark customer-flow duplicate](https://docs.roark.ai/cli-reference/commands/customer-flow-duplicate.md): Duplicate a customer flow - [roark customer-flow get](https://docs.roark.ai/cli-reference/commands/customer-flow-get.md): Get customer flow by ID - [roark customer-flow list](https://docs.roark.ai/cli-reference/commands/customer-flow-list.md): List customer flows - [roark customer-flow update](https://docs.roark.ai/cli-reference/commands/customer-flow-update.md): Update a customer flow - [roark customer-flow edge-case create](https://docs.roark.ai/cli-reference/commands/customer-flow-edge-case-create.md): Add an edge case - [roark customer-flow edge-case delete](https://docs.roark.ai/cli-reference/commands/customer-flow-edge-case-delete.md): Remove an edge case - [roark customer-flow edge-case promote](https://docs.roark.ai/cli-reference/commands/customer-flow-edge-case-promote.md): Promote an edge case to the happy path - [roark customer-flow edge-case update](https://docs.roark.ai/cli-reference/commands/customer-flow-edge-case-update.md): Update an edge case - [roark customer-flow graph replace](https://docs.roark.ai/cli-reference/commands/customer-flow-graph-replace.md): Replace a scripted flow's steps - [roark customer-flow happy-path update](https://docs.roark.ai/cli-reference/commands/customer-flow-happy-path-update.md): Update a flow's happy path - [roark dashboard create](https://docs.roark.ai/cli-reference/commands/dashboard-create.md): Create a dashboard - [roark dashboard delete](https://docs.roark.ai/cli-reference/commands/dashboard-delete.md): Delete a dashboard - [roark dashboard get](https://docs.roark.ai/cli-reference/commands/dashboard-get.md): Get a dashboard - [roark dashboard list](https://docs.roark.ai/cli-reference/commands/dashboard-list.md): List dashboards - [roark dashboard update](https://docs.roark.ai/cli-reference/commands/dashboard-update.md): Update a dashboard - [roark dashboard data get](https://docs.roark.ai/cli-reference/commands/dashboard-data-get.md): Get dashboard data - [roark dashboard widget create](https://docs.roark.ai/cli-reference/commands/dashboard-widget-create.md): Add a widget - [roark dashboard widget delete](https://docs.roark.ai/cli-reference/commands/dashboard-widget-delete.md): Remove a widget - [roark dashboard widget update](https://docs.roark.ai/cli-reference/commands/dashboard-widget-update.md): Replace a widget - [roark dashboard widget-data get](https://docs.roark.ai/cli-reference/commands/dashboard-widget-data-get.md): Get widget data - [roark http-request-definition create](https://docs.roark.ai/cli-reference/commands/http-request-definition-create.md): Create HTTP request definition - [roark http-request-definition get](https://docs.roark.ai/cli-reference/commands/http-request-definition-get.md): Get HTTP request definition by ID - [roark http-request-definition list](https://docs.roark.ai/cli-reference/commands/http-request-definition-list.md): List HTTP request definitions - [roark http-request-definition update](https://docs.roark.ai/cli-reference/commands/http-request-definition-update.md): Update HTTP request definition - [roark metric collection-job cancel](https://docs.roark.ai/cli-reference/commands/metric-collection-job-cancel.md): Cancel a metric collection job - [roark metric collection-job create](https://docs.roark.ai/cli-reference/commands/metric-collection-job-create.md): Create and run a metric collection job - [roark metric collection-job get](https://docs.roark.ai/cli-reference/commands/metric-collection-job-get.md): Get metric collection job by ID - [roark metric collection-job list](https://docs.roark.ai/cli-reference/commands/metric-collection-job-list.md): List metric collection jobs - [roark metric definition create](https://docs.roark.ai/cli-reference/commands/metric-definition-create.md): Create custom metric definition - [roark metric definition list](https://docs.roark.ai/cli-reference/commands/metric-definition-list.md): List metric definitions - [roark metric definition update](https://docs.roark.ai/cli-reference/commands/metric-definition-update.md): Update a metric definition - [roark metric policy create](https://docs.roark.ai/cli-reference/commands/metric-policy-create.md): Create a metric policy - [roark metric policy delete](https://docs.roark.ai/cli-reference/commands/metric-policy-delete.md): Delete a metric policy - [roark metric policy get](https://docs.roark.ai/cli-reference/commands/metric-policy-get.md): Get metric policy by ID - [roark metric policy list](https://docs.roark.ai/cli-reference/commands/metric-policy-list.md): List metric policies - [roark metric policy update](https://docs.roark.ai/cli-reference/commands/metric-policy-update.md): Update a metric policy - [roark metric variant create](https://docs.roark.ai/cli-reference/commands/metric-variant-create.md): Create a metric variant - [roark metric variant delete](https://docs.roark.ai/cli-reference/commands/metric-variant-delete.md): Delete a metric variant - [roark metric variant get](https://docs.roark.ai/cli-reference/commands/metric-variant-get.md): Get a metric variant - [roark metric variant list](https://docs.roark.ai/cli-reference/commands/metric-variant-list.md): List a metric’s variants - [roark metric variant update](https://docs.roark.ai/cli-reference/commands/metric-variant-update.md): Update a metric variant - [roark phone-number create](https://docs.roark.ai/cli-reference/commands/phone-number-create.md): Buy a phone number - [roark phone-number delete](https://docs.roark.ai/cli-reference/commands/phone-number-delete.md): Release a phone number - [roark phone-number list](https://docs.roark.ai/cli-reference/commands/phone-number-list.md): List phone numbers - [roark phone-number update](https://docs.roark.ai/cli-reference/commands/phone-number-update.md): Update a phone number - [roark phone-number allowance get](https://docs.roark.ai/cli-reference/commands/phone-number-allowance-get.md): Get the phone number allowance - [roark phone-number available list](https://docs.roark.ai/cli-reference/commands/phone-number-available-list.md): Search available phone numbers - [roark project list](https://docs.roark.ai/cli-reference/commands/project-list.md): List projects available to this credential - [roark simulation run](https://docs.roark.ai/cli-reference/commands/simulation-run.md): Run a simulation - [roark simulation environment create](https://docs.roark.ai/cli-reference/commands/simulation-environment-create.md): Create an environment - [roark simulation environment delete](https://docs.roark.ai/cli-reference/commands/simulation-environment-delete.md): Delete an environment - [roark simulation environment get](https://docs.roark.ai/cli-reference/commands/simulation-environment-get.md): Get environment by ID - [roark simulation environment list](https://docs.roark.ai/cli-reference/commands/simulation-environment-list.md): List environments - [roark simulation environment update](https://docs.roark.ai/cli-reference/commands/simulation-environment-update.md): Update an environment - [roark simulation group create](https://docs.roark.ai/cli-reference/commands/simulation-group-create.md): Create a simulation group - [roark simulation group delete](https://docs.roark.ai/cli-reference/commands/simulation-group-delete.md): Delete a simulation group - [roark simulation group get](https://docs.roark.ai/cli-reference/commands/simulation-group-get.md): Get a simulation group - [roark simulation group list](https://docs.roark.ai/cli-reference/commands/simulation-group-list.md): List simulation groups - [roark simulation group run](https://docs.roark.ai/cli-reference/commands/simulation-group-run.md): Run a simulation group - [roark simulation group update](https://docs.roark.ai/cli-reference/commands/simulation-group-update.md): Update a simulation group - [roark simulation job get](https://docs.roark.ai/cli-reference/commands/simulation-job-get.md): Get simulation by ID - [roark simulation job lookup](https://docs.roark.ai/cli-reference/commands/simulation-job-lookup.md): Lookup by phone number - [roark simulation job tool-mock list](https://docs.roark.ai/cli-reference/commands/simulation-job-tool-mock-list.md): List mocked tool invocations - [roark simulation persona create](https://docs.roark.ai/cli-reference/commands/simulation-persona-create.md): Create a new persona - [roark simulation persona get](https://docs.roark.ai/cli-reference/commands/simulation-persona-get.md): Get persona by ID - [roark simulation persona list](https://docs.roark.ai/cli-reference/commands/simulation-persona-list.md): List personas - [roark simulation persona update](https://docs.roark.ai/cli-reference/commands/simulation-persona-update.md): Update a persona - [roark simulation plan create](https://docs.roark.ai/cli-reference/commands/simulation-plan-create.md): Create a run plan - [roark simulation plan delete](https://docs.roark.ai/cli-reference/commands/simulation-plan-delete.md): Delete a run plan - [roark simulation plan get](https://docs.roark.ai/cli-reference/commands/simulation-plan-get.md): Get run plan by ID - [roark simulation plan list](https://docs.roark.ai/cli-reference/commands/simulation-plan-list.md): List run plans - [roark simulation plan update](https://docs.roark.ai/cli-reference/commands/simulation-plan-update.md): Update a run plan - [roark simulation plan job cancel](https://docs.roark.ai/cli-reference/commands/simulation-plan-job-cancel.md): Cancel a simulation plan job - [roark simulation plan job get](https://docs.roark.ai/cli-reference/commands/simulation-plan-job-get.md): Get simulation plan job - [roark simulation plan job list](https://docs.roark.ai/cli-reference/commands/simulation-plan-job-list.md): List simulation plan jobs - [roark simulation plan job start](https://docs.roark.ai/cli-reference/commands/simulation-plan-job-start.md): Run a simulation plan - [roark simulation plan job cost get](https://docs.roark.ai/cli-reference/commands/simulation-plan-job-cost-get.md): Get simulation run cost - [roark simulation plan job debrief create](https://docs.roark.ai/cli-reference/commands/simulation-plan-job-debrief-create.md): Generate simulation run debrief - [roark simulation plan job result get](https://docs.roark.ai/cli-reference/commands/simulation-plan-job-result-get.md): Get simulation run results - [roark simulation run-group create](https://docs.roark.ai/cli-reference/commands/simulation-run-group-create.md): Create a run group - [roark simulation run-group delete](https://docs.roark.ai/cli-reference/commands/simulation-run-group-delete.md): Delete a run group - [roark simulation run-group get](https://docs.roark.ai/cli-reference/commands/simulation-run-group-get.md): Get a run group - [roark simulation run-group list](https://docs.roark.ai/cli-reference/commands/simulation-run-group-list.md): List run groups - [roark simulation run-group report regenerate](https://docs.roark.ai/cli-reference/commands/simulation-run-group-report-regenerate.md): Regenerate a run group report - [roark simulation template list](https://docs.roark.ai/cli-reference/commands/simulation-template-list.md): List simulation templates - [roark simulation tool mock](https://docs.roark.ai/cli-reference/commands/simulation-tool-mock.md): Mock a tool call during a test call - [roark simulation tool-fixture create](https://docs.roark.ai/cli-reference/commands/simulation-tool-fixture-create.md): Set a tool fixture - [roark simulation tool-fixture delete](https://docs.roark.ai/cli-reference/commands/simulation-tool-fixture-delete.md): Delete a tool fixture - [roark simulation tool-fixture list](https://docs.roark.ai/cli-reference/commands/simulation-tool-fixture-list.md): List tool fixtures - [roark simulation tool-fixture update](https://docs.roark.ai/cli-reference/commands/simulation-tool-fixture-update.md): Update a tool fixture - [roark usage get](https://docs.roark.ai/cli-reference/commands/usage-get.md): Get usage & cost - [roark webhook create](https://docs.roark.ai/cli-reference/commands/webhook-create.md): Create webhook - [roark webhook delete](https://docs.roark.ai/cli-reference/commands/webhook-delete.md): Delete webhook - [roark webhook get](https://docs.roark.ai/cli-reference/commands/webhook-get.md): Get webhook by ID - [roark webhook list](https://docs.roark.ai/cli-reference/commands/webhook-list.md): List webhooks ## OpenAPI Specs - [openapi.documented](/api-reference/openapi.documented.json) ## Optional - [Changelog](https://changelog.roark.ai) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.