> For the complete documentation index, see [llms.txt](https://docs.amigo.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.amigo.ai/developer-guide/platform-api.md). # Platform API - [Platform API Overview](https://docs.amigo.ai/developer-guide/platform-api/platform-api.md): Platform API reference for voice agents, EHR integration, operators, FHIR, and safety monitoring. - [Authentication & API Keys](https://docs.amigo.ai/developer-guide/platform-api/platform-api/authentication.md): Authenticate to the Platform API with workspace keys or device authorization, inspect the live permission catalog, and rotate or revoke credentials safely. - [OAuth2 (Machine-to-Machine)](https://docs.amigo.ai/developer-guide/platform-api/platform-api/oauth2.md): Machine-to-machine OAuth2 client credentials flow for programmatic access to the Platform API. - [OAuth2 Clients](https://docs.amigo.ai/developer-guide/platform-api/platform-api/oauth2-clients.md): Understand provisioned OAuth2 clients used for machine-to-machine authentication with the client\_credentials grant. - [Sessions](https://docs.amigo.ai/developer-guide/platform-api/platform-api/sessions.md): Persistent WebSocket endpoint for text conversations with streamed agent responses. - [Pagination](https://docs.amigo.ai/developer-guide/platform-api/platform-api/pagination.md): How Platform API list endpoints paginate - continuation-token pagination for resource lists and limit/offset for analytics and audit endpoints. - [Health](https://docs.amigo.ai/developer-guide/platform-api/platform-api/health.md): Health check endpoints for monitoring platform subsystem status, including whether feature-flag rollouts are live. - [Workspaces](https://docs.amigo.ai/developer-guide/platform-api/workspaces.md): Manage workspaces: tenant isolation, voice settings, speech recognition, and test caller numbers. - [Agents](https://docs.amigo.ai/developer-guide/platform-api/workspaces/agents.md): Define agent identity, voice, background, and behaviors with immutable versioning in the Platform API. - [Skills](https://docs.amigo.ai/developer-guide/platform-api/workspaces/skills.md): Configure LLM-backed micro-agent capabilities with system prompts, schemas, and tool access. - [Services](https://docs.amigo.ai/developer-guide/platform-api/workspaces/services.md): Bind agents and context graphs into deployable services, manage version sets, and configure voice behavior for conversations across supported channels. - [Use Cases & Bindings](https://docs.amigo.ai/developer-guide/platform-api/workspaces/use-cases.md): List channel use cases for voice, SMS, iMessage, and email, and bind each use case to the platform service that handles its conversations. - [Scheduling Rule Sets](https://docs.amigo.ai/developer-guide/platform-api/workspaces/scheduling-rule-sets.md): Configure deterministic scheduling rules that filter appointment slots before they reach the agent. - [Voice Configuration](https://docs.amigo.ai/developer-guide/platform-api/workspaces/voice-configuration.md): Configure per-service voice latency, fillers, barge-in, response limits, provider inheritance, call forwarding, and conversation tool availability. - [Client Config](https://docs.amigo.ai/developer-guide/platform-api/workspaces/client-config.md): Retrieve client-safe configuration values for embedding in browser-side applications. - [Scribe](https://docs.amigo.ai/developer-guide/platform-api/scribe.md): Access provider-owned clinical documentation sessions, then retrieve or generate transcripts, notes, summaries, checklists, and coding suggestions. - [Sessions](https://docs.amigo.ai/developer-guide/platform-api/scribe/sessions.md): List and retrieve provider-owned clinical documentation sessions with lifecycle state and transcript, note, summary, and coding artifact availability. - [Artifacts](https://docs.amigo.ai/developer-guide/platform-api/scribe/artifacts.md): Retrieve Scribe transcripts and coding suggestions, then generate, read, and finalize clinical notes, summaries, and evidence-backed checklists. - [Conversations](https://docs.amigo.ai/developer-guide/platform-api/conversations.md): Create, inspect, continue, switch, and close durable agent conversations over REST or WebSocket while preserving cross-channel history and state. - [Runs](https://docs.amigo.ai/developer-guide/platform-api/conversations/runs.md): Browse conversation runs and best-effort projected framework history, inspect structural trajectories, and control channel-aware operator takeover by run ID. - [Channels](https://docs.amigo.ai/developer-guide/platform-api/conversations/channels.md): Internal-preview channels - email, SMS, iMessage, and WhatsApp - and how agents deliver long-running tool results on non-live channels. - [Channel Manager](https://docs.amigo.ai/developer-guide/platform-api/conversations/channel-manager.md): Manage workspace communication channel setup and use case provisioning. - [Calls](https://docs.amigo.ai/developer-guide/platform-api/conversations/calls.md): Start outbound voice calls with explicit service routing, startup instructions, retry correlation, and best-effort patient lineage. - [Voice Agent](https://docs.amigo.ai/developer-guide/platform-api/conversations/voice-agent.md): Understand the real-time voice pipeline, context graph execution, tool calls, emotion adaptation, operator takeover, recordings, and post-call analysis. - [Desktop Sessions](https://docs.amigo.ai/developer-guide/platform-api/conversations/desktop-sessions.md): The remote desktop session endpoints have been removed from the Platform API. - [Voicemail](https://docs.amigo.ai/developer-guide/platform-api/conversations/voicemail.md): Send ringless voicemail drops and track their delivery status through channel use cases. - [SMS](https://docs.amigo.ai/developer-guide/platform-api/conversations/sms.md): Send SMS messages and track delivery status through the SMS channel. - [Surfaces](https://docs.amigo.ai/developer-guide/platform-api/conversations/surfaces.md): Agent-generated data collection interfaces: SurfaceSpec, fields, channels, lifecycle, and submission handling. - [Operators](https://docs.amigo.ai/developer-guide/platform-api/conversations/operators.md): Human-in-the-loop call monitoring, takeover, escalation management, and operator analytics. - [SSE Events](https://docs.amigo.ai/developer-guide/platform-api/conversations/sse-events.md): Real-time workspace event stream delivered via Server-Sent Events (SSE). - [Observer Events](https://docs.amigo.ai/developer-guide/platform-api/conversations/observer-events.md): Real-time event types delivered over the observer WebSocket connection during a voice session. - [Serve an Agent From a Web App](https://docs.amigo.ai/developer-guide/platform-api/conversations/serve-agent-from-web-app.md): Serve a Platform agent from a customer web application using External Integration credentials and external-user session tokens. - [Platform Functions](https://docs.amigo.ai/developer-guide/platform-api/functions.md): Register, invoke, test, list, and delete workspace SQL, Python, AI, and UDTF functions for governed agent data access and computation during conversations. - [Workspace Data Queries](https://docs.amigo.ai/developer-guide/platform-api/functions/workspace-data-queries.md): Register, manage, and invoke parameterized SQL queries against workspace custom tables. - [Tool Testing](https://docs.amigo.ai/developer-guide/platform-api/functions/tool-testing.md): Test context graph tools without starting a phone call. Resolve available tools, execute world tools, and understand test-mode persistence. - [Triggers](https://docs.amigo.ai/developer-guide/platform-api/functions/triggers.md): Dispatch workspace actions from cron schedules, matching live events, or authenticated manual fire requests, with durable run history. - [MCP Server](https://docs.amigo.ai/developer-guide/platform-api/functions/mcp-server.md): The workspace-scoped Model Context Protocol server built into the Platform API - world-model read tools for MCP clients and partner agents. - [Agent Runs](https://docs.amigo.ai/developer-guide/platform-api/functions/agent-runs.md): Dispatch and poll framework agent runs that execute unmodified against the platform world-tools surface. - [Harness Context](https://docs.amigo.ai/developer-guide/platform-api/functions/harness-context.md): Retrieve the neutral session-bootstrap context for a service so your own framework can bootstrap against the same world model the hosted runner uses. - [Agent Definitions](https://docs.amigo.ai/developer-guide/platform-api/functions/agent-definitions.md): Register, version, validate, and manage native agent definitions within a workspace. - [Integrations](https://docs.amigo.ai/developer-guide/platform-api/integrations.md): Connect workspaces to REST APIs with managed credentials, endpoint definitions, and isolated endpoint tests. - [Approval-Gated Integration Writes](https://docs.amigo.ai/developer-guide/platform-api/integrations/approval-gated-integration-writes.md): Require human approval before an agent performs an integration write. Approved writes resume on the agent's next turn across streaming chat, REST, and SMS. - [Review Queue](https://docs.amigo.ai/developer-guide/platform-api/integrations/review-queue.md): Manage private-preview external write proposals: inspect staged connector payloads, approve or reject delivery, and monitor each proposal through final status. - [External Integrations](https://docs.amigo.ai/developer-guide/platform-api/integrations/external-integrations.md): Manage external integration credentials for scoped third-party access to external user session creation. - [External Principals](https://docs.amigo.ai/developer-guide/platform-api/integrations/external-principals.md): Provision role assignments and grants for entity-anchored external principals, then start tightly scoped sessions through a trusted backend. - [External User Subject-Key Binding](https://docs.amigo.ai/developer-guide/platform-api/integrations/external-user-subject-key-binding.md): Bind a backend-verified external-user subject into integration token exchange without allowing the model or browser input to choose that identity. - [Data & World Model](https://docs.amigo.ai/developer-guide/platform-api/data-world-model.md): Query and manage workspace entities, enrichment, provenance, confidence-gated writes, migration metadata, data sources, and synchronization status. - [Bulk Import (Migration)](https://docs.amigo.ai/developer-guide/platform-api/data-world-model/bulk-import.md): Bulk-import terminal Classic conversation metadata for migrated person entities. - [Entity Resolve](https://docs.amigo.ai/developer-guide/platform-api/data-world-model/entity-resolve.md): Resolve a polymorphic identifier to ranked entity candidates. - [Workspace Tables](https://docs.amigo.ai/developer-guide/platform-api/data-world-model/workspace-tables.md): Create, manage, and query workspace-owned custom data tables. - [Customer Data Intake](https://docs.amigo.ai/developer-guide/platform-api/data-world-model/intake.md): Register governed intake datasets, upload and download catalog files, refresh mapped Drive sources, and monitor durable dataset processing and update runs. - [Intake Sources](https://docs.amigo.ai/developer-guide/platform-api/data-world-model/intake-sources.md): Register Google Drive folder mappings, trigger explicit source syncs, inspect returned batches, and coordinate secure out-of-band source credential setup. - [Intake Upload Links](https://docs.amigo.ai/developer-guide/platform-api/data-world-model/intake-links.md): Create and revoke bearer-token upload links, receive allowlisted files without user login, and list or download link-scoped uploads safely by workspace. - [Connector Runner](https://docs.amigo.ai/developer-guide/platform-api/data-world-model/connector-runner.md): Supported EHR, FHIR, REST, and workspace-data ingestion, plus policy-gated external delivery, observability, and outbound call dispatch. - [FHIR](https://docs.amigo.ai/developer-guide/platform-api/data-world-model/fhir.md): FHIR endpoints for patient search, clinical timelines, resource CRUD, and bundle import. - [Data Access (MCP)](https://docs.amigo.ai/developer-guide/platform-api/data-world-model/data-mcp.md): Query organization data through the Model Context Protocol using SQL tools compatible with any MCP client. - [Safety & Monitoring](https://docs.amigo.ai/developer-guide/platform-api/safety.md): Agent safety guidance, supported audit and PHI-access evidence, configured retention policy, and compliance reporting boundaries. - [Analytics & Observability](https://docs.amigo.ai/developer-guide/platform-api/safety/analytics.md): Analyze call quality, production evaluations, operational health, recordings, event streams, and external-write review activity across a workspace. - [Insights](https://docs.amigo.ai/developer-guide/platform-api/safety/insights.md): Query workspace data, explore schema metadata, and get health digests through the platform insights endpoints. - [Metric Store](https://docs.amigo.ai/developer-guide/platform-api/safety/metric-store.md): Manage metric definitions and query recent or durable production and simulation metric values. - [Call Trace Analysis](https://docs.amigo.ai/developer-guide/platform-api/safety/call-trace-analysis.md): Deep call understanding with emotional arcs, key decision moments, coaching recommendations, and signal-response alignment. - [Voice Judge](https://docs.amigo.ai/developer-guide/platform-api/safety/voice-judge.md): Retrieve audio-native voice quality scores for your voice agent calls. - [Production Evals](https://docs.amigo.ai/developer-guide/platform-api/safety/production-evals.md): Define eval criteria for production calls and evaluate completed calls against them. - [Simulation Coverage](https://docs.amigo.ai/developer-guide/platform-api/safety/simulation-coverage.md): Explore context graph coverage, fork and score text simulations, aggregate per-conversation verdicts, and run saved-case benchmarks with source-tagged writes. - [Prompt Logs](https://docs.amigo.ai/developer-guide/platform-api/safety/prompt-logs.md): Query LLM prompt logs for auditing and debugging agent conversations across a workspace. - [Trace Export](https://docs.amigo.ai/developer-guide/platform-api/safety/trace-export.md): Export durable tool-call and supported voice operational spans as OTLP/JSON for external observability collectors. - [Platform SDK](https://docs.amigo.ai/developer-guide/platform-api/platform-sdk.md): Use the official TypeScript SDK for typed workspace resources, unified runs, streaming conversations, retries, errors, analytics, and configuration. - [Installation](https://docs.amigo.ai/developer-guide/platform-api/platform-sdk/installation.md): Install the Platform SDK with npm or yarn and configure TypeScript for type-safe API access. - [Configuration](https://docs.amigo.ai/developer-guide/platform-api/platform-sdk/configuration.md): Configure the Platform SDK client with API keys, workspace ID, and optional base URL overrides. - [Quickstart](https://docs.amigo.ai/developer-guide/platform-api/platform-sdk/quickstart.md): Common Platform SDK operations: agents, services, simulations, analytics, streaming, and entities. - [Error Handling](https://docs.amigo.ai/developer-guide/platform-api/platform-sdk/error-handling.md): Handle API errors with typed exceptions and built-in retry logic in the Platform SDK. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.amigo.ai/developer-guide/platform-api.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.