# Amigo Documentation

## Concepts

- [Welcome](https://docs.amigo.ai/readme.md): Healthcare AI platform with an event-sourced data foundation, multi-channel agent engine, EHR connectors, and operator workflows.
- [What Amigo Does](https://docs.amigo.ai/platform-overview/what-amigo-does.md): A concrete scenario showing how Amigo handles patient contact, source-aware data capture, and separately confirmed external delivery.
- [How It Works](https://docs.amigo.ai/platform-overview/how-it-works.md): Walk through a complete interaction lifecycle from patient contact to post-call analysis, mapping each step to real system components.
- [Design Principles](https://docs.amigo.ai/platform-overview/design-principles.md): Four engineering principles for measurement, composition, risk-calibrated autonomy, and goal-oriented workflows.
- [Deployment Model](https://docs.amigo.ai/platform-overview/deployment-model.md): A phased operating model for baseline definition, candidate validation, version-set release control, and workspace isolation.
- [Data Residency](https://docs.amigo.ai/platform-overview/data-residency.md): Regional workspace placement, immutable region selection, and practical planning considerations for regulated deployments.
- [Cost and Latency Optimization](https://docs.amigo.ai/platform-overview/cost-and-latency.md): How prompt caching, model routing, and pipeline design keep costs low and responses fast.
- [Agent Core](https://docs.amigo.ai/agent/agents.md): Versioned agent identity, background, behavioral guidance, communication patterns, and voice configuration.
- [Reasoning Engine](https://docs.amigo.ai/agent/reasoning-engine.md): The modality-independent reasoning core that processes signals and emits effects, powering voice, text, simulation, and API agent interactions through a unified pipeline.
- [Context Graphs](https://docs.amigo.ai/agent/context-graphs.md): Structured state machines that define conversation flow, decision points, and safety boundaries for agent workflows.
- [Dynamic Behaviors](https://docs.amigo.ai/agent/context-graphs/dynamic-behaviors.md): Classic API dynamic behavior sets, including semantic triggers, instruction injection, tool changes, versioning, and Platform API alternatives.
- [Memory](https://docs.amigo.ai/agent/memory.md): How conversation-derived observations, semantic user models, and structured clinical context become source-linked memory for later sessions.
- [Clinical Tools](https://docs.amigo.ai/agent/clinical-tools.md): Current built-in world tools for patient lookup, scheduling, clinical reads, and source-attributed writes.
- [Platform Functions](https://docs.amigo.ai/agent/platform-functions.md): Workspace-registered SQL, AI, Python, and table-valued functions for governed data retrieval and computation.
- [Continuous Improvement](https://docs.amigo.ai/agent/pattern-discovery-and-reuse.md): Use production evidence, simulations, and versioned releases to improve agent behavior through an explicit, governed team workflow.
- [Overview](https://docs.amigo.ai/channels/conversations.md): A shared reasoning engine powers voice, text, email, and web-based data collection with channel-specific delivery and control capabilities.
- [Phone](https://docs.amigo.ai/channels/voice.md): Real-time phone-based conversations with conference-first architecture, emotion detection, and adaptive voice delivery.
- [Audio Pipeline](https://docs.amigo.ai/channels/voice/audio-pipeline.md): How speech recognition, emotion detection, filler speech, barge-in detection, and TTS work together in real time.
- [Emotion Detection](https://docs.amigo.ai/channels/voice/emotion-detection.md): How acoustic emotion scores, transcript analysis, rolling state, empathy tiers, and voice steering work in the live voice runtime.
- [Compound Emotions](https://docs.amigo.ai/channels/voice/compound-emotions.md): How the five-turn resolver produces scored compound-emotion signals from acoustic, transcript, and behavioral evidence.
- [Call Recordings](https://docs.amigo.ai/channels/voice/recordings.md): Workspace-scoped call recordings with separate participant channels, synchronized playback, metadata, and waveform support.
- [Text Sessions](https://docs.amigo.ai/channels/text-sessions.md): Durable text conversations over the web API, SMS, iMessage, WhatsApp, and email, with channel-specific delivery behavior.
- [SMS](https://docs.amigo.ai/channels/sms.md): SMS channel for outbound and inbound text messaging through provisioned phone numbers.
- [WhatsApp](https://docs.amigo.ai/channels/whatsapp.md): WhatsApp supports durable text turns and separate voice-note turns through distinct service APIs and continuity models.
- [iMessage](https://docs.amigo.ai/channels/imessage.md): iMessage channel for patient communication through Apple's messaging platform.
- [Email](https://docs.amigo.ai/channels/email.md): Email channel with domain verification, inbound reply handling, thread continuity, and transactional and marketing use cases.
- [Voicemail](https://docs.amigo.ai/channels/voicemail.md): Ringless voicemail delivery for non-intrusive outreach like appointment reminders and follow-up notifications.
- [Surfaces](https://docs.amigo.ai/channels/surfaces.md): Agent-generated data collection interfaces delivered by email or web, with templates, progress tracking, and pending appointment requests.
- [Outbound](https://docs.amigo.ai/channels/outbound.md): Source-backed outbound paths for SMS and iMessage conversations, direct voice calls, scheduled voice tasks, and managed voicemail delivery.
- [World Model](https://docs.amigo.ai/data/world-model.md): Event-sourced data layer that accepts supported healthcare inputs, preserves provenance and confidence, and projects current entity state.
- [Connectors and EHR](https://docs.amigo.ai/data/connectors-and-ehr.md): Data pipelines that ingest supported healthcare sources and deliver eligible world-model events to configured external destinations.
- [Customer Data Intake](https://docs.amigo.ai/data/customer-data-intake.md): Workspace-scoped dataset ingestion and token-based file collection, with separate storage, processing, security, and rollout boundaries for each path.
- [Workspaces](https://docs.amigo.ai/data/workspaces.md): Tenant isolation boundaries with separate world models, data sources, voice configs, and role-based access control.
- [Review Queue](https://docs.amigo.ai/data/review-queue.md): Human approval workflow for proposed writes to external clinical systems, with explicit decisions, delivery status, and audit history.
- [Data Access (MCP)](https://docs.amigo.ai/data/data-mcp.md): Standalone MCP service for read-only SQL exploration using Classic API organization credentials.
- [Operators and Escalation](https://docs.amigo.ai/operations-and-safety/operators.md): Human operators monitor live interactions from Runs, take over when needed, and hand control back to the agent.
- [Runtime Safety](https://docs.amigo.ai/operations-and-safety/runtime-safety.md): Current runtime safety controls, their enforcement boundaries, operator intervention, and evidence-based release practices.
- [Compliance and Audit](https://docs.amigo.ai/operations-and-safety/compliance.md): Authentication, access control, audit evidence, workspace isolation, outbound authorization, and assurance boundaries for regulated healthcare environments.
- [Intelligence Overview](https://docs.amigo.ai/intelligence-and-analytics/intelligence.md): Per-interaction evidence, workspace analytics, dashboards, metric values, and the boundaries that determine their availability.
- [Call Intelligence](https://docs.amigo.ai/intelligence-and-analytics/intelligence/call-intelligence.md): Terminal voice-call evidence, operational quality scoring, optional audio analysis, decision traces, and playback timelines.
- [Analytics and Dashboards](https://docs.amigo.ai/intelligence-and-analytics/intelligence/analytics-dashboards.md): Workspace analytics, pipeline observability, entity inspection, dashboards, and the Insights Agent - with their freshness and evidence boundaries.
- [Proactive Journeys](https://docs.amigo.ai/intelligence-and-analytics/intelligence/proactive-journeys.md): Sample-data preview of proactive journey observability covering signal, outreach, conversation, evaluation, and outcome evidence.
- [Metric Store](https://docs.amigo.ai/intelligence-and-analytics/metric-store.md): The current metric catalog, custom-definition boundaries, dashboard behavior, query surface, and freshness semantics.
- [Testing Overview](https://docs.amigo.ai/testing/testing.md): Simulations, interactive testing, voice-path checks, metrics, and trend review support deliberate verification before and after deployment.
- [Simulations](https://docs.amigo.ai/testing/testing/simulations.md): Test agents against synthetic personas and scenarios through the production reasoning path with source-tagged effect isolation.
- [Playground and Interactive Testing](https://docs.amigo.ai/testing/testing/playground.md): Test agents interactively in the Developer Console playground through voice or text, with optional inspection panels and related testing workflows.
- [Voice Simulation](https://docs.amigo.ai/testing/testing/voice-simulation.md): Separate text-tier reasoning and tool coverage from real-audio tests of transcription, speech, turn-taking, latency, and transport health.
- [Metrics and Quality](https://docs.amigo.ai/testing/testing/metrics.md): Define multi-objective evaluation criteria and use their results in customer-owned release checks and improvement targets.
- [Drift Detection](https://docs.amigo.ai/testing/testing/drift-detection.md): Detect gradual performance changes by comparing metric trends, production examples, and simulation baselines through a deliberate monitoring workflow.
- [Healthcare Overview](https://docs.amigo.ai/use-cases/use-cases.md): Healthcare workflow patterns showing how agents, data, channels, testing, and external integrations can be composed.
- [Patient Scheduling and Outreach](https://docs.amigo.ai/use-cases/use-cases/scheduling-outreach.md): End-to-end patient scheduling and outbound outreach workflow, from clinical data loading through interaction completion and policy-gated external updates.
- [Care Coordination](https://docs.amigo.ai/use-cases/use-cases/care-coordination.md): Multi-encounter care coordination with cross-session memory, world model data unification, and personalized patient interactions.
- [Clinical Verification](https://docs.amigo.ai/use-cases/use-cases/clinical-verification.md): Build clinical-safety evidence with representative simulations, customer-owned release criteria, and qualified human review.
- [Population Health](https://docs.amigo.ai/use-cases/use-cases/population-health.md): A configuration pattern for population outreach, plus the boundaries of the synthetic Sensorium population-health demo.
- [Healthcare Contact Center](https://docs.amigo.ai/use-cases/use-cases/contact-center.md): How Amigo maps voice, text, operator, analytics, and data-collection capabilities onto contact-center workflows.
- [Glossary](https://docs.amigo.ai/reference/glossary.md): Definitions of key platform terms - from acceptance regions and actions to world model and workspaces.
- [API Terminology Mapping](https://docs.amigo.ai/reference/api-terminology-mapping.md): Map conceptual documentation terms to current Classic and Platform API resource names.
- [Agent Forge CLI](https://docs.amigo.ai/reference/agent-forge.md): Agent Forge CLI for syncing, versioning, and promoting agent configuration, with current Go and legacy Python build coverage.
- [Performance Characteristics](https://docs.amigo.ai/reference/performance.md): How to interpret voice latency, scaling, emotion-analysis windows, API rate limits, and post-call processing behavior.

## Developer Guide

- [Welcome](https://docs.amigo.ai/developer-guide/readme.md): Get started with the Amigo AI platform APIs: Classic for text-based digital health, Platform for enterprise voice and healthcare.
- [Getting Started](https://docs.amigo.ai/developer-guide/getting-started.md): Prerequisites, core documentation links, and quick start paths for both Classic and Platform APIs.
- [Core Concepts](https://docs.amigo.ai/developer-guide/getting-started/core-concepts.md): Understand the building blocks of both APIs: users, services, conversations, tools, workspaces, and skills.
- [Authentication](https://docs.amigo.ai/developer-guide/getting-started/authentication.md): Set up API key authentication and understand the two auth methods for Classic and Platform APIs.
- [Regions & Endpoints](https://docs.amigo.ai/developer-guide/getting-started/regions-and-endpoints.md): Configure regional base URLs for both APIs, LLM availability by region, and dedicated cluster headers.
- [Guides](https://docs.amigo.ai/developer-guide/guides.md): End-to-end playbooks for building production agents on the Amigo platform.
- [Build a KB Agent End to End](https://docs.amigo.ai/developer-guide/guides/build-a-kb-agent-end-to-end.md): Build a role-scoped knowledge-base agent end to end: load your data, assign roles, build the agent, test it, and manage it over time.
- [KB Agent: Retrieval & Build Methodology](https://docs.amigo.ai/developer-guide/guides/building-a-knowledge-base-agent.md): How to choose a retrieval architecture for a knowledge-base agent, and a measurement-driven process for building one.
- [Classic API](https://docs.amigo.ai/developer-guide/classic-api/core-api.md): Classic API reference for text-based conversations, user management, tools, simulations, and metrics.
- [Organization](https://docs.amigo.ai/developer-guide/classic-api/core-api/organization.md): Create, modify, and delete organizations. Manage user dimensions and branding configuration.
- [Agents & Context Graphs](https://docs.amigo.ai/developer-guide/classic-api/core-api/agents-and-context-graphs.md): Define agent personas and versioned context graphs (state machines) that power conversation flows.
- [Users](https://docs.amigo.ai/developer-guide/classic-api/core-api/users.md): Create, list, update, and delete users. Manage variables, memories, and authentication tokens.
- [User Models](https://docs.amigo.ai/developer-guide/classic-api/core-api/users/user-models.md): Read and update Amigo-managed user models with additional context from your systems.
- [Services](https://docs.amigo.ai/developer-guide/classic-api/core-api/services.md): Discover, create, and manage services with version sets, dynamic behaviors, and deployment routing.
- [Conversations](https://docs.amigo.ai/developer-guide/classic-api/core-api/conversations.md): Core conversation API for creating, interacting with, and managing AI-powered conversations.
- [Create](https://docs.amigo.ai/developer-guide/classic-api/core-api/conversations/conversations-create.md): Initialize conversations with agent-first, user-first, or external-event message types.
- [Interact](https://docs.amigo.ai/developer-guide/classic-api/core-api/conversations/conversations-interact.md): Send user messages to active conversations and process streaming NDJSON responses.
- [Events](https://docs.amigo.ai/developer-guide/classic-api/core-api/conversations/conversations-events.md): NDJSON event types for conversation streams: messages, actions, errors, and audio fillers.
- [Lifecycle & Finish](https://docs.amigo.ai/developer-guide/classic-api/core-api/conversations/conversations-lifecycle.md): Manage conversation states, finish sessions manually or automatically, and handle dangling conversations.
- [Starters](https://docs.amigo.ai/developer-guide/classic-api/core-api/conversations/conversations-starters.md): Generate contextual conversation starter prompts for UI widgets and onboarding flows.
- [Voice](https://docs.amigo.ai/developer-guide/classic-api/core-api/conversations/conversations-voice.md): Voice note exchange over HTTP and real-time WebSocket voice with audio filler management.
- [Real-time Voice (WebSocket)](https://docs.amigo.ai/developer-guide/classic-api/core-api/conversations/conversations-realtime.md): WebSocket API for low-latency bidirectional voice with VAD, interruption, and streaming TTS.
- [External Events & Multi-Stream (WebSocket)](https://docs.amigo.ai/developer-guide/classic-api/core-api/conversations/conversations-realtime-external-events.md): Send external events alongside user input on WebSocket connections for multi-stream apps.
- [Conversation History](https://docs.amigo.ai/developer-guide/classic-api/core-api/conversations/conversation-history.md): Retrieve conversation history, messages, audio sources, tags, response recommendations, and insights.
- [Tools](https://docs.amigo.ai/developer-guide/classic-api/core-api/tools.md): Create, publish, version, and invoke organization-scoped tools with environment variables and Git integration.
- [Dynamic Behaviors](https://docs.amigo.ai/developer-guide/classic-api/core-api/dynamic-behaviors.md): Create trigger-based behavior sets that inject instructions or modify tool availability during conversations.
- [Metrics](https://docs.amigo.ai/developer-guide/classic-api/core-api/metrics.md): Define and evaluate conversation quality metrics (boolean, numerical, or categorical) with automated scoring.
- [Simulations](https://docs.amigo.ai/developer-guide/classic-api/core-api/simulations.md): Automated agent testing with personas, scenarios, unit tests, and configurable success criteria.
- [Personas](https://docs.amigo.ai/developer-guide/classic-api/core-api/simulations/simulation-personas.md): Create and version simulated user profiles with background, role, and language for testing.
- [Scenarios](https://docs.amigo.ai/developer-guide/classic-api/core-api/simulations/simulation-scenarios.md): Define conversation test scripts with objectives, instructions, and initial message types.
- [Unit Tests](https://docs.amigo.ai/developer-guide/classic-api/core-api/simulations/simulation-unit-tests.md): Combine a persona, scenario, service, and success criteria into a single repeatable test case.
- [Unit Test Sets](https://docs.amigo.ai/developer-guide/classic-api/core-api/simulations/simulation-unit-test-sets.md): Group unit tests into suites with configurable run counts for batch execution.
- [Unit Test Set Runs](https://docs.amigo.ai/developer-guide/classic-api/core-api/simulations/simulation-unit-test-set-runs.md): Execute test suites, monitor progress, cancel runs, and download result artifacts.
- [Admin](https://docs.amigo.ai/developer-guide/classic-api/core-api/admin.md): Administrative endpoints for listing available LLM models and downloading prompt logs for debugging.
- [Classic SDKs](https://docs.amigo.ai/developer-guide/classic-api/sdks.md): Official Python and TypeScript SDKs for the Classic API with streaming, auth, and error handling.
- [Installation](https://docs.amigo.ai/developer-guide/classic-api/sdks/sdk-installation.md): Install the Amigo SDK in Python (pip) or TypeScript (npm) with environment setup instructions.
- [Configuration](https://docs.amigo.ai/developer-guide/classic-api/sdks/sdk-configuration.md): Configure SDK clients with API keys, regional endpoints, and environment variable support.
- [Hello World Example](https://docs.amigo.ai/developer-guide/classic-api/sdks/sdk-hello-world.md): Create your first conversation with a step-by-step tutorial in Python and TypeScript.
- [Error Handling](https://docs.amigo.ai/developer-guide/classic-api/sdks/sdk-error-handling.md): Handle API errors with typed exceptions, stream error events, and built-in retry logic.
- [Data Access](https://docs.amigo.ai/developer-guide/classic-api/data-access.md): Read operational data from Amigo via SQL API (serverless) or Delta Sharing into your warehouse.
- [SQL API (Serverless)](https://docs.amigo.ai/developer-guide/classic-api/data-access/sql-api.md): Run read-only SQL queries against organization tables over HTTPS with serverless compute.
- [Delta Sharing](https://docs.amigo.ai/developer-guide/classic-api/data-access/delta-sharing.md): Governed, read-only table sharing into your warehouse or lakehouse via the open Delta Sharing protocol.
- [Organization Tables & Schemas](https://docs.amigo.ai/developer-guide/classic-api/data-access/organization-tables.md): Schema reference for organization tables - conversations, users, services, tools, and more.
- [Conversation](https://docs.amigo.ai/developer-guide/classic-api/data-access/organization-tables/conversation.md): Table schemas for conversations, messages, and extracted memories.
- [User](https://docs.amigo.ai/developer-guide/classic-api/data-access/organization-tables/user.md): Table schema for user profiles, preferences, and dimensions.
- [Service](https://docs.amigo.ai/developer-guide/classic-api/data-access/organization-tables/service.md): Table schema for service configurations and version sets.
- [Organization](https://docs.amigo.ai/developer-guide/classic-api/data-access/organization-tables/organization.md): Table schema for organization details, agents, and state machines.
- [Metric](https://docs.amigo.ai/developer-guide/classic-api/data-access/organization-tables/metric.md): Table schema for metrics and evaluation results.
- [Role](https://docs.amigo.ai/developer-guide/classic-api/data-access/organization-tables/role.md): Table schema for roles and permission definitions.
- [Tool](https://docs.amigo.ai/developer-guide/classic-api/data-access/organization-tables/tool.md): Table schema for tools, versions, and invocation history.
- [Dynamic Behaviors](https://docs.amigo.ai/developer-guide/classic-api/data-access/organization-tables/dynamic-behaviors.md): Classic table schemas for dynamic behavior sets, versioned trigger and action definitions, and runtime invocation records available through data access.
- [Simulation](https://docs.amigo.ai/developer-guide/classic-api/data-access/organization-tables/simulation.md): Table schema for simulation personas, scenarios, unit tests, and run results.
- [Common Query Patterns](https://docs.amigo.ai/developer-guide/classic-api/data-access/organization-tables/common-query-patterns.md): SQL examples for common analytics queries across organization tables.
- [Webhooks](https://docs.amigo.ai/developer-guide/classic-api/webhooks.md): Configure webhook destinations, event subscriptions, signature verification, and secret rotation.
- [Webhook Event Types](https://docs.amigo.ai/developer-guide/classic-api/webhooks/webhook-events.md): Payload reference for each Classic API webhook event type: api-key-expiration-soon, conversation-post-processing-complete, and agent-framework-resource-updated.
- [Permissions](https://docs.amigo.ai/developer-guide/classic-api/permissions.md): Role-based access control and temporary, time-limited permission grants for Classic API users and organizations.
- [Role-Based Permissions](https://docs.amigo.ai/developer-guide/classic-api/permissions/role-based-permissions.md): Configure and manage user roles and granular permissions via the role management APIs.
- [Temporary Permission Grants](https://docs.amigo.ai/developer-guide/classic-api/permissions/temporary-permission-grants.md): Request time-limited, scoped access to specific conversations for debugging and QA.
- [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.
- [Provider Access Grants](https://docs.amigo.ai/developer-guide/platform-api/platform-api/provider-access-grants.md): Provision, list, inspect, and revoke provider Scribe access grants for a workspace.
- [Sessions](https://docs.amigo.ai/developer-guide/platform-api/platform-api/sessions.md): Persistent WebSocket endpoint for text conversations with streamed agent responses.
- [Appointments](https://docs.amigo.ai/developer-guide/platform-api/platform-api/appointments.md): List and retrieve appointments for the current calendar day, scoped to the authenticated provider's workspace.
- [External Auth Claim Mappings](https://docs.amigo.ai/developer-guide/platform-api/platform-api/external-auth-claim-mappings.md): Create, list, get, supersede, and preview-resolve external auth claim mappings that link customer-attested claims to internal roles.
- [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.
- [Best Practices](https://docs.amigo.ai/developer-guide/operations/devops.md): Operational best practices for version sets, channel tagging, multi-org tenancy, PHI isolation, and information ingestion.
- [Multi-Org Strategy (Region x Project)](https://docs.amigo.ai/developer-guide/operations/devops/multi-org-tenancy.md): Create and operate multiple Amigo organizations by region and project for tenant isolation.
- [Version Sets & Promotion](https://docs.amigo.ai/developer-guide/operations/devops/version-sets-best-practices.md): Manage version sets for safe deployment promotion from development through production.
- [Version Set CLI Reference](https://docs.amigo.ai/developer-guide/operations/devops/version-sets-best-practices/version-set-cli.md): Complete forge version-set, forge service, and forge asset command reference for listing, pinning, promoting, and rolling back Amigo service version sets.
- [Channel Tagging System](https://docs.amigo.ai/developer-guide/operations/devops/channel-tagging.md): Configure services for deployment channels (voice, text, async) with LLM preset validation.
- [PHI Isolation & Selective Sharing](https://docs.amigo.ai/developer-guide/operations/devops/phi-isolation-and-selective-sharing.md): Design patterns for PHI isolation and controlled cross-user data sharing.
- [Information Ingestion & Exchange](https://docs.amigo.ai/developer-guide/operations/devops/information-ingestion-and-exchange.md): Three paths for getting external information into ongoing conversations or user models.
- [Reference](https://docs.amigo.ai/developer-guide/operations/reference.md): Technical reference for rate limits, memory architecture, terminology mapping, common patterns, and architecture decisions.
- [Terminology Mapping](https://docs.amigo.ai/developer-guide/operations/reference/terminology-mapping.md): Complete mapping between platform documentation names and REST API field names.
- [Rate Limits](https://docs.amigo.ai/developer-guide/operations/reference/rate-limits.md): Per-endpoint Classic API rate limits, response headers, and retry guidance.
- [Memory Architecture & API Mapping](https://docs.amigo.ai/developer-guide/operations/reference/memory-architecture.md): Classic API L0-L3 memory labels mapped to their endpoints, plus the separate Platform API memory and world-model resources.
- [Common Patterns](https://docs.amigo.ai/developer-guide/operations/reference/common-patterns.md): Production-ready Classic API patterns for conversation lifecycle, user models, webhooks, routing, and CI simulation gates.
- [Architecture Decisions](https://docs.amigo.ai/developer-guide/operations/reference/architecture-decisions.md): Key architectural decisions in the Amigo API design and their rationale.

## API Reference

- [REST API Specs](https://docs.amigo.ai/api-reference/readme.md): API references and changelogs for Classic, Platform, and Scribe APIs, plus SDKs and developer tooling.
- [Classic](https://docs.amigo.ai/api-reference/readme/classic.md): Endpoints for text-based digital health. Chat agents, voice notes, streaming, user management, and simulations.
- [Organization](https://docs.amigo.ai/api-reference/readme/classic/organization.md)
- [Service](https://docs.amigo.ai/api-reference/readme/classic/service.md)
- [Conversation](https://docs.amigo.ai/api-reference/readme/classic/conversation.md)
- [User](https://docs.amigo.ai/api-reference/readme/classic/user.md)
- [Role](https://docs.amigo.ai/api-reference/readme/classic/role.md)
- [Admin](https://docs.amigo.ai/api-reference/readme/classic/admin.md)
- [Webhook Destination](https://docs.amigo.ai/api-reference/readme/classic/webhook-destination.md)
- [Dynamic Behavior Set](https://docs.amigo.ai/api-reference/readme/classic/dynamic-behavior-set.md)
- [Metric](https://docs.amigo.ai/api-reference/readme/classic/metric.md)
- [Simulation](https://docs.amigo.ai/api-reference/readme/classic/simulation.md)
- [Tool](https://docs.amigo.ai/api-reference/readme/classic/tool.md)
- [Models](https://docs.amigo.ai/api-reference/readme/classic/models.md)
- [Platform](https://docs.amigo.ai/api-reference/readme/platform.md): Endpoints for enterprise voice and healthcare. Phone agents, EHR integration, operator escalation, and FHIR data.
- [Workspaces](https://docs.amigo.ai/api-reference/readme/platform/workspaces.md)
- [Account](https://docs.amigo.ai/api-reference/readme/platform/account.md)
- [API Keys](https://docs.amigo.ai/api-reference/readme/platform/api-keys.md)
- [Skills](https://docs.amigo.ai/api-reference/readme/platform/skills.md)
- [Integrations](https://docs.amigo.ai/api-reference/readme/platform/integrations.md)
- [External Integrations](https://docs.amigo.ai/api-reference/readme/platform/external-integrations.md)
- [Conversations](https://docs.amigo.ai/api-reference/readme/platform/conversations.md)
- [Agent Runs](https://docs.amigo.ai/api-reference/readme/platform/agent-runs.md)
- [Runs](https://docs.amigo.ai/api-reference/readme/platform/runs.md)
- [Agent Definitions](https://docs.amigo.ai/api-reference/readme/platform/agent-definitions.md)
- [Use Cases](https://docs.amigo.ai/api-reference/readme/platform/use-cases.md)
- [Workspace Tables](https://docs.amigo.ai/api-reference/readme/platform/workspace-tables.md)
- [Workspace Data Queries](https://docs.amigo.ai/api-reference/readme/platform/workspace-data-queries.md)
- [External Roles](https://docs.amigo.ai/api-reference/readme/platform/external-roles.md)
- [External Role Assignments](https://docs.amigo.ai/api-reference/readme/platform/external-role-assignments.md)
- [External Identity Bindings](https://docs.amigo.ai/api-reference/readme/platform/external-identity-bindings.md)
- [Role Grants](https://docs.amigo.ai/api-reference/readme/platform/role-grants.md)
- [External Auth Claim Mappings](https://docs.amigo.ai/api-reference/readme/platform/external-auth-claim-mappings.md)
- [Config](https://docs.amigo.ai/api-reference/readme/platform/config.md)
- [Agents](https://docs.amigo.ai/api-reference/readme/platform/agents.md)
- [Context Graphs](https://docs.amigo.ai/api-reference/readme/platform/context-graphs.md)
- [Services](https://docs.amigo.ai/api-reference/readme/platform/services.md)
- [Voice Judge](https://docs.amigo.ai/api-reference/readme/platform/voice-judge.md)
- [FHIR](https://docs.amigo.ai/api-reference/readme/platform/fhir.md)
- [Data Sources](https://docs.amigo.ai/api-reference/readme/platform/data-sources.md)
- [Calls](https://docs.amigo.ai/api-reference/readme/platform/calls.md)
- [Evaluations](https://docs.amigo.ai/api-reference/readme/platform/evaluations.md)
- [Review Queue](https://docs.amigo.ai/api-reference/readme/platform/review-queue.md)
- [Sessions](https://docs.amigo.ai/api-reference/readme/platform/sessions.md)
- [Operators](https://docs.amigo.ai/api-reference/readme/platform/operators.md)
- [Entity Intelligence](https://docs.amigo.ai/api-reference/readme/platform/entity-intelligence.md)
- [World](https://docs.amigo.ai/api-reference/readme/platform/world.md)
- [Data Query](https://docs.amigo.ai/api-reference/readme/platform/data-query.md)
- [Pipeline](https://docs.amigo.ai/api-reference/readme/platform/pipeline.md)
- [Analytics](https://docs.amigo.ai/api-reference/readme/platform/analytics.md)
- [Traces](https://docs.amigo.ai/api-reference/readme/platform/traces.md)
- [M42](https://docs.amigo.ai/api-reference/readme/platform/m42.md)
- [Sensorium](https://docs.amigo.ai/api-reference/readme/platform/sensorium.md)
- [Command Center](https://docs.amigo.ai/api-reference/readme/platform/command-center.md)
- [Audit](https://docs.amigo.ai/api-reference/readme/platform/audit.md)
- [Functions](https://docs.amigo.ai/api-reference/readme/platform/functions.md)
- [Settings](https://docs.amigo.ai/api-reference/readme/platform/settings.md)
- [Metrics](https://docs.amigo.ai/api-reference/readme/platform/metrics.md)
- [Form Templates](https://docs.amigo.ai/api-reference/readme/platform/form-templates.md)
- [Scheduling Rules](https://docs.amigo.ai/api-reference/readme/platform/scheduling-rules.md)
- [Network](https://docs.amigo.ai/api-reference/readme/platform/network.md)
- [Compliance](https://docs.amigo.ai/api-reference/readme/platform/compliance.md)
- [Simulations](https://docs.amigo.ai/api-reference/readme/platform/simulations.md)
- [Insights](https://docs.amigo.ai/api-reference/readme/platform/insights.md)
- [Intake](https://docs.amigo.ai/api-reference/readme/platform/intake.md)
- [Intake Upload](https://docs.amigo.ai/api-reference/readme/platform/intake-upload.md)
- [Surfaces](https://docs.amigo.ai/api-reference/readme/platform/surfaces.md)
- [Events](https://docs.amigo.ai/api-reference/readme/platform/events.md)
- [Self Image](https://docs.amigo.ai/api-reference/readme/platform/self-image.md)
- [Surface Patient](https://docs.amigo.ai/api-reference/readme/platform/surface-patient.md)
- [Recordings](https://docs.amigo.ai/api-reference/readme/platform/recordings.md)
- [Tool Testing](https://docs.amigo.ai/api-reference/readme/platform/tool-testing.md)
- [Triggers](https://docs.amigo.ai/api-reference/readme/platform/triggers.md)
- [Dashboards](https://docs.amigo.ai/api-reference/readme/platform/dashboards.md)
- [Billing](https://docs.amigo.ai/api-reference/readme/platform/billing.md)
- [Metering](https://docs.amigo.ai/api-reference/readme/platform/metering.md)
- [Prompt Logs](https://docs.amigo.ai/api-reference/readme/platform/prompt-logs.md)
- [Auth](https://docs.amigo.ai/api-reference/readme/platform/auth.md)
- [Models](https://docs.amigo.ai/api-reference/readme/platform/models.md)
- [Change Logs](https://docs.amigo.ai/api-reference/change-logs.md): Change logs for the Amigo API, Agent Forge, Web Platform, and SDK ecosystem.
- [Amigo API](https://docs.amigo.ai/api-reference/change-logs/amigo-api.md): Release history for Amigo backend APIs, including Classic, Platform, and Scribe changes.
- [Archive: v0.9.250 - v0.9.399](https://docs.amigo.ai/api-reference/change-logs/amigo-api/amigo-api-archive-v0-9-250-399.md): Archived Amigo API release notes covering v0.9.250 - v0.9.399. For current releases, see the main Amigo API changelog.
- [Archive: v0.9.100 - v0.9.249](https://docs.amigo.ai/api-reference/change-logs/amigo-api/amigo-api-archive-v0-9-100-249.md): Archived Amigo API release notes covering v0.9.100 - v0.9.249. For current releases, see the main Amigo API changelog.
- [Archive: v0.6.0 - v0.9.99](https://docs.amigo.ai/api-reference/change-logs/amigo-api/amigo-api-archive-v0-6-v0-9-99.md): Archived Amigo API release notes covering v0.6.0 - v0.9.99. For current releases, see the main Amigo API changelog.
- [Web Platform](https://docs.amigo.ai/api-reference/change-logs/web-platform.md): Release history for the Amigo Web Platform. Admin Portal (Classic API) and Developer Console (Platform API).
- [SDK Ecosystem](https://docs.amigo.ai/api-reference/change-logs/sdk-ecosystem.md): Release history for Amigo TypeScript, Python, and Platform SDKs. New resources, breaking changes, and type safety updates.
- [Agent Forge CLI](https://docs.amigo.ai/api-reference/change-logs/agent-forge.md): Release history for the Agent Forge CLI. Commands, authentication, entity sync, simulation, and tool development updates.


---

# 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, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on a page URL with the `ask` query parameter:
```
GET https://docs.amigo.ai/readme.md?ask=<question>
```
The question should be specific, self-contained, and written in natural language.
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.