---
name: suki-platform
description: "Use when choosing among Suki Ambient, Form filling, Dictation, Patient Summary, audio streaming, webhooks, SDKs, or Partner APIs, or when the product path is unclear. After the product is known, fetch that product skill instead of relying on this router alone."
license: Suki_Proprietary
metadata:
  author: suki
  version: "2.4"
---

# Suki for Partners (platform router)

Route the agent to the correct product skill. After the job is known, **fetch that skill** and use the documentation MCP for page-level details. Do not implement a full integration from this router alone.

## Accuracy rules

- Do not invent endpoints, SDK methods, or WebSocket message types.
- Keep Ambient, Form filling, Dictation, and Patient Summary distinct.
- Ambient and Form filling stream on `/ws/stream`. Dictation streams on `/ws/transcribe` with different message shapes.
- After the job and path are known, fetch the **dedicated** SDK or API skill. Do not implement a full Web SDK, Headless, Mobile, or raw Partner API integration from this router alone.
- Credentials come from Suki partnership / onboarding. If the user lacks them, stop and open partner onboarding.

## Choose a product skill

<!-- SKILL-AUTO:START sister-skills -->
| Job | Skill |
| --- | --- |
| Ambient clinical notes (workflow) | https://developer.suki.ai/.well-known/agent-skills/suki-ambient/SKILL.md |
| Form filling (workflow) | https://developer.suki.ai/.well-known/agent-skills/suki-form-filling/SKILL.md |
| Dictation (workflow) | https://developer.suki.ai/.well-known/agent-skills/suki-dictation/SKILL.md |
| Patient Summary | https://developer.suki.ai/.well-known/agent-skills/suki-patient-summary/SKILL.md |
| WebSocket wire format (overview + Ambient/Dictation pages) | https://developer.suki.ai/.well-known/agent-skills/suki-audio-streaming/SKILL.md |
| Partner webhooks | https://developer.suki.ai/.well-known/agent-skills/suki-webhooks/SKILL.md |
| Headed Web SDK | https://developer.suki.ai/.well-known/agent-skills/suki-web-sdk/SKILL.md |
| Headless Web SDK | https://developer.suki.ai/.well-known/agent-skills/suki-headless-web-sdk/SKILL.md |
| Mobile SDK (iOS) | https://developer.suki.ai/.well-known/agent-skills/suki-mobile-sdk/SKILL.md |
| Dictation SDK | https://developer.suki.ai/.well-known/agent-skills/suki-dictation-sdk/SKILL.md |
| Form filling SDK | https://developer.suki.ai/.well-known/agent-skills/suki-form-filling-sdk/SKILL.md |
| Ambient API (REST + /ws/stream) | https://developer.suki.ai/.well-known/agent-skills/suki-ambient-api/SKILL.md |
| Form filling API (REST + /ws/stream) | https://developer.suki.ai/.well-known/agent-skills/suki-form-filling-api/SKILL.md |
| Dictation API (REST + /ws/transcribe) | https://developer.suki.ai/.well-known/agent-skills/suki-dictation-api/SKILL.md |

Index: https://developer.suki.ai/.well-known/agent-skills/index.json
<!-- SKILL-AUTO:END sister-skills -->

```bash
npx skills add https://developer.suki.ai
```

## Product map

- **Ambient:** conversation → structured clinical note
- **Form filling:** conversation → structured medical form fields
- **Dictation:** real-time speech-to-text (not full note generation)
- **Patient Summary:** FHIR / CKG → pre-visit summary
- **Audio streaming:** `/ws/stream` vs `/ws/transcribe` rules
- **Webhooks:** HTTPS callbacks for session completion and CKG ingestion

### SDKs

- **Web SDK:** headed UI (`@suki-sdk/js` / `@suki-sdk/react`)
- **Headless Web SDK:** Ambient hooks (`@suki-sdk/platform-react`)
- **Mobile SDK:** native iOS Ambient (`SukiAmbientCore`)
- **Dictation SDK:** hosted Dictation embed
- **Form filling SDK:** hosted Form filling embed

### Partner APIs

- **Ambient API:** REST + `/ws/stream` for clinical notes
- **Form filling API:** REST + `/ws/stream` for structured forms
- **Dictation API:** REST + `/ws/transcribe` for transcripts
- **Patient Summary:** CKG ingest + generate/retrieve APIs

## Environments

<!-- SKILL-AUTO:START environments -->
**Environment rule:** For direct API integrations, use staging unless the user explicitly requests production.

| Environment | REST | WebSocket |
| --- | --- | --- |
| Staging | `https://sdp.suki-stage.com` | `wss://sdp.suki-stage.com` |
| Production | `https://sdp.suki.ai` | `wss://sdp.suki.ai` |
<!-- SKILL-AUTO:END environments -->

## Shared authentication (overview)

Partner API auth is shared. Product SDKs use their own auth managers/hooks.

- Follow [Partner authentication](https://developer.suki.ai/documentation/how-to/partner-authentication) for partner type, Login, Register, and token refresh.
- On Partner APIs, send `suki_token` as **`sdp_suki_token`** and include **`sdp_provider_id`** when required.
- Do not invent login/register payloads in product skills; read the auth docs first.

Decision guide: https://developer.suki.ai/documentation/get-started/integration-decision-guide

## Always-on retrieval

<!-- SKILL-AUTO:START canonical-docs -->
- [Partner Authentication Mechanisms](https://developer.suki.ai/documentation/how-to/partner-authentication): Compare and choose the right authentication mechanism for your APIs and SDKs, including Partner Token exchange, JWKS, and provider registration
- [Ambient & Dictation - Integration Decision Guide](https://developer.suki.ai/documentation/get-started/integration-decision-guide): Compare Direct APIs, Web SDK, Headless Web SDK, and Mobile SDK to select the right integration method for your healthcare application
- [Documentation MCP Integration](https://developer.suki.ai/documentation/references/mcp): Connect Suki developer documentation as an MCP server in your AI code editor to search guides, API reference, and SDK docs while you integrate
- [AI Coding Tool Skills](https://developer.suki.ai/documentation/references/ai-coding-tools): Choose a workflow, SDK, or Partner API skill for Ambient, Form filling, Dictation, Patient Summary, streaming, or webhooks, then connect the documentation MCP
- [llms-full.txt](https://developer.suki.ai/llms-full.txt): Full-site dump for broad cross-product questions
<!-- SKILL-AUTO:END canonical-docs -->

