Ragnarock
Features

Ragnarock AI

Use the unified AI assistant for requirements, planning, and engineering help.

Ragnarock (/dashboard/projects/{projectId}/ragnarock) is the unified chat surface. It uses dedicated REST endpoints and can stream updates over WebSocket (/ai-chat namespace).

Agent capabilities

Agent keyWhat it doesTypical prompt
requirementsClarifies and structures an SRS"Turn this brief into user stories with acceptance criteria"
developer_intelligenceAnswers using SRS + linked repos"How should we structure the auth module?"
project_plannerOne-shot task breakdownTriggered via plan generation API
qa_intelligenceTest scenarios and suites"List edge cases for the login flow"
change_impactChange analysis (seeded; routing TBD)"What breaks if we remove this API?"

Agents are registered in Postgres (AgentDefinition) and executed by the FastAPI worker via Redis Streams.

User workflow

Open the project → Ragnarock.

A session is created via POST /projects/:projectId/ai/ragnarock/sessions (or resumed from the list).

Send a message — POST .../ai/ragnarock/chat returns 202 Accepted while the worker processes the job.

Listen for completion via polling or the /ai-chat WebSocket gateway (requirements sessions use the same broadcast pattern).

Promote output into Documentation or Tasks manually or via follow-up APIs.

Base path: /projects/:projectId/ai

MethodPathPurpose
POST/ragnarock/sessionsCreate unified chat session
GET/ragnarock/sessionsList sessions
GET/ragnarock/sessions/:sessionIdMessages for session
POST/ragnarock/chatSend message (async)
POST/chat/sessionsRequirements-specific session
POST/requirementsText/URL requirements turn
POST/requirements/uploadPDF/DOCX upload (max 15 MB)
POST/arch-doc/generateArchitecture document generation
POST/plan/generatePlanner one-shot
POST/qa/generateQA test suite generation
GET/draftProject shared SRS draft

Async processing

Streams (defaults from .env.example):

  • Jobs: stream:ai-requirements:jobs
  • Results: stream:ai-requirements:results

Tips for better answers

  • Set the correct persona on your project membership.
  • Link Repositories before asking implementation questions.
  • Maintain project Skills with coding standards and glossary terms.
  • Keep the project draft SRS current — new requirement chats continue from it (GET /ai/draft).

Developer details: AI agents. Troubleshooting: Common issues.

On this page