Guides

These guides take a system from its first execution profile to production. Start with an agent, choose how work is orchestrated, connect only the capabilities you need, then add serving, testing, and operations.

Choose the execution path first

Need	Start here
One autonomous agent reasons through a task	AutoAgent
Application code owns every execution step	CustomAgent
Your application already knows the workflow DAG	Workflow DAGs
Peers must derive and claim work from a source goal	Durable Goal Execution

Durable Goal Execution is an independent guide because it has a different state contract from a declared workflow: immutable attempts, source obligations, revision-fenced reconciliation, and separate execution, obligation, and response status. Learn Workflow DAGs first if you are new to multi-step execution.

1. Build the agents

• AutoAgent

  The framework brings the brain. Describe the task; the agent plans, generates code in a sandbox, and self-repairs. Use when you can describe the work but not code it.

  Read more →

• CustomAgent

  You bring the brain. Plain Python in execute_task, deterministic control, same mesh. Use when you can code the logic.

  Read more →

• System Prompts

  Define an AutoAgent's role, output contract, verification behavior, and failure handling.

  Write system prompts →

• Custom Sub-agents

  Extend the Kernel with a specialized execution unit when built-in roles are not enough.

  Build a sub-agent →

• Adapters

  Bring existing Python, LangChain, or CrewAI objects into the Mesh without a full rewrite.

  Adapt existing code →

2. Orchestrate work

• Workflow DAGs

  Declare known steps, roles, dependencies, parallel branches, and output chaining in application code.

  Build a known workflow →

• Durable Goal Execution

  Compile an unknown source goal into capability-addressed work that peers claim independently, with durable obligation truth and selective repair.

  Run a distributed goal →

• Human-in-the-Loop

  Pause only at genuine human boundaries, then resume the same durable work.

  Design human review →

3. Connect capabilities

• Integrations

  Discover the typed atom catalog for business systems, storage, developer tools, communication, and provider readback.

  Browse integrations →

• Nexus Credentials

  Register provider connections while keeping raw credentials outside agent reasoning and generated code.

  Configure credentials →

• Knowledge Base

  Ingest internal documents and add local retrieval to research work.

  Build a knowledge base →

• Internet Search

  Configure grounded and multi-provider search with ranking and resilience.

  Configure search →

• Browser Automation

  Add Playwright-backed interaction for websites that require a real browser.

  Configure browser automation →

4. Serve, test, and operate

• FastAPI

  Embed agent lifecycle into a FastAPI application.

  Integrate FastAPI →

• Chat Endpoint

  Expose synchronous and streaming conversational interfaces.

  Build a chat endpoint →

• Observability

  Inspect traces, events, costs, workflow state, and Prometheus metrics.

  Add observability →

• Testing Agents

  Exercise agent behavior with deterministic Mesh, peer, and LLM mocks.

  Test agents →

• Testing Atoms

  Validate integration functions structurally and against connected providers.

  Test atoms →

• AI Editor Setup

  Teach Copilot, Claude Code, Cursor, and other coding agents the current JarvisCore contracts.

  Configure an AI editor →

• Production Deployment

  Harden storage, credentials, sandboxing, networking, budgets, and monitoring.

  Deploy to production →