Featherlane AI
Guides

Guides

Task-oriented walkthroughs for common Featherlane AI workflows.

Guides are task-oriented. Start here when you know what you want to do and need the shortest path through the repo.

Available Guides

GuideUse it when
Coding-Agent Tool GatesYou want Claude Code, Codex, or OpenCode tool calls checked before execution.
Hosted MCP AccessYou want employee AI clients to use assigned remote MCP tools through Featherlane AI.
Python Agent FrameworksYou want to guard AG2 or Agno local tools and final plain-text output without rewriting agent flow.
AI Usage Cost CapsYou need per-caller LLM spend limits, 80% alerts, and hard preflight enforcement.
Policy AuthoringYou need to write, validate, push, or pull policy YAML.
Guard ModesYou need to decide whether an SDK integration should block, rewrite, or regenerate unsafe drafts.

Common Workflows

Guard An Agent Reply

  1. Create an agent and runtime key in the Featherlane AI dashboard.
  2. Install the SDK package for your runtime.
  3. Decorate the agent object once at construction.
  4. Keep calling its reply() method normally.
  5. Use the resulting trace to inspect the event later.

For AG2 and Agno, follow Python Agent Frameworks to protect both exposed local tools and final plain-text output.

Build A Demo

Use the demo package when you want a clean product moment:

agent drafts risky output
  -> Featherlane AI checks it
  -> user receives only the allowed or rewritten output
  -> dashboard shows the trace

For local demos, use pnpm demo:chat or the LiveKit example under demo/livekit.

Add A New Runtime Capability

Follow the SDK-driven rule:

  1. Add or update the shared Rust wire type in tl-core.
  2. Add the Rust server endpoint or behavior.
  3. Regenerate contracts.
  4. Expose the capability through Rust, TypeScript, and Python SDKs.
  5. Update examples and docs in the same change.

On this page