Improve an Agent

Use Claude Code to recursively improve your agents.

Now that your agents are running, let’s use Claude Code to improve them.

On a unified platform, coding agents can read logs to iteratively improve our agents. The codebase ships two skills for this:

• /improve-agent. Claude derives probes from the agent’s instructions, judges responses, and edits until they pass. Autonomous.
• /extend-agent. You drive this one: add a tool, refine a prompt, or fix a bug.

Both edit agents/<slug>.py directly. Hot-reload picks up the change in ~2s, so the test → judge → edit cycle is tight.

Improve: autonomous probe-and-judge

Open Claude Code in your agent-platform directory and run:

/improve-agent

Claude reads the target agent’s INSTRUCTIONS and derives 8-12 probes across four categories: golden path, edge cases, tool selection, and adversarial. For each probe, it cURLs the live container, reads tool calls from the logs, and judges PASS or FAIL against what the instructions promise. For every failure, Claude picks a lever and edits: tighten a rule, add a rule, swap a tool, bump num_history_runs. Claude re-runs only the failed probes.

Extend: user-driven changes

When you have a specific change in mind, run:

/extend-agent

Claude asks what to change. You describe a tool to add, a prompt to refine, a bug to fix. The agno-docs MCP is loaded so toolkit research is grounded in the real API. Each iteration is one small, verified change. Extend and Improve, Extend and Improve.

When to run each

Situation	Skill
Just created an agent and want to harden it before deploying	/improve-agent
Users report the agent is missing the point	/improve-agent
You want to add a new tool or knowledge base	/extend-agent
You hit a specific bug	/extend-agent
You just extended an agent and want to confirm nothing regressed	/improve-agent

Next

Run your platform on Railway →