Take Your Agent to the Next Level

This skill sets up your agent with the full LangWatch stack: tracing, prompt versioning, evaluation experiments, and agent simulation tests. Each step builds on the previous one.

Plan Limits

See Plan Limits. The free plan has limits on prompts, scenarios, evaluators, and experiments. Focus on delivering value at each step — make each creation count. Show the user what works before they hit any limits. If you reach a limit, summarize what was accomplished and suggest upgrading at https://app.langwatch.ai/settings/subscription

Prerequisites

Set up the LangWatch MCP first — you'll need it for every step below.

See MCP Setup for installation instructions.

If MCP installation fails, see docs fallback to fetch docs directly.

Consultant Mode

After completing all steps, don't just stop. See Consultant Mode — summarize everything you set up, then suggest 2-3 ways to go deeper based on what you learned about the codebase.