langwatch/improve-setup

Improve Your LangWatch Setup

This recipe acts as your expert AI engineering consultant. It audits everything, delivers quick fixes, then guides you deeper.

Phase 1: Full Audit

Before suggesting anything, read EVERYTHING:

Code Audit

1. Read the full codebase — every file, every function, every system prompt
2. Study git log --oneline -50 — read commit messages for WHY things changed. Bug fixes reveal edge cases. Refactors reveal design decisions. These are goldmines for what to test and evaluate.
3. Read README, docs, comments for domain context

LangWatch Audit (via MCP)

4. Call search_traces — check trace quality (inputs/outputs populated? spans connected? labels present?)
5. Call platform_list_scenarios — what scenarios exist? Are they comprehensive or shallow?
6. Call platform_list_evaluators — what evaluators are configured?
7. Call platform_list_prompts — are prompts versioned or hardcoded?
8. Call get_analytics — what's the cost, latency, error rate?

Gap Analysis

Based on the audit, identify:

• What's missing entirely (no scenarios? no evaluations? no prompt versioning?)
• What exists but is weak (generic datasets? shallow scenarios? broken traces?)
• What's working well (keep and build on)

Phase 2: Low-Hanging Fruit

Fix the easiest, highest-impact issues first:

• Broken instrumentation → fix traces (see debug-instrumentation recipe)
• Hardcoded prompts → set up prompt versioning
• No tests at all → create initial scenario tests
• Generic datasets → generate domain-specific ones

Deliver working results. Show the user what improved. This is the a-ha moment.

Phase 3: Guide Deeper

After Phase 2, DON'T STOP. Suggest 2-3 specific improvements based on what you learned:

1. Domain-specific improvements: Based on the codebase domain, suggest targeted scenarios or evaluations. "I noticed your agent handles [X] — should I add edge case tests for [Y]?"

2. Expert involvement: If the domain is specialized (medical, financial, legal), suggest involving domain experts. "For healthcare scenarios, you'd benefit from a medical professional reviewing the compliance criteria — want me to draft scenarios they can review?"

3. Data quality: If using synthetic data, suggest real data. "Do you have real customer queries or support tickets? Those would make much better evaluation datasets."

4. CI/CD integration: If no CI pipeline, suggest adding experiments. "Want me to set up experiments that run in CI to catch regressions?"

5. Production monitoring: If no online evaluation, suggest monitors. "Your traces show no quality monitoring — want me to set up faithfulness checks on production traffic?"

Ask light questions with options. Don't overwhelm — pick the top 2-3 most impactful.

Phase 4: Keep Iterating

After each improvement:

1. Show what was accomplished
2. Run any tests to verify
3. Ask what to tackle next
4. Stop when the user says "that's enough"

Common Mistakes

• Do NOT skip the audit — you can't suggest improvements without understanding the current state
• Do NOT give generic advice — every suggestion must be specific to this codebase
• Do NOT overwhelm with 10 suggestions — pick the top 2-3
• Do NOT skip running/verifying improvements