improve-setup

name	improve-setup
description	Expert AI engineering consultant for your LangWatch setup. Audits your codebase, traces, evaluations, and scenarios, then guides you to improve — starting from low-hanging fruit and going deeper. Use when you want to level up your agent's engineering quality.
license	MIT
compatibility	Requires the `langwatch` CLI with a valid `LANGWATCH_API_KEY`. Works with Claude Code and similar coding agents.
metadata	{"category":"recipe"}

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 CLI)

4. langwatch trace search --limit 25 --format json — check trace quality (inputs/outputs populated? spans connected? labels present?)
5. langwatch scenario list --format json — what scenarios exist? Are they comprehensive or shallow?
6. langwatch suite list --format json — what suites (run plans) exist?
7. langwatch evaluator list --format json — what evaluators are configured?
8. langwatch monitor list --format json — any online evaluation monitors set up?
9. langwatch prompt list --format json — are prompts versioned (or are they all hardcoded in code)?
10. langwatch analytics query --metric trace-count and --metric total-cost, --metric avg-latency, --metric eval-pass-rate — what's the current cost, latency, error/pass 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 (langwatch prompt init, see the prompts skill)
• No tests at all → create initial scenario tests (see the scenarios skill)
• Generic datasets → generate domain-specific ones (see the datasets skill)

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 with langwatch monitor create?"

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 / re-query analytics to verify (langwatch trace search, langwatch suite run --wait, etc.)
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