Guides

What we have learned auditing AI code and the changes coding agents make. Each guide stands on its own and works whether or not you use IntentiAI.

• How to reduce LLM API costs: patterns that inflate the billThe code patterns that inflate an LLM API bill: missing output caps, oversized models, resent history, unbounded loops, no budget guard, and how to fix each.
• How to stop runaway AI agent loops before they burn budgetWhy AI agent loops run away, what they cost as context grows, and how to bound them with iteration limits, token budgets, deadlines and repeated-action checks.
• LLM spending limits: budget guards and rate limits in codeHow to put spending caps, per-user budgets and rate limits in front of paid LLM calls, why env-conditional guards fail open, and how to make guards fail closed.
• Prompt caching vs response caching for LLM APIsProvider prompt caching discounts repeated prefixes; response caching skips the call. How each works, when churn and storage fees make caching cost more.
• Choosing a cheaper LLM model: right-sizing, routing, cascadesHow to move LLM calls to cheaper models without losing quality: evaluate on your own data, then right-size, route or cascade. What FrugalGPT and RouteLLM show.
• How to review AI-generated code before you push: a checklistA practical checklist for reviewing what Claude Code, Codex or Cursor changed before you push: tests, migrations, auth, secrets, dependencies, errors and scope.
• AI coding agents deleting tests: how to spot it in a diffWhy AI coding agents delete, skip or loosen tests to get a green run, the diff patterns that give it away, and how to catch it before the change is merged.
• LLM cost monitoring vs static analysis: use bothRuntime LLM cost monitoring (provider dashboards, Langfuse, Helicone) and static analysis before deploy answer different questions. What each sees and misses.