Paste a prompt that gives weak results and get a diagnosis of its flaws, a rewritten and structured version, a change log and test cases to check it really works better.
Generate a ready-to-paste Google Apps Script: it reads your sheet, sends emails or creates events, runs on a trigger, avoids duplicates and includes a test mode and setup steps.
Design a retrieval-augmented generation chatbot: ingestion and chunking, embeddings, hybrid search, citations, permissions, evaluation, cost and risks such as prompt injection.
Decide between a modular monolith, extracting a few services or full microservices, using explicit criteria, operational prerequisites, risks and an ADR ready to share.
Decide what to cache in Redis and how: a pattern per data type, key naming, jittered TTLs, invalidation, stampede protection, memory policy and sample code.
Generate a complete FastAPI module for one resource: Pydantic v2 schemas, model and Alembic migration, a paginated CRUD router, and pytest tests with httpx.
Interpret your PageSpeed Insights or Lighthouse report and get the likely causes of poor LCP, INP or CLS, prioritized fixes with code and a plan to measure with real-user data.
Convert a JavaScript file or module to TypeScript with types inferred from real usage, a recommended tsconfig, a list of bugs the types reveal and a plan for the rest of the codebase.
Get an adversarial test plan for your chatbot or AI assistant: prompt injection, data leaks, out-of-scope answers and made-up promises, with a test case table and mitigations.
Design a prompt that sorts texts (tickets, reviews, emails) into your labels, with clear definitions, balanced examples, structured output and a plan to measure its accuracy.
Generate a React Native and TypeScript mobile screen with loading, empty, error and offline states, an optimized list, accessibility, safe areas and tests with Testing Library.
Generate a complete browser extension with Manifest V3: a least-privilege manifest.json, service worker, content script, popup, messaging, storage and a Chrome Web Store checklist.
Get the code to customize WooCommerce with actions and filters in your own plugin: the right hook, security, HPOS and block checkout compatibility, and a staging test plan.
Design an evaluation for AI answers with an anchored rubric, an LLM-as-judge prompt with JSON output, bias mitigation and calibration against human labels.
Build a reliable pipeline to extract free text into JSON with an LLM: JSON Schema, a prompt with null rules, few-shot examples, validation code with retries and test cases.
Turn a list of commits or PRs into a Keep a Changelog entry, a SemVer version proposal, breaking changes with a migration guide and release notes your users can actually read.
Generate a clear commit message (Conventional Commits or free form) and a PR description with context, changes, how to test and risks, straight from your diff and ticket.
Turn a repo tree and key files into a clear map: architecture, how a request flows, glossary, risky areas and exactly where to start for your specific task.