Work through the problem. Check what actually works.
Bilingual implementation notes on Web development, PostgreSQL, Cloudflare, AI tool workflows, and TypeScript programming problems.
Featured notes
- A Green Build Is Not a Live Release
Separate a successful build from evidence that a release is live.
- Why does the next page repeat a row? OFFSET and keyset pagination
Reproduce duplicate and skipped rows after inserts or deletes, then choose a pagination strategy.
- The site is deployed. Why am I still seeing the old version?
Trace stale pages through HTML, ETags, and asset URLs.
Recent notes
Structured Output: The AI Returned JSON. Now What?
Compare format prompts, JSON mode, and schema constraints. Use metadata checks, timestamps, and a token-estimation counterexample to see what the application still needs to validate.
Context Placement: Where Should the Important Bits Go?
You supplied the context, but the answer missed it. Explore information placement, long documents, conversation summaries, and ways to test each change separately.
Core Prompting Techniques: When Should I Add Examples?
When one instruction isn't enough, should you add rules or examples? Compare standard, zero-shot, one-shot, and few-shot prompts using GitHub issues.
Standard Prompts: Start with a Clear Request
A short Practical Prompt Engineering note: improve a newsletter-form request with context, constraints, targeted clarification, and concrete checks.
Temperature and Top P: How a Model Selects the Next Token
Practical Prompt Engineering notes: use a five-token probability example to understand temperature, nucleus sampling, Top P 0.5, and the limits of consistent output.
Token Limits and Context Windows: What Can the Model See in This Turn?
Practical Prompt Engineering notes: distinguish tokens from words, context from output limits, and conversation history from memory, with a worked token budget.
Curious to explore more?
Explore all notes