Articles for people who
ship the stack
Original rewrites on React, Node.js, TypeScript and AI — practical notes from the same engineering practice behind our operator software. Article bodies are in English.
Tagged: Prompt Engineering
Context Engineering for AI Agents: Curating What the Model Sees
Why agents degrade as their context grows, how context engineering differs from prompt wording, and a simple pipeline for choosing what each model call sees.
8 min readDiagnosing LLM Output Problems: When to Prompt, Retrieve or Fine-Tune
A symptom-first way to decide whether a weak AI feature needs a better prompt, a retrieval layer or fine-tuning, and why training a model on facts backfires.
7 min readSix AI Concepts That Tell You What to Check Before Trusting an Answer
Tokens, context windows, temperature, hallucination, RAG and agents explained as verification tools, so you can spot errors, control cost and judge AI product claims.
10 min readFrom Vague to Precise: Refining One Prompt in Three Deliberate Passes
Watch a one-line LLM prompt evolve into a structured brief, and learn why context says what is true while role, format and constraints define a good result.
4 min readBuild a Personal Prompt Refiner and Generator with Claude Artifacts
Turn one Claude chat into a personal prompt refiner with Artifacts: it sharpens weak prompts and grows rough ideas into basic, advanced and expert versions.
9 min readBounded Prompts: Stopping AI Assistants from Inventing a Parallel Stack
Why vague feature requests make coding assistants add duplicate libraries and wrappers, and how a bounded prompt with paths, invariants and hard stops fixes it.
6 min readComposing LangChain Pipelines with LCEL: Linear, Parallel and Branching
Learn to wire prompts, models and parsers into linear, multi-stage, parallel and conditional LangChain pipelines with the pipe operator, RunnableParallel and RunnableBranch.
41 min readAn AI-Assisted Workflow for Shipping a Small Website to Cloudflare
A repeatable workflow and prompt templates for designing, iterating on and deploying a small site with an AI coding assistant, GitHub and Cloudflare's free tier.
9 min readReverse Prompting: Turning a Good LLM Session into a Reusable Prompt
Learn how to extract a one-shot prompt from a successful multi-turn LLM conversation, and how prompt inversion recovers prompts when you only have the outputs.
6 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.