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: openai
Prompt Engineering: Steer LLMs Without Fine-Tuning
Use roles, few-shot examples, chain-of-thought, and format constraints to guide models — and know when prompting alone hits a ceiling versus fine-tuning.
748 wordsRead articleComposing 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.
9373 wordsRead articleFrom GPT-1 to Reasoning Models: What Each Generation Changed for Developers
Trace the GPT family from 2018 pre-training to reasoning models, see which ideas each generation added, and call GPT-4o vision and Structured Outputs from Python.
2084 wordsRead articleThe Stateless Chat Loop: Calling the OpenAI API by Hand in Python
Build a multi-turn chat with the OpenAI Python SDK by managing message history yourself, and see why the same loop underpins LangChain memory and agents.
1167 wordsRead articleSwapping LLM Models Safely: Human Labels, Per-Step Metrics, Effort Settings
How to migrate a multi-step LLM pipeline to newer models without chasing phantom regressions: human ground truth, per-step metrics, stale prompts and reasoning effort.
3579 wordsRead articleOpenAI's Agents API: A Managed Alternative to Custom Agent Frameworks
This article explains how OpenAI's new Agents API handles context management, tool orchestration, and execution environments so teams can skip building custom agent infrastructure.
1161 wordsRead articleUnderstanding Items vs Messages in OpenAI's Responses API
Explains how OpenAI's Responses API reorganizes model outputs into items instead of messages, and why that shift matters for tool-calling and agentic workflows.
1836 wordsRead articleWhy AI Access, Not Capability, Is Your Real Dependency Risk
This article examines recent export-control incidents with Claude and GPT-5.6 to argue that access to AI models is a volatile variable independent of raw capability.
2598 wordsRead article
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.