Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: llm
From prompt tweaking to feedback loops: DSPy, GEPA and Claude Code
Learn how DSPy, MIPRO, STORM, GEPA, Claude Code and MCP shift AI work from rewriting prompts to building measurable programs with executable feedback loops.
10 min readA six-month roadmap from beginner to working AI engineer
Follow a month-by-month plan covering Python, LLM APIs, RAG, agents, evaluation, deployment and cost, with four portfolio projects that show you can ship AI systems.
10 min readLangChain basics: what it solves and when to skip it entirely
Learn what LangChain actually provides, why multi-provider tool calling pushed teams toward it, which packages to install, and when a thin wrapper is the better choice.
7 min readA Production Harness for Claude Code: Six Layers From Slack to Merged MR
How a six-layer harness turns Slack tickets into merged code: event intake, gated agent loops, durable state, self-healing, observability and operator control.
42 min readFifty Years of Retrieval Research Hiding Inside Your RAG Pipeline
RAG chunking, hybrid search, HyDE, reranking and evals all have decades-old ancestors in information retrieval. A tour of the research and where it falls short.
17 min readCutting Agent Token Costs: Caching, Routing and Context Hygiene
Shrink LLM agent bills with prompt caching and semantic caching, lazy-loaded tools, model routing and cascades, subagents, and plain old context hygiene.
16 min readAI Agent Foundations: Purpose, Prompt Design and Model Selection
How to lay the groundwork for a production AI agent: define purpose and success metrics, write prompts with goals and guardrails, then pick the right model.
21 min readContext Engineering in Practice: A Claude Agent SDK Research Agent
Build a Python research agent with the Claude Agent SDK using write, select, compress and isolate patterns, then compare it against a naive baseline in measured runs.
20 min readWhat a Model-Diffing Agent Finds: Style Shifts Overshadow a Narrow Fine-Tune
A model-diffing agent audited a finance LoRA fine-tune: 82% of runs caught the length and structure shift, while the intended reasoning change stayed hidden.
15 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.