Series31 parts
AI-Assisted Engineering
Working with AI coding agents, one part per post: lay out the project, plan before code, pick skills, agents or MCP, verify the output, write reusable skills.
newest first
Latest posts
Deep dive13 min read
LLM feedback loop: turn production failures into eval cases
Run an LLM feedback loop: collect user feedback, read failing traces, name failure types, fix one layer, and keep each fixed failure as an eval case.
Deep dive10 min read
AI agent state management: resume a run without paying twice
Design state for an AI agent you build: task state in your own store, a checkpoint per step, tool calls safe to retry, and long-term memory that expires.
Deep dive14 min read
RAG retrieval: get the right chunk into the top k
Build RAG retrieval in steps: clean and chunk documents, filter by permission, use hybrid search, rerank, cite the chunk, and test retrieval on its own.
Deep dive10 min read
Valid JSON, wrong values: validate LLM structured outputs
Get reliable JSON from an LLM: structured outputs or strict tool calling, Pydantic validation, refusals and cut-offs, bounded retries and schema versions.
Deep dive12 min read
LLM model routing: test on evals, pin it, fall back safely
Choose an LLM per task with your own eval set, route by task type, classifier or failed check, keep fallbacks on the same contract, and pin versions.
Deep dive13 min read
Unit tests miss LLM output that varies: build an eval suite
Build an eval suite for an LLM feature: real and edge-case inputs, a grader per property, several runs per case, and a rerun on every prompt or model change.
Deep dive9 min read
Six engineering decisions to keep human with AI agents
See which engineering decisions stay human when a coding agent writes the code, how to sort them by reversibility and reach, and what the agent prepares.
Deep dive11 min read
Coding agents can cross module boundaries: make a check fail
Give coding agents module boundaries a tool can check: a public surface, one dependency direction, owners in CODEOWNERS and folder-scoped instructions.
new here? start with these
Start here
What I write about
picked three
Selected projects
Cross-Platform Mobile App
A React Native app I built and released myself on both Google Play and the App Store, using AI coding tools for most of the build and the deployment.
AI-Assisted Business Central Development
Internal R&D tooling that turns written requirements into AL test files, so I spend less time writing the same kind of test by hand.
IoT Health Monitor
A wearable monitor built on ESP32 with pulse oximetry and temperature sensors, sending readings to a React dashboard over Wi-Fi.