Building software with AI agents
How we use two AI coding agents, capture decisions in QnA MD and connect assistants to our tools.
Product help explains QnA MD question files and how to connect assistants to our MCP servers. The format reference is listed separately for readers who need the exact grammar.
Engineering notes describe our two-model development experiments, with dated results and limits. They are accounts of what we tried, rather than universal rules for building with AI.
9 articles by Steven Michael Barber.
How we gave every app an MCP interface, and what an AI assistant can do with it
Product help
Why each of our apps has a Model Context Protocol server, how one is made from the app's own functions, a shielding question worked through it, and the rules.
Batch questions with QnA MD and the agentic development life cycle
Product help
How agents compile open questions into one QnA MD file, an owner answers them in one sitting, and the answers are applied and recorded before the next round.
How we first set up Claude and Codex in one repository
Engineering note
The first arrangement: Codex built, Claude reviewed, the owner merged, signed and deployed. Verification records, handoff reports and one merge queue.
QnA MD use cases: six ways to use a question file
Product help
Agent questions to an owner, approval chains and quorum decisions, an idea-to-brief interview, a skill brief, a team sign-off, and answering with no signal.
Two AI models, one repository: early speed and quality data
Engineering note
Measured results from the first 25 hours of Claude and Codex reviewing each other: pull requests, review findings and test counts. Early, thin data.
What we changed after a day of two-model development
Engineering note
The 2026-10-19 changes: approvals delegated to the other model, what the owner keeps, automation held to the same rules, and the build-review flip.
Why we built QnA MD: agent questions that outlive the chat
Product help
Why an AI agent's questions and decisions belong in a Markdown file as hidden HTML-comment tags: git-friendly, invisible when rendered, offline and phone-first.
Why we use two AI models to build and review each other's work
Engineering note
One model reviewing its own work misses things. We had Claude and Codex check each other's work and batched the owner's decisions to what matters.
Format reference
QnA MD file format: tags, fields, statuses and log lines
Product help · Format reference
The QnA MD tag grammar (spec v0.1 draft): six item types, ids, fields, options and (rec), status values, log verbs, timestamps, escaping and our conventions.