Parallel Agents Need More Than Separate Branches
Separate worktrees help with file edits; an ownership map makes shared databases, ports, contracts and integration checks explicit.
22 posts
Separate worktrees help with file edits; an ownership map makes shared databases, ports, contracts and integration checks explicit.
A release receipt should connect the tested candidate, built artifact, deployment and production route without pretending one smoke check proves everything.
I let coding agents research, source, generate and iterate three native KiCad revisions of an NFC business card over three days in October. The files are real and the checks are clean; the confidence came from datasheets, exact part numbers and independent re-examination, not from the renders.
I wrote a Claude Code skill in April because I book the same gym classes every week. By October it was an app on both stores, and an agent runs it. Here is why.
A durable handoff separates observations, hypotheses and unfinished work, then records what would make each observation stale.
The $7.99 rebuild bought a first version; the repository now shows the less photogenic work of preserving an archive and keeping its promises.
A review bundle should connect the requirement to evidence for the exact candidate and make the remaining decision explicit.
A CI alert becomes useful work when its revision, evidence and next owner survive the handoff; another prompt template does not supply them.
A useful agent acts within delegated authority, prepares consequential actions for review, and asks again when the action changes.
One paper shows frontier models degrade as context grows — even on trivial tasks. The other shows reasoning models hit a wall and think less as problems get harder. Read carefully, both point at the same engineering response.
Anthropic let Claude run a real shop for a month. It sold metal cubes at a loss, invented a Venmo account, and claimed to wear a blazer. The 'AI department that works while you sleep' is a genre — here's where it actually breaks.
Principles 26–30. The calibration layer that catches what the rest of the framework would miss: a PR-noise budget, independent verification, model-swap regression discipline, the 15-tool-call rule, and protecting junior development.
Principles 21–25. The governance and safety layer: strictKnownMarketplaces, no goal-conflict prompts, quarterly AppSec, four telemetry signals, monthly incident discipline.
Principles 15–20. The harness configuration that keeps the kernel and lifecycle cheap: CLAUDE.md under 200 lines, hooks for real incidents, skills that auto-invoke, subagent isolation, pinning, and Stage 5 distribution.
Principles 6–14. How work moves through an agentic engineering team: the ticket as contract, AI distillation with human curation, three gates, verification before done, characterisation tests, the 1.2× capacity rule, the J-curve, and telemetry.
Principles 1–5. The five rules that everything else in the framework rests on: standardise the harness, make verification load-bearing, default to plan mode, pick the cheapest layer, reflect every task.
Karpathy named one mode. Willison named the other. Most 'AI failed in production' stories are actually 'we promoted a vibe-coded prototype without transitioning into the production discipline.'
ReAct gave us a three-step loop. Production hardened it into five. The two new steps — Plan and Verify — are where everything that goes wrong, goes wrong. And the field has now named the worst offender.
Three open-source extractions converged on the same five layers. The architecture isn't a vendor narrative — it's a discovered structure. Here's the decision rule that keeps you from over-engineering it.
Most teams plateau at Stage 2 because they confuse 'we built skills' with 'we have a working AI engineering culture.' Here's the 5-stage diagnostic — and the moves that get you from Individual to Distributed.
The prototype-to-production gap for AI agents isn't technical — it's governance. Most organisations have nothing in this layer. The companies that build it first win the enterprise market. Everyone else stays in pilot purgatory.
When I first built Gluon on my Mac mini, I was solving a personal problem: monitoring Claude agents without losing my mind to tmux logs. But when teams join the picture, everything changes — security, governance, observability, and the fundamental role of the developer. Here's what production infrastructure for autonomous agents looks like.