Writing

Notes on orchestration, infrastructure, and the methods I want to reuse.

14 posts

The collaboration harness

Jul 2026 · 6 min read

Two names already exist for this stack: one wraps a model so it can act, one governs several of those wrappers. A live call between a human and recruitable agents needs a third.

A picture is worth a thousand tokens

Jul 2026 · 5 min read

Making diagrams an agent's default output format took more than a skill description: trigger stacks, context budgets, a rendering failure, and a last line of defense.

When the repeating unit is the product

May 2026 · 3 min read

For platforms of many near-identical units, the product is the scaffold: discovery → analysis → generation → validation, with CLI tools collapsing context and scripts judging while agents propose.

How a diagram-to-infrastructure tool turned into a research habit

Nov 2025 · 1 min read

Terragram kept losing the thread on long sessions. Fixing that meant studying how models use context, and that research became the reusable asset.

Orchestration engineering: systems that spawn engines

Apr 2026 · 3 min read

After prompts and context, what compounds is meta-engineering: reusable orchestration that generates domain engines with roles, gates, and encoded expertise.

Let the scripts judge and the agents fix

Mar 2026 · 1 min read

The most reliable pattern I keep reaching for: deterministic checks decide, and agents only ever propose.

Nobody should both write and merge

Feb 2026 · 1 min read

Separating edit authority from merge authority is the one rule that makes agent-authored code safe to ship.

One service layer, many surfaces

Jan 2026 · 1 min read

A browser, a Claude agent, and a background worker should all go through the same code. Anything else drifts.

Compress for agents, not for humans

Dec 2025 · 3 min read

Context windows are attention budgets. Optimize value-per-token with offline distillation and structured handoffs, not prettier prose for people.

Why I build orchestration systems locally first

Nov 2025 · 1 min read

Reproducibility before scale: run agent loops on your own machine before they touch anything shared.

Studying how hidden information breaks

Oct 2025 · 1 min read

You can’t reason about the robustness of a watermark or a steganographic scheme until you’ve tried, carefully, to break it.

Agents deserve a real context format

Sep 2025 · 1 min read

AGENTS.md and SKILL.md solved pieces of agent context. BRIEF.md is my attempt at the missing discovery-and-handoff piece.

Analogical reasoning as an engineering tool

Aug 2025 · 1 min read

Borrowing the shape of a solved problem speeds up the next one, as long as I stop where the domains diverge.

Dual channels and rule layers beat a longer prompt

Jul 2025 · 3 min read

When sessions grow, better prompts help less than splitting silent generation from review, and pushing recurring guidance into a cheap rule hierarchy so the working window stays small.