Harness engineering
Parts, in publishing order
- Five layers to tune before you fork your agent
What makes AI agentic, how to split a deterministic core from an agentic edge, and the five layers you can tune without rebuilding the harness. Real numbers from circle…
- DeepSeek harness, dissected
An architecture read of dsh, DeepSeek's new agent harness: the plugin tree, the patch-layer boot, the log-first session model, and what it means for a Claude Code shop.
- What the Engelberg report got right about us
Thoughtworks published the findings of its second Future of Software Engineering retreat. Most of what the room converged on is what we have been learning and putting…
- Claude Code 2.1.259 turned our Read() deny rules into a Bash tripwire
Bypass-mode sessions started stalling on 'a Read() deny rule is configured' prompts. What the harness now infers from a Bash command, why a CLAUDE.md rule couldn't stop…
- The debug loop: make the agent measure the browser before it touches the CSS
A repeatable loop for AI-driven UI debugging: name the metric, name the axis, drive a real browser over CDP, read the DOM into a table, kill theories, sweep the suspect,…
- Our publish step took 110 seconds, then 78. Our release tab took three tries.
Reading a CI log line by line cut memo's publish step from 110 to 78 seconds and exposed three silent bugs. Then agents started deploying all day, and the Releases tab…
- Guest writers on memo, keyed by the writer's own domain
How memo.d.foundation publishes posts from writers' own blogs as native notes: domain-verified joins, semi-auto review with a human verdict, ICY rewards per post, and…
- Making our site AI-agent-ready, 50 to 93
We ran memo.d.foundation through is-agentic.com, read its rubric closely, and shipped the fixes that took the score from 50 to 93. Here is the rubric in full and what…
- The tells
AI writing gives itself away at the level of structure, not word choice. A field guide to the patterns, and the guideline change that bans them from our posts.