#context engineering
The science and practice of engineering context for AI assistants: maturity models, team systems, token reduction, and portability.
Context engineering and code review with Bruno Soulez
ArticleMy conversation with Bruno Soulez on context engineering, agent harnesses and code review: what I delegate and what I still check.
Testing Opus 5.5 as the code-review baseline
ArticleOpus 5.5 is the next reviewer baseline to test: set effort explicitly, update the API adapter, and keep a second reviewer only when it catches verified defects.
Dev With AI 2026: what changes in developers’ work
GuideReview, business context, costs and product development: my synthesis of Dev With AI on October 12, 2026, with the full illustrated conference report.
From code to merge: organizing agent workflows as a team
GuideDev With AI talk guide: agent harnesses, local checks, AI reviews, bounded corrections and results tied to the right commit. Examples and slides.
How to read a token-compression benchmark
ArticleRead token-compression claims through their denominators, paired tasks, cache costs and success criteria, with Tokenade versus RTK as a worked example.
Moving the memory observer to a local model: five constraints nobody documents
GuideA September 2026 claude-mem 13.24.1 case study: moving observations from Sonnet 5 to Qwen2.5-Coder-7B, with measured timeout and output-quality limits.
2/2 · Claude selected my output style. Then ignored it
ArticleClaude Code selected flow-lean but skipped its footer. A casing fix showed why installation, selection, and behavior need separate evidence.
Persistent memory: the six failures that never raise an error
GuideI ran claude-mem for four and a half months. Six things were broken, four of them since March, and none ever raised an error.
Portable agent configuration is a release system, not a shared folder
ArticleShare Claude Code and Codex instructions, skills and MCP definitions through versioned releases, host adapters and checks of installed and runtime behavior.
Context engineering: the L0-to-L5 playbook
GuideChoose context controls from L0 to L5 according to the failure you observe, from project documentation to scoped rules, behavior checks and shared configuration.
Claude Code setup, level by level
GuideThree configuration layers for project context, daily tools and persistent memory, with checks for what loads and how it behaves.
6/6 · Portability becomes a Scale concern
ArticlePortable instructions require neutral sources, generated runtime outputs, release controls, and behavioral tests. Native primitives alone do not provide portability.
5/6 · The AI instruction system is a product, not a config file
ArticlePersonal CLAUDE.md to team AI instruction system for six engineers. How Méthode Aristote separates sources, shares modules, and catches behavioral drift in CI.
4/6 · The responsibilities around context engineering
ArticleA map of context engineering responsibilities: architecture, specifications, agent identity and evaluation, with practical directions for existing skills.
3/6 · Mapping the token-reduction toolbox
ArticleCompare RTK, Tokenade, Headroom and prompt caching by mechanism, integration and evidence. Smaller tool output does not establish a cheaper completed task.
2/6 · Diagnose and repair context drift
ArticleUse L0 to L5 to diagnose context drift, then maintain adherence through observation, repair, and replay instead of treating setup as finished.
1/6 · Opposite AI results: what context can explain
ArticleAnthropic measured merged PRs; METR measured task duration in a different setting. What these results and long-context research establish, and what remains a hypothesis.