Reading series / 6 parts · 1.7h read
Context Engineering
The same model and stack can produce opposite results because context changes the outcome. These six articles draw on 9 months of production data at Méthode Aristote.
The reading path
Read in order. Return as needed.
- 01
1/6 · Opposite AI results: what context can explain
Anthropic measured merged PRs; METR measured task duration in a different setting. What these results and long-context research establish, and what remains a hypothesis.
- 02
2/6 · Diagnose and repair context drift
Use L0 to L5 to diagnose context drift, then maintain adherence through observation, repair, and replay instead of treating setup as finished.
- 03
3/6 · Mapping the token-reduction toolbox
Compare RTK, Tokenade, Headroom and prompt caching by mechanism, integration and evidence. Smaller tool output does not establish a cheaper completed task.
- 04
4/6 · The responsibilities around context engineering
A map of context engineering responsibilities: architecture, specifications, agent identity and evaluation, with practical directions for existing skills.
- 05
5/6 · The AI instruction system is a product, not a config file
Personal CLAUDE.md to team AI instruction system for six engineers. How Méthode Aristote separates sources, shares modules, and catches behavioral drift in CI.
- 06
6/6 · Portability becomes a Scale concern
Portable instructions require neutral sources, generated runtime outputs, release controls, and behavioral tests. Native primitives alone do not provide portability.