Skip to main content
FB.
Series 6 articles · 1.6h 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.

  1. 1

    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.

    · 11 min read
  2. 2

    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.

    · 20 min read
  3. 3

    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.

    · 14 min read
  4. 4

    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.

    · 14 min read
  5. 5

    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.

    · 17 min read
  6. 6

    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.

    · 17 min read
Contact