What actually happened

At the end of a long day that included a sprint planning session for a civic technology platform I run, I printed a document. It was a GitLab milestone description — one page, formatted for a meeting, listing every priority in the sprint with the reasoning behind each one. It showed which issues were P1 and why, who owned which lane and why that ownership was designed the way it was, and what each sub-sprint was actually for.

The document was accurate. Not in the “it listed the tickets” sense, but in the “it understood the strategy” sense. I didn’t explain any of this in the session. The model already knew.

The context layer

The reason the model already knew is that I maintain a private, versioned knowledge base — a small set of Markdown files in a git repository — that describes my actual situation. Career strategy. Current projects and their purposes. Financial position and the constraints it imposes. Decisions already made. The relationships and dynamics that shape how work gets done. Anything that would change the advice if the model had it.

This repository loads into every Claude Code session I run. The first message I send is the actual question — not the background. The model doesn’t need me to re-establish context because the context is already there, accurate, and current.

The expensive part of working with AI isn’t the inference. It’s the context-establishment. Every session you re-explain your situation, or you don’t, and the model gives advice for a generic case. The context layer removes that cost.

What the files look like

The structure is simple. A CLAUDE.md at the root tells the model what the repository is for, what the key files are, and what to update when things change. A knowledge/ directory holds the prose: one file per major domain, written to be read by a model giving advice to the person who wrote it.

The discipline is maintenance. The files are as useful as they are accurate. When something material changes — a decision gets made, a priority shifts, a constraint is added — the relevant file gets updated. A five-minute update after a significant decision makes every subsequent session better.

Three patterns

The context layer shows up in three distinct ways depending on what you’re trying to do.

The exec-assistant pattern is for individuals: a personal knowledge base covering career, finances, projects, and priorities. Makes planning and career advice concrete instead of generic.

The sprint planning pattern connects the context layer to a project management system. The model reads both the strategic context (why things matter) and the current ticket state (what’s open). Sprint planning becomes something the model can reason about, not just summarize.

The content creator pattern is a knowledge base of positions, research, and publication history. When you write, the model knows your voice, your constraints, your previous arguments.

The open-source version

I’ve published the templates, pattern documentation, and prompts as an open-source repository: github.com/trentonmercer/context-layer. Everything needed to understand and implement the system is there.

The assembly — adapting the templates to your specific stack, connecting to your PM system, configuring the session setup for your workflow — is the work that requires someone who’s done it before. That’s what Mercature does.