SR-SI is not a prompting technique. It is a context architecture for keeping AI coherent across a real product build.
I published the second version of the SR-SI research paper after months of using AI as the primary development collaborator across products such as Protocol, Gestalt, Neon Oracle, and Sila. The paper documents a simple problem: AI can be useful in one session and still lose the thread across a full build unless the project gives it a way to reconstruct context.
The usual fix is to paste more into the prompt: more brief, more examples, more background, and more instructions. That helps for a while, but it does not change the underlying architecture; the next session still begins with reorientation.
SR-SI stands for Simulated Recall via Shallow Indexing. Instead of loading the AI with everything it might need, the system maintains a shallow, navigable index of decisions, constraints, terminology, priorities, known failure modes, and the specific parts of the project that should be consulted before work begins.
That distinction matters. A full archive can store everything and still fail to orient the work, while a shallow index works because it tells the AI where to look and what to reconstruct for the task at hand.
In practical terms, sessions that used to begin with re-explaining the product could begin with the work. The AI still needed direction, review, and judgment, but it did not need the entire project reintroduced every time.
The bigger implication is team-level. When a shared index exists, the developer who has been on the product for a year and the developer who joined last month can start from a more comparable context base. The quality of AI output depends less on one person's briefing skill, and more on whether the team has built a usable context architecture.
That is why I treat SR-SI as methodology, not as a prompt trick. The goal is not to make the model sound informed for one session; the goal is to make product context reconstructable across the full lifespan of the work.
Read the full version: https://www.mghachem.com/2026-06-16-sr-si-the-methodology-for-ai-that-maintains-context-across-a-full-product-build/