Brains

Origin

Every conversation with a language-model assistant starts at zero. Voice preferences drift, project state is re-explained, hard-won corrections evaporate. After enough sessions you realize you are not actually working with an assistant — you are conducting a series of first dates that happen to be productive.

Problem

What's needed is not a longer context window. What's needed is structure: a place where facts, directives, corrections, decisions, and predictions live as first-class rows that any assistant in the rotation can read and write. The cognitive infrastructure has to outlive the conversation.

Approach

A relational substrate for first-class persistent cognition. Facts, directives (rules to follow), corrections (mistakes not to repeat), decisions (with their alternatives and beliefs intact), predictions (with verification windows), voice laws (how to write), and tool profiles all live as structured rows. Operates as a shared MCP layer; every assistant in the rotation reads from and writes to the same brain. Predictions are graded against reality on a fixed loop; calibration drift triggers updates across the directive set.

Methodology

The schema is opinionated by design. There is no 'notes' bag. A correction has explicit shape — what was wrong, what is correct, how dangerous, in what context — because the kind of correction that matters has structure, and the kind that doesn't, doesn't belong here. A decision is recorded with the alternatives that were on the table, because the alternatives are usually what makes the decision interesting. Voice laws are versioned because what one assistant calls 'tone' another calls 'formatting', and the only way to keep them in sync is to write the rules down where both can read.

Selected milestones

• Operational across multiple assistants
• Prediction-verification loop in production on a fixed cadence
• Voice laws and corrections enforced on every session start

Open questions

• How calibration drift propagates across distinct domains (markets vs. conservation vs. infrastructure)
• Where the line is between a correction (rule-shaped) and a fact (claim-shaped)
• What happens when two assistants disagree about a directive's scope

Ask me about

• How predictions are graded against reality on a fixed loop
• Why the schema is so opinionated — and what gets thrown out
• What 'voice laws' are, structurally, and how they survive across model upgrades
• How a correction differs from a fact in the schema

Stack