Principle

The Separation Principle.

Every Elevator entity has fields written for two readers: the user, and the integrator itself. Confusing them is how integrators drift.

scroll ↓
01

One entity, two readers

Every Evidence row is read by two different audiences after it's written. The user, scanning a UI to understand why a claim was assessed a certain way. And the integrator itself, returning on a later cycle to re-evaluate.

The fields are split deliberately. Some are narrative, for humans. Others are structured, for the integrator. Mixing them is how integrators drift.

02

What humans read

When a user opens this Evidence in Elevator, this is the part they engage with: rationale and concern_text. Prose. Reasoning. The explanation of why the integrator said what it said.

These fields exist to explain. They are written for one audience: the human. They are never re-consumed.

03

What the integrator reads

The machine-state fields are different. source_claim is the atomic claim, stated plainly. fragment_snapshot is a verbatim quote from the source document. confidence, status, and source_verified_at are calibration flags.

These are written once, with care, and re-consumed by future integrator cycles. They're structured because they have to be machine-readable a month from now.

04

The next cycle

A month later, the integrator returns to this Evidence — maybe because the source document changed, or because low confidence triggered a re-check. It re-reads the source document. And the machine-state fields.

It deliberately ignores its own previous rationale.

05

Why

Your own previous narrative is a hypothesis about what the source says. The source itself is the authority. If you re-read your own narrative on the next cycle, errors compound — a slightly generous initial assessment becomes the baseline for the next one, and drift accelerates.

The same split applies elsewhere. Question has findings, recommendations, proposed_answer for users — and source_extracts, source_responses, tagged_users for the integrator. Requirement has interpretive_context: append-only, citing every trigger. Different entity, same discipline.

that's the tour
Back to the Overview

The fundamentals come back to the same picture: humans bring the truth, the integrator brings the structure. Everything else is discipline.