Module 2 of 4 · Stages 02–03
Evaluate & Remediate
Objective
Find the important factual problems in your context and resolve them, without blocking anyone's work.
Runs as things change, then human review · Produces prioritized gaps and improved ground truth · Usually learning and development, or the subject-matter expert
In the loop
Evaluate extracts the material claims from your content and from what models say, and checks each one against the approved context that governs it. Remediate turns what fails that check into prioritized work.
| Do this | Call | Why |
|---|---|---|
| Track the questions that decide a purchase | POST /org/questions | Not the ones with the most volume. Volume is not the same as consequence. |
| Read how models answer today | GET /org/analytics/prompts | Evaluate before you write. Content with no gap behind it is content nobody asked for. |
| Let evaluation extract the claims | Each material claim is compared with the section of the context layer that governs it. This is the step that turns an answer into a gap — and it is not built yet. | |
| Send a gap with no source back to module 1 | POST /org/kb/raw | Remediating it here would mean inventing the answer. |
| Replace the source, do not add a second one | PUT /org/kb/nodes/{id}/file | Two versions of the same fact is the conflict you were trying to remove. |
Stage 02 — Evaluate
Your next customer isn't human.
These are the questions your buyers ask agents, by funnel stage. Someone gets cited in those answers. Pick your industry and see whether it is you.
Sign in and improve narrative control across your industry.
Representative rows, not live data. Yours come from your own tracked questions.
Not wired up yet
There is no public industry endpoint, and every organization route needs a key, so the rows above are representative rather than live. Your real rows come from your own tracked questions once you have an organization.
Stage 03 — Remediate
- 1Let evaluation extract and check claims.Each claim from each answer is compared with your context. It runs in the background as things change, not while you wait.
- 2Read the gaps, highest consequence first.Six kinds, below. Each names the sources involved.
- 3Decide the material ones.Supply what is missing, confirm which source governs, or reject the correction.Requires a human
- 4Write the resolution back into your sources.The previous version stays readable. Nothing is overwritten silently.
Prioritization happens inside Remediate. There is no separate stage called Prioritize.
Status
Claims evaluation is not built yet. What exists today are utility endpoints, not a running system, and none of it is in the published API. The intent is event-driven — evaluation fires as content and answers change, rather than on a nightly batch.
Why it is not instant
Checking every claim against your sources takes time, so results arrive after the fact rather than while you wait. Ingestion, search and answers stay available throughout.
A finished ingest does not mean your claims have been checked. If you are reporting state, say ingestion is done and evaluation is queued.
What a gap can be
Contradicted
An approved source says otherwise.
Unsupported
Nothing in your context backs it.
Missing evidence
Plausible, but nothing was found.
Stale
Correct once, past its freshness window.
Ambiguous authority
Two sources could govern; unclear which.
Source conflict
Both approved, and they disagree.
Gap
A factual problem evaluation found, waiting on a decision. Gaps are surfaced, never fixed on their own.
Full definition →Human gates
- Two approved sources disagree, or it is unclear which governs
- The claim affects price, policy, eligibility, coverage, compliance, safety or terms
- The fix would change what a published page means
An agent can summarize the evidence and recommend. It cannot rewrite a source of record or sign off for someone else.
How to reach it
/org/promptsOpen in API reference →Create a question to track. Typed awareness, consideration, evaluation or decision./org/analytics/mentionsOpen in API reference →Mention rate: the share of answered runs that named you./org/analytics/citationsOpen in API reference →Citation Rate, Coverage and Share, per tier and per source./org/kb/nodes/{id}/rawOpen in API reference →Correct a source. Cuts a new version; the old text stays readable./org/product-lines/{id}Open in API reference →Update a price, term or eligibility rule at its source of record.Every metric here has an exact denominator. Analytics has the math.
Rules for this module
- Surface conflicts. Do not pick a winner and edit the source to match.
- A claim that cannot be supported stays unresolved. It does not become true by default.
- Model answers are observations. They rank what to work on; they never overwrite a source.
- Ask the same questions each run, or the comparison means nothing.
Done when
- You know which questions you lose, and to whom
- Every gap names its type and the sources involved
- A person decided each material conflict, and it is recorded with the claim
- Nothing was corrected silently