Early accessFree during early access: draft a course from your own document in minutes.Try it now →
RoadmapGovern · Evidence Graph

Every claim in your training, linked to the passage that supports it

An evidence graph connects each source clause to the objectives, lessons, questions, scenarios and tutor answers that rely on it. Reviewers see why every sentence is there; when a clause changes, you know precisely what it touches.

Evidence Graph preview with fictional sample data

Illustrative preview of the roadmap workbench · fictional sample data

RoadmapA product direction we are designing toward. Not available today. The workbench shows an interactive preview with illustrative data.
Capabilities

What Evidence Graph does

Claim-level citations

Each instructional claim points to a page, section and paragraph in an approved source.

Roadmap

Unsupported-claim flags

Statements without support are flagged before review, not after release.

Roadmap

Impact in one click

Select a clause and see every lesson, item and answer that depends on it.

Roadmap

Approval trail

Who approved the source and the claim, and when.

Roadmap

Tutor grounding

The governed tutor answers only from claims in the graph.

Roadmap

Exportable evidence

Hand an auditor the claim-to-source map for any release.

Roadmap
How it works

From source to release

STEP 01

Extract claims

Instructional statements are identified in every lesson.

STEP 02

Link evidence

Each is matched to the passage that supports it, or flagged.

STEP 03

Review

Reviewers confirm or fix links in context.

STEP 04

Reuse

Change analysis, tutor answers and audits all read the same graph.

Try it

Interactive preview

A front-end demonstration with fictional data, so you can feel the workflow before it ships. Nothing here touches a real system.

evidence/lesson 03
Illustrative data

Select a claim to see its support.

Notify Tier 2 within 15 minutes of P1 classification.
Source Incident policy v15 · p.14 · §4.2 ¶1Status Directly supportedUsed by L03 script · Q14 · Scenario 2 · 2 tutor answers
Page the incident commander if Tier 2 doesn't acknowledge in 5 minutes.
Most P1s are resolved within an hour.
Depth

Designed for the hard cases

The details that separate a governed system from a generator. All of these are roadmap design, shown so you can judge the direction.

Under the hoodRoadmap

Claims and obligations

Extracts what a source requires, of whom, and under what conditions.

Under the hoodRoadmap

Applicability & criticality

Which roles a rule applies to, and how much it matters if it's wrong.

Under the hoodRoadmap

Authority hierarchy

When sources disagree, the higher authority wins and the conflict is flagged.

Under the hoodRoadmap

Learning BOM

A bill of materials for every course: the sources, versions and approvals inside it.

Under the hoodRoadmap

Coverage graph

Which critical obligations have no lesson or assessment yet.

Under the hoodRoadmap

Proof-carrying releases

Each release ships with the evidence that supports it.

Honest status

What works today, and what is coming

Today

Live today
  • Drafts are written from your source only, and review notes flag claims to check

Open the app →

On the roadmap

Roadmap
  • Claim extraction and source linking
  • Unsupported-claim flags in review
  • Impact view per clause
  • Evidence export per release

See the roadmap →

FAQ

Questions

Is this the same as citations in a chatbot?
It's stricter. Citations are attached to every claim in the course, checked before release, and reused when a source changes, not generated after the fact for one answer.
Does it prove training is correct?
No system can. It makes support visible and reviewable, so experts spend their time on what isn't supported.

Start with the part that works today

Draft a course from your own document in minutes. The rest of the platform is being built in the open.

Free during early access · No account needed · We don't keep your files