Executive Summary

IntentSutra AI is a local-first, open-source command-line workbench that turns a rough feature request into versioned, reviewable requirements and then keeps an honest record of the evidence behind each one. Its single organizing rule: it must be harder, not easier, to claim a requirement is complete without real, reviewable proof. Version 0.2.1, Apache-2.0, created by Vatsal Shah.

The problem

Teams routinely treat a closed ticket, a merged pull request, a test file or a green status field as proof that a requirement is done. None of these is proof. Approvals get attached to text that later changed. Evidence goes stale silently. Auditors then cannot tell what was actually reviewed, by whom, against which version.

What IntentSutra does

NeedWhat the tool does
Capture intentImports Markdown or JSON; assigns stable IDs; records the SHA-256 of the source
Expose unknownsGenerates explicit questions (actor, trigger, constraints, authorization, delivery failure, money) and never invents answers
Draft acceptanceProduces five candidate Gherkin scenarios marked unapproved, with [TO CONFIRM] placeholders
Keep humans accountableApproval requires a named reviewer, a note, the exact revision and an explicit --confirm-human flag
Bind evidence to versionsEvery link carries the requirement revision; a new revision makes old approvals and links stale, preserved as history
Detect driftRe-hashes linked files; a changed file is reported as hash-mismatch
Prove it independentlyintentsutra audit re-derives every claim and writes a sealed report as JSON, Markdown and HTML

What it deliberately does not do

Evidence this release works

Recorded 2026-11-22T18:43:05.809Z on Node v24.15.0 (win32/x64):

CheckResult
Automated tests118 total, 116 passed, 0 failed, 2 skipped
Independent audit of the demo workspace11 of 11 checks passed; verdict PASS
Same workspace after a silent registry editverdict FAIL (forgery detected)
Fuzzing, fixed seed5398 generated inputs, 0 unexpected exceptions or undetected tampering

Raw logs, transcripts and sealed sample reports are linked from the test report and the assurance page.

Who benefits

Product owners and business analysts (clear unknowns and approvals), engineering leads (version-bound traceability), QA engineers (test file is not a test pass), release managers (stale evidence cannot be promoted) and internal auditors (a hash-chained log and a reproducible audit report).

Maturity, stated plainly

Verified offline starter (milestone M0) plus an independent audit report. Authored but not runtime-verified: native activation in the nine supported IDEs, optional MCP/GitHub/Jira connectors. Not built: real test-execution capture, verified identity, signed audit, dashboard, multi-user server. See the roadmap.