Skip to content
Live from production

The Receipts

Our platform mines its own failures, writes its own fixes, ships them through gated deploys, measures the result, and reverts regressions. This page is the log.

Every entry below is a real production record — dates, ship times, and root causes as the system wrote them. No human approved these ships; a human audits them afterward.

8
improvements it shipped itself since Jul 5
126
tickets handled in the last 30 days
<6%
of tickets needed a human
14 min
fastest self-filed ticket to live fix

30-day window ending Jul 13, 2026: 126 tickets — 28 self-healed code fixes, 30 questions answered, 17 resolved, 8 with verified outcomes; 7 needed a human.

Self-shipped improvements

Eight improvements the system identified, specified, and shipped itself — four of them in a single 92-minute window on the evening of July 5.

Jul 5, 2026Builder

Repeat-ask guardrail

Detected that users sometimes ask for the same change twice because the previous build didn't actually apply it (zero diff) or the change wasn't visible in the preview. Shipped a gate that verifies a build changed what the user asked for before declaring it done.

Jul 5, 2026Builder

Autofix retry-loop breaker

Found its own retry loops: fix attempts that didn't change the code kept being retried. Shipped a breaker that requires a root-cause diagnosis before another attempt is allowed.

Jul 5, 2026Builder

Zero-diff rebuild gate

Noticed rebuilds that produce no delta (the change was already present, or the feedback wasn't actionable) waste compute and erode trust. Shipped an abort gate for zero-diff refines.

Jul 5, 2026Support agent

Thread-artifact grounding for email replies

Caught itself answering “this” and “it” on long email threads from the latest message only. Shipped grounding that resolves pronouns against the artifact the thread was originally about.

Jul 8, 2026New capability14 minutes, filed to live

Product catalog lookup

Couldn't answer “which existing apps match this capability profile?” — so it specified the missing internal lookup, filed its own work order, and shipped it. Fourteen minutes from self-filed ticket to healed.

Jul 8, 2026New capability

Test-run history lookup

Couldn't check whether a requested test had already been executed, or retrieve its results. Specified and shipped the query capability for its own test-run history.

Jul 10, 2026New capability

Spreadsheet formula tracing

Was asked how a number in a proposal was derived from a linked Google Sheet and couldn't trace cell values and formulas. Shipped the tracing capability.

Jul 12, 2026New capability33 minutes, filed to live

Attachment content analysis

Couldn't read a .docx attachment well enough to extract a calculation methodology. Shipped document-content extraction for attachments — 33 minutes from self-filed ticket to healed.

How the loop works

The system never edits code directly. It names failure classes, proposes fixes, and files work orders into the same gated pipeline every human change goes through.

01

Mine

Clusters 30 days of escaped failures — tickets a human had to touch, retries, repeat asks — into named failure classes. 39 classes mined so far.

02

Propose

For each recurring class, drafts a guardrail or missing capability, grounded in how the actual tickets were resolved — with an adversarial self-review and a confidence score.

03

Gate

Every ship goes through the same pipeline as human changes: compile checks, a gold test-suite floor, and smoke tests before traffic flips.

04

Ship

Files its own work order and implements through the standard pipeline. One ship in flight at a time. No human approval since July 4 — a human audits after the fact.

05

Measure

Each shipped guardrail gets a verified reward: recurrence of its failure class in equal windows before vs. after ship.

06

Revert

A guardrail that regresses its own metric is automatically reverted, and its failure class is marked human-only forever.

What keeps it honest

  • Correctness-anchored circuit breaker: if resolution quality degrades week-over-week, autonomous shipping pauses itself and emails the founder.
  • Every self-shipped change rides the same smoke-gated deploy pipeline as human commits — nothing skips the gates.
  • Per-guardrail verified reward; regressions auto-revert.
  • Security-sensitive surfaces (auth, tokens, access control, billing) are fenced off from autonomous changes.
  • One-line kill switch, and a daily audit briefing to a human.

Don't take the log's word for it

Send us any back-office workflow. The same system builds you working software in 24 hours.

Intuist is raising a $3M seed. Investors: write to [email protected] or open in Gmail.