We're building an invoicing system with AI agents, in public

Description and use

DynoInvoice is an AI‑driven invoicing system governed by Keel, ensuring traceable requirements, automated reviews, and credential safety.

Problem

Developing a multi‑tenant invoicing system where mistakes are expensive, requiring strict data isolation, regulatory compliance, and auditability.

Outcome

The system now prevents agents from marking tasks as done without full commits, avoids looser interpretations of requirements, catches time‑sensitive test failures, ensures scans cover actual artifacts, enforces exact quotations, and eliminates agent‑to‑agent dispatch deadlocks.

Workflow

• Define requirement in Keel
• Agent drafts task and checks readiness
• Agent executes coding task and generates diff
• CI runs tests and automated gates
• Independent examiner reviews merge request
• Server marks task done based on CI verdict
• If issues arise, task is blocked and human answers questions
• Repeat until feature complete

Evidence

Agents fail in ways that look like success. A few things we caught, and what we changed:

Source

A coding agent reported a task complete with a green pipeline. It had pushed only scripts and fixtures; the main change was never committed.

Source

A test hard‑coded a moment in time while the SQL used the database clock. It was green when reviewed, then turned main red a couple of days later and blocked every merge request.

Source