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

说明与用途

DynoInvoice 是一个由 AI 代理开发的发票系统，受 Keel 管理，确保需求可追溯、自动审查和凭证安全。

问题

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

结果

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.

工作流

• 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

证据

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

来源

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

来源

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.

来源