An AI agent audited my Raft database and found a critical bug. Then I caught the agent’s own mistake.

I asked an AI agent to audit my own distributed database. It found a critical bug. Then I had to catch the agent's own mistake.

I built Phalanx, a Raft key-value store in Go replicated across 5 regions. I wanted to know if my docs matched my code, so I gave an AI agent strict rules: never invent a number, save raw output for every claim, write a failing test before each fix, and report anything where my docs and my code disagree.

What it found:

• Raft log entries were never written to disk. A restarted node would have lost acknowledged data.
• Seven more gaps between what I'd claimed and what the code did (pre-vote never initiated, no snapshots, gossip bypassing consensus, and more).
• I fixed all eight, test by test. A linearizability checker (Porcupine) now passes 99 of 100 randomized failure runs.

The part I think matters for this community: the agent's first benchmark report looked great, and some of it was wrong. Its cross-region latency numbers were identical before and after my changes, which means they were never measured. I caught it by reading the data, not the summary.

My takeaway: AI is great at running the audit. It's not safe to trust its conclusions without raw evidence and tests.

I wrote it all up, limits included, in a 32-page report: github.com/tijani-web/tijani-web/blob/main/docs/Basit-Tijani-Systems-Architecture-Rev2-DARK.pdf

I'm also looking for my next role: backend/infrastructure engineer (Go, Java; Raft, Kafka, Kubernetes), remote or with relocation sponsorship. I'm based in Lagos.

Question for the room: if your team hires infra engineers remotely, or you've made a move like this yourself, what worked? Real names and companies welcome.