The Machine That Builds Failproof: an engineering session
Most of the code in Failproof is written by agents. A spec goes in, several coding agents work on it in parallel, and what comes out gets shipped. The agents building Failproof run under Failproof: every tool call they make goes through our own policies, and every run is traced.
Nivedit Jain (niveditjain), co-founder and CTO of Failproof AI, will open up the whole setup and walk through how it actually works day to day.
This is an engineering session, not a product demo. Here's what you'll get into:
The loop, end to end. How a piece of work goes from a spec to shipped code: how specs are written, how work gets split across agents, and where humans still step in.
Running agents in parallel without chaos. How [number] agents work on the same codebase at once, how they avoid stepping on each other, and what happens when two of them disagree.
Eating our own cooking. The policies we run on our own agents, what they block, what they correct, and the ones we had to rewrite because they got in the way.
Traces as the feedback loop. How failed runs from the machine turn into better specs and new policies, so the same mistake doesn't happen twice.
What still breaks. The failure modes we haven't solved, the tasks we still don't hand to agents, and why.
Your questions, live. The last 20 minutes are open. Bring your own setup and what you're stuck on.
Schedule
6:00 · the machine, end to end
6:15 · walkthrough of real runs, including the failed ones
6:40 · open Q&A
For engineers and founders who build with coding agents every day and want to see how a small team runs them at scale.
Tuesday, November 3 · 6:00 to 7:00 pm PT