Startup Ops
I Used to Handle Marketing. Now I Manage Coding Agents Too.
Coding agents have changed my working day. I still have to decide who the products are for, and I want more than my own assumptions to work with.
Sep 29, 2026
#
AI Agents
24 posts
Engineering
The Bill Is Authorised by Delivery, Not by Your Spend
Paying a vendor feels like it should authorise charging the client. It does not, and the wording that says it does once billed 900 credits for a video that did not exist.
Sep 18, 2026
Startup Ops
The Cheapest Way to Run an AI Product Is to Not Pay for It
Three products now let the user's own Claude plan pay for inference. Anthropic's terms permit one shape of that and ban another, and you cannot tell which.
Sep 17, 2026
AI & Automation
We Shipped an Agent-Native API Without OpenAPI
No /openapi.json, no generator, no spec to drift. The machine-readable entry point is the MCP server's tools/list — and that turned out to be the honest choice, not the lazy one.
Sep 17, 2026
Engineering
Negotiate the Format Before You Pay the Vendor
A 3% aspect mismatch is a rounding error. A 40% one is a different video. The threshold between them decides whether you refuse before the bill or apologise after.
Sep 16, 2026
AI & Automation
Never Answer an Agent With a Silent Substitution
An unmet parameter should come back named. We learned why the hard way: two warnings went missing for weeks and every test stayed green.
Sep 15, 2026
Engineering
One Reviewer Approved It. The Other Found the Bug.
Six blockers across four consecutive stories, and the two reviews agreed on one of them. Here is what running both actually cost us, and the rule we ended up with.
Sep 14, 2026
AI & Automation
Your Agent Can Branch on a Refusal. It Cannot Branch on a Warning.
Refusals in our API carry stable codes. Warnings carry none, on purpose — and the bug that proved why cost us two warnings nobody noticed were missing.
Sep 12, 2026
Engineering
We Charged 900 Credits for a Video That Didn't Exist
Our billing rule said: failed run after a paid vendor call means we charge. It sounded fair. On a run that only paid for speech, it was false, and it cost a customer.
Sep 3, 2026
Engineering
Your Agent Isn't Confused. Your Schema Lied to It.
Teams blame MCP when agents fumble their tools. We shipped an MCP server for a video API and found the real defect: offering a field you answer with a 400.
Sep 3, 2026
AI & Automation
Why Multi-Step AI Agents Compound Failure
TL;DR: A 95%-accurate agent step sounds safe, but ten steps land you near 60% and twenty near 36%. Multi-step chains multiply their error. Cut the chain, verify between steps, gate the risky actions.
Jun 29, 2026
AI & Automation
Silent-Success Drift: Why Your AI Agent Lies About Winning
TL;DR: A third or more of AI agent failures aren't crashes. They're agents reporting success for work that didn't happen. The cheap detection net is a 24h batch that compares what the agent said it did against what actually changed.
Jun 27, 2026