Notes from the build
Agent orchestration, evals that can fail a deploy, and what happens when a benchmark turns out to be measuring nothing.
- 19 August 2026agents, pipelines, provenanceA pipeline that cannot invent your UIGenerated product videos show software that does not exist. Fixing that is not a prompting problem. It means making every frame cite the line of code it came from, and refusing to finish when it cannot.
- 18 August 2026infrastructure, containers, securityA container per job, without a daemonBuilding a bespoke image for every unit of work, from a package list rather than a Dockerfile, and why having no build step at all is the security property, not a limitation.
- 16 August 2026infrastructure, sandboxing, cloud-runTaking the network away from a Cloud Run jobRunning untrusted code with no egress, on managed infrastructure, without a VM you have to operate. The trick is one prefix, and the reason it looks broken at first is that loopback starts down.
- 10 August 2026agents, routing, evaluationWhat a routing benchmark cannot measureI set out to prove a routing architecture and killed my own hypothesis on day one. What survived is a condition the standard dialogue corpora fail, including one where not a single test dialogue contains the decision being benchmarked.
- 4 July 2026hiring, evals, hunrProving a challenge discriminates before anyone takes itEvery hunr challenge ships with two solutions: one an expert would write, one a plausible engineer would. If the hidden tests can't tell them apart, it never goes live.
- 18 May 2026agents, orchestration, productionWhy a sticky orchestrator beat a smarter routerWe kept trying to make the router smarter. What actually fixed support agents was refusing to re-route mid-conversation.
- 2 March 2026evals, ci, agents739 cases that can fail a buildAn eval suite nobody can block a deploy with is a dashboard. Here's what it took to make ours a gate.
