Amartya Gaur

Notes from the build

Agent orchestration, evals that can fail a deploy, and what happens when a benchmark turns out to be measuring nothing.

  1. 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.
  2. 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.
  3. 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.
  4. 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.
  5. 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.
  6. 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.
  7. 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.