SBSayok Boseinsayok.hashnode.dev·5d ago · 8 min readYour first AI SRE: I gave the worst hour of on-call to a team of agents, and they diagnosed the incident, scored their own confidence, and opened the fix.TL;DR The first hour of almost every incident is toil. Find the service, check the last deploy, read the logs, form a hypothesis, guess how confident you are. Same motions, every time, usually at 2am00
SBSayok Boseinsayok.hashnode.dev·Jun 4 · 6 min readPart 5 of 6: The Regulation That Cannot See the Bias It Was Built to Catch.TL;DR: The EU AI Act's high-risk provisions take effect August 2026. Your multi-agent pipeline is covered. But the regulation doesn't define "bias," doesn't require population-level testing, and can't00
SBSayok Boseinsayok.hashnode.dev·Jun 4 · 12 min readPart 6 of 6: How to Build Pipelines That Don't Gaslight Themselves.TL;DR: Six parts of bad news. Here's what actually helps — with code. Cross-family judges reduce the core bias. Structured multi-dimensional evaluation cuts it by 31.5%. Chain-of-thought adds 1.5 to 100
SBSayok Boseinsayok.hashnode.dev·Jun 4 · 6 min readThe Regulation That Cannot See the Bias It Was Built to Catch.TL;DR: The EU AI Act's high-risk provisions take effect August 2026. Your multi-agent pipeline is covered. But the regulation doesn't define "bias," doesn't require population-level testing, and can't00
SBSayok Boseinsayok.hashnode.dev·Jun 4 · 7 min readPart 4 of 6: One Rogue Agent. The Whole Swarm Followed.TL;DR: One adversarial agent. 2% of the population. That was enough to flip the entire swarm's behaviour. This is prompt injection at population scale — and your individual security audits can't see i00
