All 127 posts in date order, newest first. ← back to topics
Twelve months of running multi-agent AI in a regulated context. SLIs that matter, the incident runbook, drift detection, continuous adversarial testing, secret rotation, compliance posture as code.
The RBI FREE-AI incident reporting form, expressed as a Go struct and a Postgres table. Every entry is an auto-generated artefact from the runtime — not a form an operator fills in retrospectively.
Every one of the 26 RBI FREE-AI recommendations, mapped to a specific file in a working multi-agent platform. What's ✅ done, what's 🟡 partial, what's ⚪ honest gap.
Stdlib over libraries, single binary over framework, fail-closed defaults over forgiveness. The boring-on-purpose case for choosing Go to ship a multi-agent system into a regulated environment.
Fallback agents plus a CI step that replaces the primary agent with one that always errors. If the fallback doesn't produce a usable answer, the PR can't merge.
Classification → provider allowlist. A pii-classified message can only reach a provider whose region is in the allowlist for pii. Sovereignty as a runtime gate, not a checkbox.
UPI, IMPS, NEFT, RTGS — which rail to use depends on amount, urgency, window, success-rate history. A deterministic chooser with a HITL gate above ₹2 lakh.
A tiny CEL-style DSL plus a board-approved YAML file. The risk team adds a governance rule by editing a config file; engineering ships the rule by restarting the service.
PAN check-digit validation, Aadhaar offline KYC, DigiLocker, PEP/sanctions — all in Go code, not in a prompt. The LLM's job is to translate the verdict into something a human can read.
Field notes from running multi-agent AI on K8s. The patterns the book recommends, the ones that survived contact with production, and the ones that broke in interesting ways.