Notes from the lab

Engineering, product, and POV on the agent teams Super Genius Labs is putting into production.

68 notes3 tracksLatest Oct 16, 2026Editorial team RSS feed

Latest notes

A metric-version ledger can separate changed agent behavior from changed KPI definitions when observability formulas move.

Evaluate Haiku 5.5 by workload volume, latency tolerance, context size, and escalation cost before changing production routes.

A WebMCP review should reveal how each client interprets risk annotations across primary and fallback browser routes.

A decision-specific interview approach keeps healthcare AI research tied to setting, action, expectations, and evidence limits.

Measure repository writes, shared-ref contention, CI fan-out, cache behavior, and review queues before raising agent concurrency.

Treat an agent-generated infrastructure pull request as a handoff artifact, with deployment and cutover evidence still to come.

A channel-choice test helps medical practices assess whether an AI receptionist preserves usable routes and clear next steps.

Turn Claude Agent SDK 0.3.287 release notes into focused regression fixtures for host-visible events, states, and cleanup.

Sonnet 5.5 pairs half the listed token price of Opus 5.5 with a nearby result on one reported benchmark.

A route-level ledger separates Grok 4.7’s umbrella launch from dated availability records for its API, Copilot, and Bedrock.