Performance agents need a profile-to-commit receipt

Performance agents need a profile-to-commit receipt

Performance-agent reviews should bind the production profile, exact deployed commit, invariant tests and controlled canary in one receipt.

AI coding extensions need an install receipt

Sales AI needs a buyer-proof clock

EY's 3% result needs a friction-transfer ledger

EY's 3% clean-removal result is a triage signal; track where review, rework and recovery cost moves before deleting friction.

AI ROI needs an acceptance-to-EBIT bridge

4GB VRAM is not a 4GB capacity plan

AirLLM runs Llama 3.x 70B on about 4GB of VRAM by streaming layers from disk, which moves the constraint to host RAM, disk, latency and token rate.

Agent monitors need a tamper boundary

Health agents need separate expert and user gates

Health-agent releases need separate expert-safety and user-usability gates, with evaluator disagreement tracked instead of averaged away.

A 311-skill catalogue is a routing problem

ECC bundles 311 skills, but catalogue size does not prove useful routing; start with a narrow profile, inspect hooks and verify harness parity.

On-device AI needs a feature resource ladder