Posts about the messy middle of AI adoption: workflows, tools, MCPs, review habits, data boundaries, and the small decisions that make or break automation inside a team.
How posts are edited8 min read
Company adoption
Seat utilization can inform a contract negotiation. It cannot show whether an AI-assisted workflow is useful, safe, supportable, or still worth renewing.
7 min read
AI infrastructure
Jev is designed to make bounded judgments that software can consume, not to draft prose. These three workflow designs show where that distinction helps—and where deterministic rules and human review must remain.
3 min read
AI infrastructure
NotchFuel makes the MacBook camera notch useful by keeping Claude Code, Codex, and Grok CLI usage visible without another dashboard.
10 min read
AI infrastructure
Use AI to plan, correlate, and document a penetration test, while deterministic tools, external policy, and a human tester retain control of every risky action.
8 min read
Company adoption
An AI rollout can remove drafting while adding review, exception handling, surveillance, and accountability. A work-delta review makes that transfer visible before launch.
9 min read
AI infrastructure
Two ordinary writes create a crash gap between an agent's decision and its external effect. Commit the decision and an outbox event together, then let a conventional relay handle delivery.