Preview: Keep a Team of Agents Running for Months, With Memory a Person Approves
Level L05
T07
19 min read
Run several agents that colleagues depend on, over months: keep the number of agents small, let a person approve every note they remember, log every run, review four numbers weekly, handle incidents with a written runbook, keep an audit folder, and hand it all to a deputy who has run it.
Matching textT07-L05 · Agents · Level 5 Operator · 20-minute read, plus 3 hours of doing and 15 minutes a week Keep a Team of Agents Running for Months, With Memory a Person Approves A
Preview: Connect an Agent to a Real Mailbox Without Handing It the Keys
Level L04
T07
22 min read
Let an agent work on a real mailbox or business system while it holds no credentials itself: two small scripts hold one narrow key, IT limits it to one mailbox, a gate checks every draft, a person sends. Test it with planted instructions, prove what the key can't do, and know how to switch it off.
Matching textT07-L04 · Agents · Level 4 Integrator · 18-minute read, plus 4 hours of doing and a week of waiting for IT Connect an Agent to a Real Mailbox Without Handing It the Keys
Preview: Build a Small Agent Your Colleagues Can Run, Test and Stop
Level L03
T07
20 min read
Package a small agent that drafts, and never sends: instructions in a file, tool permissions the software enforces, a turn and spend limit, a test set of requests with known answers, a check script and a README. Decide first whether the job needs an agent at all, and stop where real credentials begin.
Matching textT07-L03 · Agents · Level 3 Builder · 17-minute read, plus 3 hours of doing Build a Small Agent Your Colleagues Can Run, Test and Stop The agent that promised Friday A genomics core
Preview: Taming Rogue AI Agents with Observability-Driven Evaluation — Jim Bennett, Galileo
youtube
Turn observed production failures into evaluations and feedback. Galileo/agent examples, not book's dashboard, database or retention policy.
Matching text… or handover. No additional monitoring product is required.
T07-L05: Learn to inspect agent traces, define evaluation contracts and turn failures into proposed improvements with human feedback.…
Preview: Claude Agent SDK [Full Workshop] — Thariq Shihipar, Anthropic
youtube
Understand agent/harness choices, scoped access and verification. Long SDK workshop; recommend relevant sections, not exact book folder/check.py configuration.
Matching textT07-L03: Use the workshop's workflow-versus-agent, harness and verification discussions to understand a reusable agent's moving parts. It is a long SDK workshop, not the book's folder/check.py…