All books
Compare the outcome you want, then open a book. Filter by level and track.
Progress is saved in this browser only.
5 books
AI harnesses5
- T20-L01Same Model, Different Harness: See What the Program Around the AI ChangesA four-row comparison table (three given runs plus your own OpenCode run) with result, minutes and step counts, one sentence naming the biggest difference, and three lines for your own task: the task, a check the agent cannot see, and two measures.
- T20-L02Choose a Harness by Testing It on Five of Your Own TasksA ten-row table (five tasks x two harnesses: known answer, minutes, three habits) and a recommendation of at most five lines naming the pick, the deciding score, the habit that mattered, what the test did not cover and when to test again.
- T20-L03Run a Harness on a Model You Control: Local Server or Team GatewayA half-page set-up guide: approved model and where it runs, the four values per harness, the practice task result (2.000) per harness, and one provoked failure with how each harness reported it.
- T20-L04Set Up a Harness So a Mistake Stays Small: Container, Rules, Keys and NetworkThe four promises with their layers, the two probe rows (before and after), and the practice task result in the final set-up. Passes when the after-row shows internet and writing outside blocked, no promise depends on a harness rule alone, the key expires and is limited to one model, and a colleague can rerun the probe.
- T20-L05Run Coding Agents for a Team: Shared Rules, a Test Set, Nightly Jobs and No Lock-InHouse rules with their checks, the four-row run table, links to one passing and one deliberately failed workflow run, and the operator log. Passes when every rule has a check, the job fails on a broken rule even if the agent reports success, harness/model/gateway are single settings, and the log names the next test-set date.