Good judgment needs
something to work on.
Follow the evidence, question the first answer, and make a decision you can explain.
Read. Decide. Compare.
Each case includes the information needed to make a recommendation. Write your own decision before opening the worked answer. The goal is to make your reasoning visible.
The convincing brief with unsupported claims
Audit an AI-assisted briefing, separate citation identity from claim support, and produce a defensible revision.
Explore the case →Practitioner · Worked caseThe automation that moved the bottleneck
Follow a support-drafting pilot through misleading time savings, a failed handoff, and a bounded redesign.
Explore the case →Expert · Worked caseThe agent that passed the wrong test
Inspect an apparently strong evaluation, uncover a critical permission failure, and write a defensible release memo.
Explore the case →Choose a case by the decision you face.
Publishing a claim? Start with the research brief. Improving a process? Inspect the support workflow. Releasing a connected system? Review the agent evaluation.
These longer cases complement the short scenario labs on the homepage. They add evidence packets, completed reviews, and reusable worksheets.