No learned weights, none. Casebook runs on knowledge your team writes down, so the same evidence always produces the same reasoning. Explain your findings to the CISO in a language auditors accept.
Every investigation your team completes becomes memory the next investigation can use. Similar-case retrieval finds prior patterns. Baselines learn from your environment. Institutional knowledge stops dying when people leave.
Click any finding. See the exact events that triggered it. See the detection rule set that recognized the pattern. See the named human who taught that pattern. Named human author on every taught pattern.
Casebook is a system that executes operational knowledge your team authors. Not a model. Not a copilot. It runs written-down rules, it does not predict.
A construction-time neural network proposes typed structure — new evidence types, new patterns, new mappings. A human approves. A deterministic walker verifies. The safety checks gate the change. Then the runtime executes on your evidence with zero neural networks present — deterministic under pinned versions: same evaluator, same knowledge, same runtime produces the same output every time.
The receipts
If you've ever tried to defend a machine-learning alert to a CISO, an auditor, or a customer's legal team, you know the exact shape of the problem Casebook was built to solve.