The learning plane
The watchdog reads receipts and labels, remembers patterns, and can raise the next verdict toward caution. It is never inside the verdict path: a poisoned entry can mis-flag one check at worst, it can never rewrite the checks.
the watchdog can raise the next verdict toward caution. it can never lower one, and it never rewrites a check.
Alert feed
REALrules tier. one alert per receipt on its highest severity signal; time-to-alert is measured, not asserted.
- no refusals in this window yet. run a replay below and one lands here.
Threat graph
REALnodes are agents, mandates and threat classes read from the log; edges are the receipts that link them. counterparty alerts point at the two loaded feeds.
CrowdStrike Threat Graph visual grammar, our honest claims. a lit node is a receipt from the last few seconds.
Trip the threshold
The one moment that makes the watchdog a product instead of a dashboard.
run the prompt-injection replay. the first time it is a DENY and an alert. the second time the watchdog has flagged the pattern for this session, and the escalation happens before the engine finishes: the matching action is pushed to DENY through the core.
empty. it fills with the first refused replay.
Held-out baseline vs current engine
We will not claim the watchdog learned something until a receipt proves it against a held-out baseline on a fixed replay set. Until that receipt exists this panel stays empty on purpose.
the Darktrace rule: a learned signal is shown when it beats the held-out baseline, with the receipt that proves it, and not one day before.
Per-agent behavioural baselines
Pick an agent and see its normal band, built from its own receipt history, with deviations marked.
the agent's normal band, built from its own receipt history. deviations are marked. the receipt holds fingerprints, not amounts, so the band is hours, cadence and latency; amounts and counterparties join the band when the base adapter lands.
the band appears once the log holds an agent.