Skip to content

Governance, Safety & Risk Management

5 build exercises to practise the concepts in this domain.

5.1 — Map the Control Surfaces for One Claude System

Advanced
45 minutes
  • How to state a risk in the language a user or regulator would use rather than in control jargon
  • How to assign each risk to the one surface that can actually hold it
  • How to test whether a second, independent layer really exists
  • How to find every risk currently carried by wording alone
  • How to red-team a design so scoping, not phrasing, is what stops the payload

5.2 — Write the Risk Register for One Claude System

Advanced
45 minutes
  • How to separate irreversible actions from reversible ones and name who bears each consequence
  • How to work the durable limitation classes into concrete rows for a specific system
  • How to give every row a mechanism, a blast radius, a detection signal, an owning control and a named accepter
  • How to rank by consequence and detectability instead of likelihood
  • How to test a register against the question of what would move in the telemetry first

5.3 — Design and Stress-Test the Human-Oversight Layer

Advanced
45 minutes
  • How to classify every action by reversibility and by the window in which reversal is still possible
  • How to select between the five oversight patterns on evidence rather than on comfort
  • How to recognise when a qualified reviewer is required rather than optional
  • How to specify the evidence and the time budget a reviewer needs to be effective
  • How to set the override rate at which you would conclude the gate is decorative

5.4 — Trace the Compliance Path for One Regulated System

Advanced
45 minutes
  • How to enumerate every hop a regulated data class reaches, including the ones built for observability and evaluation
  • How to test each hop against purpose, retention, location and the agreement that covers it today
  • How to locate the first gap and understand what inherits it downstream
  • How to prefer remedies that reduce what crosses over remedies that leave the flow intact
  • How to write the deletion story and find the copy you could not currently reach

5.5 — Write the Ethics Page for One System That Decides About People

Advanced
60 minutes
  • How to write a harm hypothesis and derive cohorts from it rather than from available fields
  • How to find the proxies in a feature set and test whether each one carries the signal
  • How to choose a fairness criterion and defend it against the ones you rejected
  • How to work the remediation ladder without falling back on the base model
  • How to turn the three transparency obligations into concrete artefacts with a named accountable owner