๐Ÿ”AI RiskAtlas
โ† All systems

Human + AI Professional Workflow

A person uses AI for a high-stakes task, then acts on the output

Architecture introduced 27 May 2023

A real professional โ€” a lawyer, a support agent โ€” asks an AI for help, then files or sends whatever it produced. The AI advises; the human is the one who acts. If nobody checks the AI's work, its mistakes become real.

Human + AIVerification (often skipped)Real world / system of recordasks for help๐Ÿง‘โ€โš–๏ธHuman Operator๐Ÿง AI assistantโœ‹Independentverification๐Ÿ—„๏ธSystem ofrecord (court /
InstructionsDataActionsControl / decisionFeedback / logs
๐Ÿ‘† Click any component in the diagram to inspect its risks & defenses

Follow a request ยท step 1 of 4

A professional asks the AI to help with a real task.

AI RiskAtlas is an educational model of how GenAI & agentic systems work and fail. Architectures and payloads are illustrative and simplified for learning โ€” not operational guidance. Real-world cases are summarised from public reporting.

Sources & further reading โ†’ยทBuilt by Shi Yuan โ†—