An AI claims assistant has reviewed a single claim and proposes a high-blast-radius 3-action bundle. This page is a guided demo: pick a persona, review the case, submit the AI's proposal to HELM, see the deterministic decision, then take the next-step action that belongs to your role.
Four steps. Each persona sees the same case differently and takes different next-step actions. Try at least two personas to feel the architecture.
Five roles in the same insurance organization. Each has different authority, different views, and different next steps.
Same claim packet for everyone — but the framing card shows how your role reads the situation.
The deterministic gate evaluates 6 checks. The eval is the same regardless of persona — HELM is not opinion-based.
After the decision, your persona panel on the right shows what you can actually do next. The interactive ones expand inline.
The way KAiM engages is concrete: pick one high-risk AI-assisted workflow you're worried about — claim triage, code review, public claims, refunds, vendor onboarding, something else. We map it to actor / action / authority / policy / evidence / escalation, then show how HELM gates it. No deck. No demo theater. A working session.