Lians is the system of record for AI in regulated workflows. Preserve exact source, prompt, policy, permission, model, and tool versions so teams can reconstruct agent decisions after the underlying facts change.

Hi Product Hunt, I am Ethan, co-founder of Lians. AI audit logs usually record prompts, outputs, and tool calls. That works until the underlying policy, filing, entity record, or external source changes. Replaying the workflow with today's data produces a new decision, not the original one. We built Lians to reconstruct what an AI system knew, did, and why at the moment a decision was made. It preserves the exact evidence, prompts, policies, permissions, source versions, models, and tools active during a run. We are three weeks old, pre-1.0, and the product is live. We are opening a founding cohort for 5 to 7 design partners in financial research, risk, compliance, and other evidence-heavy agent workflows. We would especially value feedback from teams whose agents depend on facts or rules that change over time. What breaks first in your current audit trail when the facts change?

would love a diff view that highlights what changed between two agent runs so I can quickly see why a decision shifted when the underlying data or model version was updated

Lians

Reconstruct what AI knew, did, and why at decision time

Reconstruct what AI knew, did, and why at decision time