Investigation speed. Exam-ready proof.
Not a wrapper
Evidence-first workflow, not chat outputs.
How we're different
- Evidence collected automatically.
- Narratives cite every claim.
- Humans approve high-risk actions.
Trust rule: AI drafts, humans decide for sensitive outcomes.
Why this is different
Wrapper
Prompt
Text output
No provenance
Alertrun
Evidence
Graph
Cited narrative
Gates
Export
- Deterministic evidence ingestion.
- Citation enforcement on every narrative.
- Append-only audit log.
- Policy engine for approvals.
- Connector SDK for data sources.
- Model-agnostic LLM layer.