Making AI-assisted intake reviewable.
Methodology published on SSRN·Interactive walkthrough available·U.S. provisional patent application filed
Most AI intake systems preserve useful artifacts: transcripts, summaries, and structured fields. But when someone later asks what supported a particular matter classification, urgency determination, or other assessment, the answer is often buried in the original conversation.
Antecedent preserves that supporting structure in the Decision Record itself.
The Decision Record preserves what was observed, which observations support each assessment, and which observations were preserved but remained unlinked.
A reviewer no longer has to reconstruct the assessment from the original conversation. The basis is in the record.
Open the interactive walkthrough →A Decision Record is a structured record of what was observed during an intake interaction, which observations support each assessment, and which observations were preserved but remained unlinked. It is created during the intake workflow rather than reconstructed later.
A transcript shows what was said. A summary condenses it. A Decision Record shows the specific observations supporting each assessment. Without that structure, someone reviewing the matter later must return to the original conversation and interpret it again.
The Decision Record doesn't tell you how the model thought. It tells you what the system committed to at the moment the assessment was made. That commitment is stable and reviewable. An AI-generated explanation produced after the fact can change every time someone asks. The Decision Record cannot.
Not necessarily. The protocol can be incorporated into human, AI-assisted, or hybrid intake workflows. The Decision Record uses the same underlying structure regardless of who or what performs the intake.
Contact us at contact@antecedentinc.ai.