Evidence‑Gated Agency: building an agent that can’t be optimistic

Description and use

An automated agent that verifies government funding calls against municipal project data, preventing errors and improving funding capture efficiency.

Problem

Municipalities in Colombia lose public funding because staff cannot monitor procurement portals and match funding calls to their project data in a timely way.

Outcome

The agent reliably identifies eligible funding calls, prevents hallucinated or incorrect filings, and provides transparent, actionable reports to municipal staff, improving funding capture and maintaining credibility.

Workflow

• 1. Agent schedules periodic checks of official procurement portals.
• 2. For each new funding call, agent extracts requirement text and matches it against municipality’s structured project data.
• 3. Agent requests verbatim quotes from the source document for any numeric or date information.
• 4. Code verifies quotes literally exist in the source and parses numbers only from verified text.
• 5. Four gates are applied: requirement evaluable, quote verified, attribute has real value, and a subtractive adversary model pass that can only refute.
• 6. If all gates pass, agent marks requirement as met; otherwise it records an honest zero with missing pieces and owners.
• 7. Agent drafts filing and messages planning secretary overnight for human review.
• 8. Human reviews, decides, and files the application.

Evidence

The model reads a source document and returns a verbatim quote — the exact span of text that declares the amount.

Source

Four gates before any "requirement met"

Source

The honest zero is a first‑class output

Source