Building Agent-Callable Evidence from Government Open Data

Описание и применение

CivicDataForge разработала рабочий процесс для преобразования открытых государственных данных в доказательства, пригодные для использования ИИ-агентами. Решение включает обработку пагинации, явную семантику решений (например, «нет опубликованного совпадения») и строгое отслеживание происхождения данных.

Задача

Government open data is often incomplete, paginated, or structurally inconsistent, making it unreliable for production systems or AI agents that require definitive evidence rather than just raw data.

Результат

The team established a rigorous framework for treating government data as evidence, ensuring completeness, provenance, and clear semantic boundaries for AI agents, moving beyond simple scraping to reliable evidence delivery.

Рабочий процесс

• Discover publisher page limits and request every page in a stable order.
• Track page count, observed row count, and source-reported totals.
• Reject monitoring baselines if the query is capped, partial, or structurally inconsistent.
• Bind the completed scope into a receipt with source metadata.
• Use an explicit decision vocabulary (EVIDENCE_FOUND, NO_PUBLISHED_MATCH, etc.) instead of binary yes/no.
• Normalize data while retaining lineage (publisher, endpoint, query, timestamp, original field names).
• Monitor independent dimensions: availability, schema compatibility, record-count behavior, and freshness.
• Implement idempotent webhook handlers using actor_run_id + event_type as keys.
• Define task-to-tool selection contracts for AI agents specifying boundaries and minimum inputs.

Доказательства

A response can be valid JSON, have a 200 status, and still represent only the first page.

Источник

We use an explicit, fail-closed decision vocabulary: EVIDENCE_FOUND, NO_PUBLISHED_MATCH, REVIEW_REQUIRED, SOURCE_UNAVAILABLE, SCOPE_INCOMPLETE.

Источник

idempotency_key = actor_run_id + ":" + event_type

Источник