State machine
Collecting, normalizing, clustering, ranking, summarizing, verifying, reviewing, and publishing are explicit states.
Agentic feed summaries
Coordinate source monitoring, clustering, summary generation, and verification without giving one model unrestricted access or publication authority.
Agent architecture
The agent coordinates specialized tools instead of combining browsing, judgment, and publishing in one opaque loop.
Collecting, normalizing, clustering, ranking, summarizing, verifying, reviewing, and publishing are explicit states.
Fetchers cannot publish; summarizers cannot browse; publishers accept only approved briefing objects.
Topic and destination policies determine when review is mandatory and what can auto-publish.
Source control
The agent should not improvise access to arbitrary websites.
Approved feed or API URL, host allowlist, parser profile, language, topic scope, cadence, credentials reference, access policy, owner, and health status.
Every run records the source configuration version.
Scheduled checks and push events enqueue source-specific work with deduplication keys. The collector still validates and retrieves the source under policy.
Repeated events are idempotent and bounded by retry rules.
Editorial control
A validated summary is not automatically an approved communication.
Use validated item and cluster records with explicit evidence IDs.
Check schema, facts, dates, quantities, entities, coverage, and source references.
Route high-risk topics and low-evidence results to mandatory review.
Capture reviewer decisions as structured feedback and preserve the draft history.
Render the approved object, use an idempotency key, and record the delivery hash.
Feed Signals
Events, source registries, tools, clustering, verification, memory, security, review, and recovery.
An architecture for agentic AI news summaries that uses clear tool boundaries, event-driven updates, provenance, and human review gates.