The async localization API ships jobs in parallel across every target locale, retries on failure, and webhooks back when done. Until this week, that all happened off-screen – if a job stalled or failed, you found out from logs and webhook payloads. The Localization Jobs UI lands end-to-end: inspect job groups, watch per-language progress, see the source payload, see the webhook delivery, drill into any failed locale.
Also shipped#
- AI Reviews pass / fail / N-A discrimination. System prompt rewritten so reviewers stop returning ambiguous verdicts on edge cases.
- Built-in instruction reviewer handles a wider range of instruction types. Better behavior on instructions that didn't apply to a given piece of content.