Skip to main content

Documentation Index

Fetch the complete documentation index at: https://www.opentrain.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

The changelog covers product changes to OpenTrain AI. For documentation updates, see the GitHub repository.
​
May 28, 2026
weekly

​
Highlights this week

Employer-side Open Label review workflow, proposal message safety screening, agency marketplace free trials, and a new provider invite access flow.

​
New

  • Employer Open Label review — Employers can now filter proposals by Open Label test status, launch a test directly from a proposal, and rate AI trainer submissions. See Managing candidates.
  • Open Label retake required — Employers can mark an Open Label test as required to retake when an AI trainer’s submission needs another attempt. AI trainers see the retake request from their proposal. See AI Interview.
  • Proposal message abuse screening — Outbound proposal and bulk messages are automatically screened for abusive content before they reach the other party. Flagged messages are held for admin review so conversations stay safe. See Proposal Messages.
  • Agency marketplace free trial — Agencies can self-serve a 30-day free trial to access the marketplace without entering payment details up front.
  • Provider invite access — Employers can invite external annotation providers directly into a job, granting scoped access to candidates and deliverables without sharing their full workspace.
  • Open Label test reminders — AI trainers who start but don’t finish an Open Label test now receive a reminder so they don’t miss the opportunity to complete their proposal.

​
Fixes

  • AI Trainer dashboard contract crash — Resolved a crash on the AI Trainer dashboard when a contract lookup returned no result.
  • Public job detail — Fixed an incorrect Open Label badge on public job detail pages so candidates see the right test requirement before applying.
  • Support ticket review briefs — Improved support escalation handoffs and corrected due-date handling on internal review tasks, reducing delays on tickets that need human review.