WitnessAI Documentation
List
Start Here
Start Here
Analytics
Analytics
Conversations
Conversations
Users
Users
Alerts
Alerts
Policy
Policy
Administration
Administration
Apps & Resources
Apps & Resources
Release Notes
Release Notes
Administrator Guide
Administrator Guide
WitnessAI Release: April 16, 2026
Release Date: April 16, 2026
Note: New and updated features may not be immediately available on your dedicated deployment due to participation in limited availability releases, beta programs, or regional configurations.
If you don't see a feature you expect, please reach out to your Customer Success team. We're happy to help.
Â
New Features
No New Features identified in this release.
Â
Feature Updates
Conversations & Alert Consoles: Displaying vendor logos in the Applications column, for at-a-glance understanding which AI application is associated with each conversation.
Â
Fixed Issues
Data Protection
- Fixed an issue where Data Protection guardrail actions (Warn/Block) could apply incorrectly to non-Data Protection prompts after a policy change.
Guardrails & Policy Enforcement
- Fixed an issue where some Behavioral Activity guardrail filters could not be processed, resulting in warning errors in policy responses.
- Fixed an issue where the Behavioral Activity guardrail was not routing some prompts according to the configured policy.
- Fixed an issue where some prompts outside of defined allowed behaviors were not being blocked by the Behavioral Activity guardrail as configured in a policy.
- Fixed an issue where the Model Protection guardrail was not blocking some risky prompts as configured in a policy.
- Fixed an issue where policy-defined warning and block messages were not being shown in Model Protection guardrail responses.
- Fixed an issue where "prompt injection detected" was incorrectly replaced with "malicious content detected" in Model Protection guardrail responses.
- Fixed an issue where the prompt-protect guardrail endpoint returned data retrieval errors in some circumstances.
Display & Console
- Fixed an issue where the conversation details header would stay in a loading state when a conversation was opened via a redirect from the Alerts view.
- Fixed an issue where Performance Overview metrics (input/output evaluation) were missing from the dashboard for some tenants.
Â
Known Issues
No Known Issues identified in this release.
Â
Breaking Changes
No Breaking Changes identified in this release.
Â
Made with Bullet