Deploy notes contain code changes that are intended to fix bugs, improve performance, and prepare for new features. These deploys take place monthly.
Unless otherwise stated, all features in this release are available in the Production environment as of 2026-February.
Updated Features
Ask Your Data
Large Language Model (LLM)
Location to Enable Feature | NA |
Name of LTI Tool | Ask Your Data |
Permissions | Intelligent Insights |
Affects User Interface | No |
Affected Areas | Large Language Model (LLM) |
Related Ideas | None |
Summary
The following updates and improvements are made to the Large Language Model (LLM):
- The Ask Your Data search bar in filter categories allows users to begin typing with a single click, resolving an issue that previously required two clicks.
- Refinement questions are improved and consistently return results, eliminating instances of empty results.
- For graded classic quizzes, the model context is updated to use submissions as the primary source of truth.
- Improved named-entity-recognition for assignment_groups.
- Improved the following sub-account scoping for Role-Based Access Control (RBAC):
- Grading_periods and grading_period_groups correctly filter by account_id, ensuring tables populate with accurate data as expected.
- Sub-account filtering accurately includes all polymorphic joins across several tables, including conversation_messages, discussion_entries, communication_channels, learning_outcomes, quiz_questions, content_tags, context_external_tools, and more.
