25.10 Release Notes
🧭 Better Navigation
A new persistent sidebar makes it faster to jump between Chat, Studio, and Admin. Your last view is remembered—pick up right where you left off.
✨ Custom Components in the Library
Build once. Reuse everywhere. Design custom layout components (like branded headers) and save them to the Component Library for easy reuse.
🔗 Power BI: Direct Dataset Creation
Connect Power BI → instantly build datasets → start analyzing. No messy exports. Secure credentials. Fast setup.
⚡ Auto K-Shot Generation for AI SQL Generation
Click Auto-Generate K-Shots to create smart question–SQL pairs in seconds. Review, tweak, and boost accuracy.
🧹 Clear Skill Run Cache
Need fresh results? Clear cache from Agent Settings or via SDK. Perfect for refreshes, testing, or deployments.
🔐 Skill-Level Access Control
Lock down sensitive skills. Grant access to specific users or groups. One agent, tailored experiences.
🚀 Research: Faster & Sharper
The Research feature now runs faster and produces cleaner, more accurate results.
🧰 SDK Power-Ups
- Run research tasks programmatically
- View user groups
- Retrieve embeddings
- Clear cache
- Dataset CRUD
- Async skill execution
- MaxSQLGen expressions
🧠 Prompt Library Boost
- Full tracing of executions
- Evaluation sets for structured testing
- JSON-based evaluation prompts
- Add cases from traces or chat
- Model per prompt for fine control
Refine faster. Measure quality. Scale confidently.
Additional Note for Self-Hosted Customers
This release does not introduce additional upgrade requirements beyond standard processes. As always, we recommend running backups before upgrades as a best practice.
To download Max from our container registry use the following tag: v25.10.3.1
Tested Models
AnswerRocket SDK version: 0.2.91
OpenAI:
- Chat: gpt-4.1-2025-04-14
- Narrative: gpt-4.1-2025-04-14
- Evaluations: gpt-4.1-2025-04-14
- SQL: o4-mini-2025-04-16
- Researcher: gpt-5-mini-2025-08-07
- Embedding: text-embedding-3-small
Gemini:
- Chat: gemini-2.5-pro
- Narrative: gemini-2.5-pro
- Evaluations: gemini-2.5-pro
- Embedding: models/embedding-001
Anthropic:
- Chat: claude-3-5-sonnet-20241022
- Narrative: claude-3-5-sonnet-20241022
- Evaluations: claude-3-5-sonnet-20241022
- Embedding: Not Applicable