New
New LLMs
- Fable 5 (Anthropic) has been re-enabled
"Claude Fable 5 introduces our 5th model generation for your most ambitious work. Tackle days-long, complex, and asynchronous tasks previous models couldn't sustain." — Anthropic
Claude Fable 5 is Anthropic's most capable generally available model, built for long-horizon coding projects, deep research, and multi-stage enterprise workflows. It can plan across stages, delegate to sub-agents, and check its own work — including using vision to evaluate outputs against the original goal. It's state-of-the-art on coding, knowledge work, and computer use.
⚠️ Note: Claude Fable 5 consumes significantly more credits than other models — approximately 12x our baseline. It also requires special 30-day data retention for safety monitoring. Learn more about Fable's data retention practices.
- GPT-5.6 Sol (OpenA)
- GPT-5.6 Terra (OpenAI)
- GPT-5.6 Luna (OpenAI)
"GPT‑5.6 Sol is our strongest model yet. To give a preview of model performance, we share a set of evaluations highlighting improved agentic capabilities in coding, biology, and cybersecurity" - OpenAI
Artifacts
- An artifact is a reusable item created by AI and distributed through Workshop, group shares, or public links.
- Ask Hatz to build a report, slide deck, tracker, or interactive web page, and it's created as an artifact you can preview and refine right in the conversation.
- Creates Code, PDF, DOCX, PPTX, and HTML
Compliance & Logs
- Admins can review a complete, searchable record of every AI interaction in their organization.
- See each invocation — the user, their tenant, the model used, and the chat, app, or agent it came from — then filter by user or date range and open any entry to inspect its content.
- Records can be exported for audits and reporting.
- MSP Admins have full control over who has access to this feature and can choose whether or not to enable it per tenant.
Search Hatz Docs From Hatz Chat
- Hatz users can now reach Hatz's own knowledge and capabilities through MCP, and without enabling tools.
- Get real time answers based on searches of our up to date documentation.
Improved
Phone agent improvements:
- Phone agents now report the correct, local time to callers
- Natural language interruptions - callers can now speak over the agent and it intelligently classifies whether that speech is a real interruption, so conversations feel more natural.