Changelog
Follow up on the latest improvements and updates.
RSS
New
- Use an AI-powered combination of multiple search and web crawling tools inside of the chat interface. The AI will choose what providers to use and can select multiple tools for the task. Currently the AI has access to Brave Search, Perplexity, and Firecrawl. Note: Some operations involving multiple tools and reading multiple web pages make take time to respond.



- Create and run multi-step workflows (beta). Chain multiple prompts together. Use the output of one prompt into another step.
- Select different LLMs for each node of the workflow.
- New "Workflows" section in workshop.
- See output from each step of the workflow result.


- Create custom email templates for sending password resets.

Improved
- Better chat input and clickable links.

- Drag and drop file upload in app builder.

- Private Apps populate in "My Apps"
New
- GPT-4.1, GPT-4.1 Mini, and GPT-4.1 Nano added to the model selector. These models offer a large context window and a credit usage similar to 4o. They are excellent for coding or tasks requiring a lot of input.
New
- Grok 3 model family added to the model selector. These models are currently marked beta by xAI. The release includes Grok 3, Grok 3 mini, Grok 3 fast, and Grok 3 mini fast.
- Amazon Nova model family added to the model selector. The release includes Amazon Nova Micro, Amazon Nova Pro (vision), and Amazon Nova Lite (vision)

Fixed
- Fixed a bug sometimes preventing Client Admins from deleting apps.
improved
fixed
Dual Audio Recording and Bug Fix
Improved
- Dual audio recording for AI Phone Agents
Fixed
- Fixed bug causing constants to not properly load when invoked via the API
New
- Integration with Zapier available to all users here.

- File upload integration for chat with OneDrive and SharePoint. Note:we will be adding additional features related to Microsoft Graph over the coming weeks. This feature may require approval from an Office365 administrator.

Improved
- Password resets now use OTP codes instead of links to prevent issues related to email filtering link spoiling. Users with MFA active will still require an additional MFA TOTP input.

- Improved user invitation acceptance page with better error handling.

Fixed
- Fixed bug causing chat and app requests to sometimes fail when the browser window is left open for an extended period of time.
New
- Grok 2 and Grok 2 Vision added to the LLM selector. We are anticipating a Grok 3 API release soon and will add it as soon as possible.

- Deepseek R1 added to the model selector. This is a reasoning model so response times will be in line with LLMs like o1. The model is hosted in AWS and differs from the deekseek[dot]com

- Upgrade packages inside the Hatz Platform and display multiple packages.


- Usage notifications showing credit overages.

- AI Help Center. Talk to our new assistant "Lark Meeper" about Hatz and how to use the platform.

Improved
- Improved Retrieval Augmented Generation. Our chunk ranking and retrieval strategy was improved to rank find more text blocks, set better similarity thresholds, and was optimized for faster responses. You should now see much better results when working with documents larger than the context window of the chosen model.
Fixed
- Notifications and logic to prevent inviting more users than licenses available.

New
- GPT 4.5 Preview (Open AI) added to the model selector
New
- Added Claude 3.7 Sonnet, Gemini 2.0 Flash, and Gemini 2.0 Flash Lite Preview 02-05 to the multi-LLM selector.
Fixed
- Improved some quirks when viewing in Dark Mode, including the website loader and custom color schemes.
New
- Dark mode for Admin Dashboard and Customer View by system default or toggle setting. Note: Dark Mode currently defaults to violet theme. Other standard themes will be available shortly.

- Paste files directly to chat.

Improved
- Upgrade packages from within the tenant view.
- Better tracking and metrics in the tenant adoption tab.
New
- OpenAI's o1 reasoning LLM now available in chat and workshop. Note: this model can take a long time to think.
- Open AI's o3-mini reasoning LLM now available in chat and workshop.

Improved
- Drag and drop multiple files to chat.

Fixed
- Better file handling for PDFs with corrupt metadata.
Load More
→