New
Skills
Teach Hatz how you like a task done once, and it follows the same steps every time. A skill is a saved set of instructions, plus any files it needs, for work you repeat, like a client update, a ticket recap or an onboarding checklist.
- Make one in chat:tell Hatz what you want, for example "Make a skill that turns my Patch Tuesday notes into a client-ready summary." Hatz drafts it, and you review it before saving.
- Use it in chat:just ask for the task, and Hatz uses the right skill. You can also pick one by typing/in the chat box.
- Bring your own:already built skills in another AI tool? Import them, even a whole folder, and choose what to include.
- Manage them in Workshop → Skills:create, search and edit your skills there, or start one from the model selector.
- Every new skill gets a structure and security check before it's ready to use.
Google Calendar Integration
Connect Google Calendar so Hatz can read your schedule and create or update events. Before Hatz emails anyone an invite or an update, it shows you a preview in chat and waits for your OK.
- Find it in Settings → Integrations(search "Google").
Slack Integration
Connect Slack in a click, with no custom MCP setup needed. Once it's connected, Hatz can work with your Slack channels and messages from chat.
- Find it in Settings → Integrations → Slack.
LLMs
GPT-6.1 Terra
GPT-6.1 Terra was added to the model selector for chats, agents and workflows. It's a fast everyday model that reads images as well as text.
- Credits:1.25x per message, the same as Claude Sonnet 5.5.
- How it compares:close to GPT-6.1 Sol and GPT-6 Astra at reading images, with far fewer factual mistakes than GPT-5.6 Terra.
- Good for:client emails and proposals, reading screenshots and scanned forms, and pulling details out of invoices.
Reflection Beam
Reflection Beam was added to the model selector for chats, agents and workflows. It's a fast, efficient model for text, with up to 1M tokens of context.
- Credits:0.33x per message, the lowest multiplier in Hatz.
- How it compares:ahead of larger open models at working across connected apps and tools.
- Good for:high-volume work where credits matter, like summarizing long documents and multi-step tasks across your apps.
Rather not choose? Stay on Auto and Hatz picks the right model for each task.