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.

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.

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.

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.

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.

Rather not choose? Stay on Auto and Hatz picks the right model for each task.

Workflows can now make simple calls on their own: which team a ticket belongs to, how urgent it is, or whether it needs a person to look at it. Add a Decide step, ask your question in plain words, and the steps after it use the answer. It's fast and uses a fraction of the credits of a full AI step.

Rate any Hatz answer , , or . Your ratings show us where Auto picks the best model, so we can keep improving it.

We added an IT Glue integration. Connect your IT Glue account so Hatz can read your client documentation. It's read-only, so nothing in IT Glue changes.

Share an artifact with a client behind a generated password, no Hatz account needed. New links are password-protected by default, puts the link and password in one message, and publishing a new version keeps the link working.

Every Shadow AI scan in Activate now produces a client-ready report: what the scan found and its overall risk rating, the AI tools that stand out and how each handles company data, the controls that keep AI safe, and a 90-day plan from detected to managed. The report lives in Activate with the scan.

The tenant sidebar's section is now , matching the MSP admin side. Account, API keys, AI preferences, integrations, and administration all live there, and bookmarked links still work.

Make your own copy of any artifact you created or that was shared with you, then edit the copy while the original stays as it is.

: Scroll through the multipliers tab and choose your model directly from that view.

Hatz moves its navigation into a sidebar on the left. Chat, Workshop, AI Phone Agent, Learn, and Workspace each open to list their pages, and the page you're on stays highlighted. Pages across Hatz also share consistent spacing and titles, with clearer empty states and tables that scroll cleanly.

Claude Haiku 5.5 was added to the model selector for chats, apps, agents, and workflows.

Gemini 4 Argon was added to the model selector for chats, apps, agents, and workflows.

Older models have been retired so Hatz can focus on the most capable, most credit-efficient models.

When Hatz uses a tool in chat, each call shows as one line that says what it did, such as "Searched the web" or "Ran Python". Any member can click a line to see the code and output. A failed call shows in red and opens on its own.

Any member can talk with Hatz in chat and hear it answer out loud. Click the wave icon in the chat box to start.

Any member viewing an artifact gets one menu, with the original file at the top and its export formats below.

When Hatz searches the web with Perplexity, it can bring back the actual pages and links, so answers cite sources people can open and check. Works in chats, agents, and phone agents with Perplexity turned on.

MSP admins manage a custom role from one dialog under , including moving several people onto a role at once.

Requests made with Hatz API keys have limits on requests, tokens, and simultaneous calls for each key and the user and organization that own it. This is to improve reliability with our services. Using Hatz in the app isn't affected.

Any member gets a redesigned chat, with new navigation, a new composer and appearance controls.

Agents connected to Microsoft 365 can now act in Outlook, OneDrive, and SharePoint, not just read from them.

Claude Sonnet 5.5 was added to the model selector for chats, apps, agents, and workflows.

DeepSeek V4.1 Flash was added to the model selector for chats, apps, agents, and workflows. It's a fast, low-cost model for members who choose their own model, built for long documents, images, and tool use.

When you present an artifact full screen, a small toolbar now offers , , and , so you can point at and draw on what you're showing.

While Hatz works on a reply, a status line now sits right under it in the conversation, showing what it's doing (thinking, using tools, responding) and how long it's been going. When it finishes, the reply shows how long Hatz thought.

In , a customer's tab now has an button. Pick you've shared with your tenants, write your own, or have AI suggest one.

"More ways to bring frontier intelligence into the work you do every day." — OpenAI

Any member can select OpenAI's two newest GPT-6 models in chat, agents, and workflows.

"Grok 4.7 is our most capable model for coding and knowledge work." — SpaceXAI

Any member can select xAI's two newest Grok models in chat, agents, and workflows.

"Opus 5.5 is a major step up from Opus 5. It's the new leading model." — Anthropic

Any member can select Claude Opus 5.5 in chat, agents, and workflows. It is Anthropic's latest Opus model for long-running agentic coding and knowledge work, with a 1M-token context window and adaptive thinking always on.

A prospect's tab in Activate opens on five Hatz Official use cases, each modeled for that company's size.

MSP admins can set a weekly credit limit on a custom role, separate from the monthly one, and choose what happens when someone reaches it.

Any member can connect their LinkedIn account and post from chat — through the , or under .

Any member can attach files up to — documents, images, audio, and archives. Full decks, recorded calls, and scanned document sets go in whole, in chat and as sources for agents and apps.

MSP and tenant admins can connect an integration through their organization's own OAuth app, and it applies across the workspace.

Everyone sees:

For MSP admins, under in the Admin dashboard:

MSP users with a prospect-management permission can deactivate a PSA-sources prospect from the customer table or their company page, after confirming the exact prospect.

MSP admins can run device-discovery scans that finish in about three seconds, with detection counts reflecting distinct devices.

Reconnecting a PSA integration — ConnectWise, Autotask, or Halo — keeps your existing connection in place until the new credentials are confirmed.

Hatz Learn has a Resources tab, with its own set of guides, walkthroughs, and videos for each audience. Everything opens in place — videos play on the page, and the reference material opens as a Hatz artifact.

For your team, under :

For MSP admins, under in the Admin dashboard:

The two sets are kept apart: your clients see their own Resources tab, and the MSP enablement material stays in the Admin dashboard.

Google's newest Flash model is in the model selector for chat, apps, agents, and workflows, with a 1-million-token context window and a 65,536-token output ceiling.

Anthropic's newest Fable model is in the model selector for chat, agents, and workflows, with a 1-million-token context window, a 128,000-token output ceiling, and adaptive thinking always on.

Z.ai's full-size GLM 5.3 joins GLM-5.3-Flash in the model selector for chat, agents, and workflows, with a 1-million-token context window and a 262,144-token output ceiling.

Primary Admins, Admins, and Sales Users.

GLM-5.3-Flash is now in the model selector for chat, apps, agents, and workflows.

"" — ZAI

Creating a phone agent starts with one screen: pick a curated template, copy one of your existing agents, or start from scratch.

Every recorded call now has a play control right in the call log, so you can listen to the whole conversation without needing a summary email.

You can now select more than one event type at once when filtering Compliance & Logs, so a single search covers everything you're looking for.

Various improvements to Activate, including:

Control exactly what gets imported instead of an all-or-nothing sync. Filter by each PSA's own live classifications, preview how many companies match, and only those sync going forward.