Changelog

Follow up on the latest improvements and updates.

RSS

New
Hatz Mobile for iPhone and Android
Hatz is now available on iPhone and Android. Your team can pick up or start new chats and talk to Hatz hands-free with voice mode, wherever the work happens.
  • Same chats everywhere:
    chats sync with the web. Press and hold a chat to pin it.
  • Voice mode:
    tap the voice button to talk to Hatz on site, on a call or on the road.
  • Nothing to set up again:
    integrations and admin controls are set on the web and carry over to the app.
Download
Hatz
from the App Store or Google Play and sign in. Available in the US only.
hatz-mobile
Hatz Official Skills
Every Hatz account now comes with four ready-made skills built by Hatz. A skill is a saved set of instructions for one task, so you don't have to explain it every time. Type
/
in a new chat and they're at the top of the list, marked
Hatz Official
. There's nothing to build or upload first.
  • /day-ahead-briefing:
    preps tomorrow's meetings from your Outlook or Google calendar and email: who you're meeting, what they've asked for recently and what to ask them.
  • /executive-assistant:
    your week at a glance, with recent email sorted into what needs a reply.
  • /file-analysis:
    answers questions across contracts, invoices, reports and spreadsheets, with every figure traced back to its file.
  • /whats-next-in-hatz:
    suggests the best next step to get more out of Hatz, based on how you already use it.
The calendar and email skills work once Outlook or Google is connected.
hatz-official-skills
Outlook Emails in Your Own Writing Style
Hatz now writes Outlook emails and meeting invites the way you do. Go to
Settings → AI preferences → Email and calendar
and click
Scan my sent emails
to have Hatz pull your signature and calendar or meeting links from your recent sent mail, or click
Set it up myself
to add your signature, tone, greeting and sign-off. Every Outlook draft Hatz writes uses them from then on.
  • See it on every email:
    approval and sent cards say
    Written in your style
    . Click
    Edit
    to change it.
  • You approve every send:
    each email or invite appears as a card with the recipients, subject and message. Click
    Approve
    to send it or
    Deny
    to stop it.
  • Turn it off anytime:
    switch off
    Use my writing style in drafts
    .
outlook-personalization
Send Webhook Steps in Automations
Automations can now send their results to the tools your team already uses, like Zapier, Microsoft Teams or your own system. Add a
Send webhook
step, paste the link from your app, send a test, and confirm where it goes once in chat.
  • Ask in chat:
    paste a link into a request like "every Monday, send my team this week's priorities to this link," and Hatz builds the automation and checks with you before it saves.
  • Every send leaves a receipt:
    open the step in any run to see whether it was delivered, the status and when it was sent.
  • Only where you approved:
    Hatz shows just the service and host, such as Zapier at hooks.zapier.com, never the full link.
  • Admins stay in control:
    admins can turn Send webhook off for their organization.
send-webhook-changelog
Improved
Share Spaces with Your Whole Organization or a Group
Space managers can now share a Space with the whole organization, a group or specific people at once, each with its own role. Click
Share
in any Space and start typing a name.
  • See who has access:
    the Space header shows who can open it, such as "Everyone at" your organization. Click it to see each person, group and role.
  • One role per person:
    if someone is included more than once, they get their highest role.
  • Undo:
    the "Saved sharing" message offers Undo for a few seconds after you save.
share-spaces-org-sharing
Audit Log: Workshop and User Events
The audit log now shows who created, edited, deleted or restored an agent, app, workflow, skill or automation, plus user deletions, role changes and community publishing. Find it under
Settings → Compliance & Logs
.
MSP Admins
Notification Center
One place for everything that needs your attention across your clients. Click
Notifications
at the bottom of the sidebar, or hover over it for a quick preview.
  • Client requests:
    when a client asks for more usage or a phone agent, it shows up here with a link to review it.
  • Usage limits:
    see when a client reaches its package or extra usage limit, with urgent items flagged.
  • Free trials:
    see when trials are ready to give out, with the redeem-by date and a link to create the tenant.
  • Filter fast:
    show unread only or filter by category, and mark everything read in one click.
notification-center
Bulk Role Changes, Last Active and Limit Status on the Users Table
Manage who can do what, in bulk. MSP admins and tenant admins can change many people's roles at once and see who's active and who's close to their credit limit, all from the Users table.
  • Bulk role change:
    select people on any page, or everyone matching your filters, then pick a role. The dialog shows who will change and who's skipped before you confirm.
  • Last active:
    a new column with filters for people inactive 30, 60 or 90+ days, or who have never used a credit.
  • Limit status:
    credit usage and limit status in one place, with a filter for anyone over 85% or blocked.
  • Your own team too:
    MSP admins can change roles for their own staff from the dashboard.
users-bulk-role-change
users-last-active
Fixed
  • Auto now uses each person's saved profile and preferred time zone when personalization is on.
New
Subscription Overview
MSP admins can now see exactly what they're billed for. Subscription Overview itemizes every charge by client, month by month, so invoices are easier to check and easier to explain to clients. Find it under
Billing → Subscription Overview
.
  • Every charge, by client:
    each tenant's base package, add-ons and usage, with upgrades, trial conversions and new trials marked as they happen.
  • See next month's invoice:
    see your next bill as it stands today.
  • Transparency without clutter:
    credit notes and unassigned licenses get their own lines, and a
    Hide trials
    toggle keeps free trials out of the way.
  • Export:
    download a CSV for every tenant or just one, or a PDF summary for a single tenant.
hatzrel-subscription-overview
LLMs
Claude Fable 5.2
Auto now sends its most demanding work to Claude Fable 5.2, Anthropic's newest model for complex reasoning and long, multi-step tasks. Stay on Auto and Hatz uses it when a task calls for it, with nothing to change.
  • Credits:
    12x per message, the same as Claude Fable 5.1.
  • How it compares:
    a big step up from Fable 5.1, and ahead of Claude Opus 5.5 and GPT-6 Astra on agentic coding, computer use and knowledge work.
  • Good for:
    in-depth analysis, long reports and complex work that spans several apps.
hatzrel-fable-5-2-benchmarks
Gemini 4 Carbon
Gemini 4 Carbon was added to the model selector for chats, agents and workflows. It's Google's most capable model, built for complex reasoning, long documents and security work.
  • Credits:
    2.5x per message during the current promotion, the same as Gemini 4 Argon.
  • How it compares:
    ahead of Gemini 4 Argon, GPT-6 Astra and Claude Opus 5.5 on most benchmarks, including business workflows, long-context reading and cybersecurity.
  • Good for:
    reviewing long documents and large files, security reviews, and multi-step business tasks.
hatzrel-gemini-4-carbon-benchmarks
MSP Admins
Activate: Link Tenants Sooner and See PSA Company Details
  • Link a tenant at any stage:
    create or link a tenant from a prospect's
    Use Cases
    tab, whatever stage the prospect is in.
hatzrel-activate-link-tenant
  • Company details from your PSA:
    a PSA sync now fills in company dates, employee counts and market labels under
    Company Information
    . ConnectWise provides all three, and Autotask provides dates and labels.
hatzrel-activate-company-info
We've made major improvements to the engine behind Hatz chat, so it can take on more of your work and finish it. Hatz now plans each task, splits work across helpers acting at the same time, works in the apps and websites the task needs, and saves what works as an automation you can run again. Welcome to Hatz 2.0.
New
One Auto Mode
Lite, Performance and Turbo are now one Auto mode. Auto picks the right model for each step of a task and runs parts of the work at the same time with helpers, so results come back faster and stronger. We conducted extensive testing on our internal benchmark using real MSP and SMB use cases, and found that Auto mode outperformed legacy modes in 3 areas:
  • 24% better outputs than Turbo - Quality
  • 15% more cost effective than Performance - Cost
  • 12% faster than Lite - Speed
In head-to-head testing, Auto consumed 68% fewer credits than Sonnet 5.5 for the same tasks, and provided results 76% faster than Terra 6.1.
Auto lays out the steps before it starts and shows each one as it runs. Click
Edit steps
to add, reorder or remove steps.
  • The right questions up front:
    when a task needs a decision, Auto asks a few quick questions first and marks a recommended answer for each.
  • Connect as you go:
    if a task needs an app that isn't connected yet, Hatz offers to connect it right in the chat, then carries on.
hatzrel-harness-plan
hatzrel-harness-questions
Automations
Automations are repeatable tasks you build just by describing them in chat. When a chat does something you'll need again, like a weekly client report or a ticket triage, save it as an automation. Run it on a schedule, or click
Run
with new inputs whenever you need it.
Unlike workflows, you don't build automations step by step in an editor. Hatz builds the automation from the work it just did in Chat, and you can edit by chatting. Open any automation to see its steps and what each one does.
  • Find them in one place:
    every automation you can use is listed under
    Automations
    , with what's running, what's upcoming and anything that needs you.
  • Bring your workflows over:
    ask Auto in chat to convert a workflow. It shows a preview of each one, and only the ones you tick are converted.
hatzrel-harness-automations
Browser Control
Hatz can now open websites in a secure browser and work in them for you. That includes vendor portals, billing sites and any tool without an integration, so a task no longer stops where the integrations end. You can watch the browser live, right next to the chat. If a site needs a person, like a sign-in check, Hatz pauses and lets you
Take control
, then picks up where you left off.
hatzrel-harness-browser
Vault
Vault is a secure place to save the API keys your work depends on, so you never paste a key into a chat. Add a key once under
Settings → Vault
, with a name and the sites it's for. When a task needs it, Hatz uses it in your chats and agents. Hatz attaches the key itself, so the AI never sees it. Only you can use your keys, and you can edit or stop using any key from the same page.
Parallel Chats
Run as many chats as you want at once. Each chat can keep working for up to three hours, even after you leave it, and you can watch every chat's live status as it works. When a chat needs you, it's marked
Needs you
in the sidebar, so you know exactly where to jump in.
  • Steer as it goes:
    add instructions while Hatz works, like "Keep it brief," or use
    /btw
    to ask a side question without changing the task.
  • Approvals your way:
    Smart
    runs low-risk actions on its own and asks before anything risky.
    Manual
    asks before more actions.
    Stop
    ends a run at any point and keeps what's finished.
hatzrel-harness-needs-you
MSP Admins
Simpler Default Model Settings
Default model settings now offer Auto plus specific models, and the older Auto tiers are retired. Existing role limits still apply.
Rate limiting now defaults to Auto instead of the legacy Auto Lite.
New
Hatz Spaces
Spaces are shared workspaces for ongoing projects. A space holds instructions, files, memory and connected tools, so every chat started in it already has that context and teams can collaborate securely within Hatz.
  • To set one up:
    click
    New space
    in the left sidebar, or choose
    Turn into a space
    from any chat's menu. Add instructions and files, then invite teammates.
  • Shared context:
    instructions, files and memory stay in the space, and every new chat in it starts with them.
  • Team roles:
    invite people as owners, managers, contributors or viewers, or share the space with the whole organization.
  • Private chats, shared when ready:
    chats in a space stay private until someone shares them. Pin the chats everyone should see.
  • Space files:
    share a file with the space and every chat in it can use it.
  • Edit from chat:
    ask Hatz to update the space in plain words. It shows a preview before anything changes.
  • Tenant admins choose who can create and share spaces.
hatzrel-spaces-all-spaces
hatzrel-spaces-tour
AI Gateway
AI Gateway connects Hatz to the AI coding tools teams already use, like Claude Code, Codex CLI and OpenCode. Requests from those tools run through Hatz, so the same controls apply as in the Hatz app, and all AI usage is tracked in one place.
  • Turn it on:
    MSP admins go to
    Settings → AI Gateway
    .
  • Connect a client:
    each client opts in once from
    Settings → Connect a client
    .
  • Connect a tool:
    copy the ready-made setup for Claude Code, Codex CLI, OpenCode, Pi or Hermes on Mac, Windows or Linux, then click
    Test connection
    .
hatzrel-gateway-connect-a-client
MSP Admins
Per-User Usage Reporting
Per-user usage reporting shows how each person uses Hatz. MSP admins can view it for one client or across all clients, for any time period.
  • Find it:
    in the admin view, open
    Dashboard
    and click
    See all users
    on the Power Users card. For one client, open
    Tenants
    , pick the client, and click
    See all users
    on its overview.
  • The people list:
    each person's credits, busiest day, top model, what they mostly use Hatz for and when they were last active. Search, sort and pick any time period.
  • Each person's page:
    click a name to see their credits per day, models, top agents, apps and workflows, and what they use Hatz for. Select a day to see that day's sessions.
  • Export:
    click
    Export
    to download the list as a CSV.
hatzrel-usage-people-list-demo-2x
Draw.io File Support
Any member can now work with draw.io diagrams in chat. Hatz reads, edits and creates diagrams, and returns a .drawio file that opens in draw.io.
  • Edit a diagram:
    attach it and describe the change, like "Add our new branch office and connect it to the main firewall over a site-to-site VPN." The rest of the layout stays where it is.
  • Create a diagram:
    describe a network, a process or an org chart and get a new .drawio file.
  • Supported files:
    .drawio, .dio and draw.io PNG.
hatzrel-drawio-chat
hatzrel-drawio-diagram
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.
Skills in Workshop
Create a skill in chat
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").
Screenshot 2026-10-30 at 12
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
    .
Screenshot 2026-10-30 at 12
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.
GPT-6.1 Terra benchmark
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.
Reflection Beam benchmarks
Rather not choose? Stay on Auto and Hatz picks the right model for each task.
New
Decide Steps in Workflows
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.
  • Add one from
    Add new Step → Decide
    and try it on a sample first.
  • Already have a workflow? Ask Hatz to optimize it with Decide steps, and Hatz applies the changes for you.
Decide step in a workflow
Response Feedback in Chats
Rate any Hatz answer
Bad
,
OK
, or
Great
. Your ratings show us where Auto picks the best model, so we can keep improving it.
  • Bad
    asks what went wrong and offers a retry with that feedback in mind.
  • Now and then, Hatz asks for a quick 1–5 rating, at most once every six hours.
Response feedback
IT Glue Integration
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.
  • Find it in
    Workshop → Connections → IT Glue
    .
  • In beta:
    it shows up once an admin turns on
    Enable Beta Features
    in
    Settings → Organization Settings
    .
IT Glue
Password-Protected Artifact Links
Share an artifact with a client behind a generated password, no Hatz account needed. New links are password-protected by default,
Copy share message
puts the link and password in one message, and publishing a new version keeps the link working.
Password-protected link
Improved
Shadow AI Scan Reports
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.
Shadow AI scan report
Settings in the Tenant Sidebar
The tenant sidebar's
Workspace
section is now
Settings
, matching the MSP admin side. Account, API keys, AI preferences, integrations, and administration all live there, and bookmarked links still work.
Settings in the sidebar
Duplicate an Artifact
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.
  • Click
    Duplicate
    at the top of the artifact. Hatz copies the version you're viewing and opens your copy in a chat.
Duplicate an artifact
Fixed
Choose a Model from the Multipliers Table
: Scroll through the multipliers tab and choose your model directly from that view.
Multipliers table
New Left-Hand Navigation
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.
left-hand-navigation
LLMs
Claude Haiku 5.5
Claude Haiku 5.5 was added to the model selector for chats, apps, agents, and workflows.
  • Credits:
    the same multiplier per message as Claude Haiku 4.5.
  • Good for:
    classification, pulling details out of documents, chat, and tool use, with up to 1M tokens of context.
Gemini 4 Argon
Gemini 4 Argon was added to the model selector for chats, apps, agents, and workflows.
  • How it compares:
    Google's benchmarks put it ahead of Claude Opus 5.5 and GPT-6 Astra on DeepSWE, a real-world software engineering benchmark.
  • Good for:
    reasoning, coding, and long documents, with up to 1M tokens of context.
vendor-gemini-4-argon-benchmark-table
Model Catalog Maintenance
Older models have been retired so Hatz can focus on the most capable, most credit-efficient models.
  • Nothing to update:
    any agent, workflow, or default that used a retired model now runs on its successor automatically.
  • Same credits:
    each successor is priced the same as the model it replaces, so nobody pays more.
  • Stay on Auto:
    Auto always routes to the current best model for the task.
Improved
Compact Tool Calls in Chat
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.
compact-tool-calls
Fixed
  • Memory search:
    Hatz finds saved memories by meaning, even when a question uses different words.
New
Hatz Voice Mode
Any member can talk with Hatz in chat and hear it answer out loud. Click the wave icon in the chat box to start.
  • Real work, by voice:
    ask for an artifact, a document, research, or something in a connected app, and Hatz does it as a normal chat turn while the conversation keeps going.
  • Natural back-and-forth:
    talk any time to interrupt. Hatz listens, thinks, and replies out loud, with live captions under the orb.
  • Voice commands:
    say "cancel that" to stop a running request, or "end voice" to finish.
  • Every exchange is saved to the chat.
    Press
    Esc
    or
    End voice
    to go back to typing.
image
image
Download Menu for Artifacts
Any member viewing an artifact gets one
Download
menu, with the original file at the top and its export formats below.
  • Named files:
    downloads are named after the artifact's title, on public pages too.
  • PDF:
    HTML apps download as PDF, and PowerPoint files can now download as PDF as well.
  • Deck navigation:
    slide decks show a small Prev / Next control that tucks away while idle.
image
Improved
Research With Real Sources
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.
Role Settings in One Place
MSP admins manage a custom role from one
Role Settings
dialog under
Customize Roles
, including moving several people onto a role at once.
Screenshot 2026-10-08 at 5
User Rate Limiting
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.
New
Refreshed Chat
Any member gets a redesigned chat, with new navigation, a new composer and appearance controls.
  • Resizable sidebar:
    drag the sidebar to the width you want, or collapse it.
chat-refreshed
  • Search every conversation:
    press
    Cmd+K
    or
    Ctrl+K
    to search chats, including older ones and chats inside folders.
chat-search
  • Appearance:
    choose
    System
    ,
    Light
    , or
    Dark
    from the account menu.
chat-appearance
Microsoft 365: Agents Can Take Action
Agents connected to Microsoft 365 can now act in Outlook, OneDrive, and SharePoint, not just read from them.
  • Send email:
    chat asks a person to approve each email before it goes out. Emails keep their formatting (bold, lists, links) in Outlook.
  • Calendar:
    cancel meetings, and accept, tentatively accept, or decline invites.
  • Files:
    upload to OneDrive and SharePoint, and share files with people inside the organization.
  • Sharing outside the organization:
    a person approves each external share or "Anyone" link.
  • SharePoint lists:
    add and update list items.
  • Deletes are confirmed in chat
    before anything is removed.
  • The organization's own Microsoft 365 sharing policies still apply. When Microsoft blocks a share, chat shows Microsoft's reason.
LLMs
Claude Sonnet 5.5
Claude Sonnet 5.5 was added to the model selector for chats, apps, agents, and workflows.
  • Where Auto uses it:
    Performance mode, the default, sends its hardest tasks to Sonnet 5.5, and Turbo uses it for complex work, with the most demanding requests going to Claude Opus 5.5. Lighter coding tasks now go to GPT-6 Luna.
  • Credits:
    1.25x per message, the same as Claude Sonnet 5.
  • How it compares:
    Anthropic's benchmarks put it well ahead of Sonnet 5 on agentic coding and knowledge work, and close to Claude Opus 5.5 (2x).
  • Good for:
    everyday work that needs a strong model: fixing bugs, and polished documents, slides, and spreadsheets.
hatzrel-auto-modes
hatzrel-vendor-sonnet-5-5-benchmarks
DeepSeek V4.1 Flash
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.
  • Credits:
    0.33x per message, the lowest multiplier in Hatz, alongside GLM 5.3 Flash.
  • How it compares:
    DeepSeek's benchmarks put it ahead of Kimi K3 and GLM-5.3, and level with or ahead of Claude Opus 5 and GPT-5.6 Sol on three of four agentic benchmarks.
  • Good for:
    high-volume work where credits matter: summarizing long files, reading screenshots and images, and routine steps in agents and workflows.
  • With Auto:
    Auto doesn't route to it today and already sends lighter work to low-multiplier models like GPT-6 Luna and GLM 5.3 Flash. Choose DeepSeek V4.1 Flash from
    All Models
    when you want it specifically.
vendor-deepseek-v4-1-benchmark
Retired models:
  • Kimi K2.6, Kimi K2.7-Code, Inkling, and DeepSeek V4 Pro have been retired by their provider. Any agent, workflow, or default that used one now uses a replacement automatically, and DeepSeek V4 Pro moves to DeepSeek V4.1 Flash.
Presenter Tools for Artifacts
When you present an artifact full screen, a small toolbar now offers
Cursor
,
Laser
, and
Pen
, so you can point at and draw on what you're showing.
  • Slide decks:
    each slide keeps its own drawing. Move to the next slide and it starts clean; go back and your marks are still there.
  • Clear and undo
    work on the current slide only.
  • Drawings are temporary:
    they're never saved into the artifact or its downloads, and they clear when you leave full screen.
presenter-tools
Improved
Timestamps and Thinking in Chat
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.
Screenshot 2026-10-01 at 8
chat-thinking-recording
MSP Admins
Activate: Add Your Own Use Cases
In
Activate
, a customer's
Use Cases
tab now has an
Add use cases
button. Pick
Workshop items
you've shared with your tenants, write your own, or have AI suggest one.
  • Enrich this item:
    Hatz researches the use case in about a minute, then fills in its hours, value, and talking points from what it finds.
  • Into the pitch:
    enriched use cases appear in the pitch you generate. You can leave one out of the proposal, though including it is recommended.
  • Who Has Access:
    MSP admins using Activate.
activate-use-cases
Custom MCP Servers With Public OAuth Apps
  • Members adding a custom MCP server can connect one whose OAuth app doesn't use a client secret. In
    Add Custom MCP Server
    , choose
    OAuth
    , then
    I have credentials
    , then
    Public client (no secret)
    .
custom-mcp-public-oauth
New
GPT-6 Sol and GPT-6 Luna
"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.
  • GPT-6 Sol
    is built for complex reasoning, coding, and agentic work.
  • GPT-6 Luna
    is the fastest GPT-6 model, made for high-volume everyday work like summarizing, drafting, and routine automation.
  • Both have a 1.05M-token context window and up to 128K tokens of output.
models-a-picker
Grok 4.6 and Grok 4.7
"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.
  • Grok 4.7
    is xAI's most capable Grok model for complex reasoning, coding, and agentic work.
  • Grok 4.6
    is built for coding, agentic tasks, and knowledge work.
  • Both read images and offer configurable reasoning. A custom role that blocks xAI models blocks both.
models-c-grok-gdpval
Claude Opus 5.5
"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.
models-d-opus-benchmarks
MSP Admins
Activate: Ready-Made Use Cases for Every Prospect
A prospect's
Use Cases
tab in Activate opens on five Hatz Official use cases, each modeled for that company's size.
  • Each card shows the hours and dollars a year it gives back, and the totals update when the headcount under
    Modeled for
    changes.
  • Open a card for talking points (Hook, Proof, Provide, Objection), tips to get started, and
    How we got this
    , the math and sources behind the estimate.
  • Generate pitch
    creates a branded PDF with the same numbers to help guide conversations with the prospect.
  • Creating a tenant from a pitched prospect copies the included use cases into the new tenant, and its AI Quickstart Checklist lists their tips as first steps.
activate-a-usecases-tab
activate-c-usecase-flow
Load More
→