Feature Requests

We have multiple staff members report that the Hatz platform delivers noticeably slower response times compared to competing LLM platforms (ChatGPT, Claude.ai , Perplexity), with a key frustration being the visibility of verbose internal tool calls, reasoning chains, and processing steps that clutter the UI and delay perceived response time. This issue persists across multiple LLM models within the platform, indicating a systemic platform-level UI/rendering problem rather than a model-specific issue. We recommend optimizing response delivery to hide or defer tool calls and reasoning logic from the primary output stream by default, allowing users to see clean, actionable results immediately, with detailed reasoning available only on demand via an expandable section or user preference toggle.

Need an option to sell to orgs governed by HIPAA. This means a bundle of LLMs that are HIPAA friendly and the ability to get a BAA signed by Hatz. We've lost opportunities because this isn't available yet.

Allow custom MCP's to be shared across company with other users or by group.

Would love to have a HatzAI desktop app that connects to everything on my laptop so that I can reference things and take action in apps, shell scripts, etc.

We have clients in a variety of verticals and locations where the state has extensive consumer protection laws on consumer privacy. If a business is large enough, standard HR departments will be handling employee PII. We implement DLP solutions within MS365, firewall, Checkpoint Avanan for these clients and some clients have other point solutions in place that they manage. We need to be able to monitor for compliance breaches in Ai prompts within Hatz Ai. Feature options such as: Warn the end user for possible PII in real-time Alert a security officer or email distro while halting the user/Agent AI usage or process provide a compliance dashboard reporting mechanism full api access to the prompt and input txt I am sure others are much more verse in other safeguards and actual regulation standards that must be met. However, we are getting these types of questions to provide our clients (outside of possible Hatz deal) to provide them with Prompt security to Copilot and Claude. It's still early in the industry, every vendor is just 6 weeks they claim from going GA on some new Ai security solution. One of our clients didn't understand that with SentielOne's recent Prompt Security platform, we couldn't just turn it on in the S1 agent. Customers are seeking security solutions for AI, the more native and baked into Hatz the better.

Platforms like Claude have popularized "skills" — structured, multi-file AI instruction packages that go well beyond a basic system prompt. A skill bundles a core instruction file, reference documents the model loads on demand, supporting assets, and a trigger description that controls when it activates. Users are building skills for everything from technical playbooks to domain-specific mentors to operational runbooks, and this pattern is becoming the standard way power users encode reusable expertise into AI. Currently, there's no way to import these into Hatz. Users who've built skill libraries on other platforms have to manually recreate them as separate Apps or Agents, losing the multi-file structure and progressive context loading in the process. For MSPs onboarding teams onto Hatz, this creates unnecessary migration friction and duplicated effort. The core ask is a skill import pipeline that accepts a standard skill package (ZIP with a SKILL.md at root + optional reference files and assets) and converts it into Hatz-native Workshop items — mapping instructions to Agent system prompts, reference files to knowledge sources, and descriptions to Workshop metadata. Unsupported components would be flagged during import so the user knows what needs attention. The bigger unlock is skill routing in Chat. Once skills exist as first-class objects, Hatz could evaluate a user's message against available skill descriptions and automatically load the right expertise context — no manual app or agent selection required. This would transform Chat from a general-purpose LLM interface into a context-aware assistant that knows which domain knowledge to pull in based on the question. Long-term, this naturally extends into multi-tenant skill distribution and a community marketplace — the same management model Hatz already does well with Apps and Agents, applied to portable, versioned expertise packages that MSPs can build once and deploy across all their tenants.

Native integration between Hatz and Google Workspace apps (calendar, sheets, etc.) Similar to the M365 integration where users can use Hatz models to review/edit Google calendar, drive, and other files.

Problem: Our technicians frequently use Microsoft Teams for communication, collaboration, and incident resolution. While Hatz.AI 's chat and agent functionalities are incredibly valuable for accessing information, troubleshooting, and generating solutions, there's currently a disconnect. Technicians often have to switch between Teams and the Hatz.AI platform to leverage AI assistance. This context switching disrupts their workflow, adds friction, and can delay resolution, especially when dealing with complex problems that require rapid access to AI-driven insights during ongoing conversations. Proposed Solution: We request the development of an official integration that allows Hatz.AI 's AI chat and agent capabilities to be seamlessly accessible directly within Microsoft Teams. This could manifest as: A Teams App: A dedicated Hatz.AI app within Teams where technicians can initiate chats with the AI, access specific agents, or trigger AI actions without leaving the Teams interface. A Teams Bot: A Hatz.AI bot that can be invoked within team channels or private chats to answer questions, provide information, or perform tasks using Hatz.AI 's underlying AI models. Message Extensions/Connectors: The ability to highlight text in a Teams conversation and send it to Hatz.AI for analysis, summarization, or to generate a response, which can then be inserted back into the chat. Expected Benefits: Implementing this integration would significantly enhance the value and usability of Hatz.AI for our organization, leading to: Improved AI Usage & Adoption: By making Hatz.AI readily available within their primary communication tool, technicians will naturally integrate AI assistance into their daily workflow, increasing overall AI adoption. Streamlined Workflows & Productivity: Eliminating the need to switch applications reduces context-switching overhead, allowing technicians to stay focused and work more efficiently. Faster Problem Resolution: Technicians can get instant AI assistance for complex issues directly within their resolution conversations, accelerating troubleshooting and decision-making. Enhanced Collaboration: AI-generated insights and solutions can be easily shared and discussed within Teams channels, fostering better collaboration and knowledge sharing among team members. Reduced Training Burden: Integrating AI into a familiar environment like Teams may reduce the learning curve for new users and encourage broader utilization. We believe this integration would be a game-changer for improving technician efficiency, leveraging Hatz.AI 's power more effectively, and ultimately leading to faster and more consistent problem resolution across our operations.

This is probably already on your list, but I think it's very important for this model to be added ASAP. It appears likely that this is the most important open source LLM to be released since DeepSeek R1.

If Auto-Tool is enabled, you can still click tools, scroll through the tools and then not be able to select anything. This seems counter intuitive and blocking things at the last step. I propose one of two options: 1) When Auto-Tool is checked, do not permit Tools to be clicked, and show a tooltip that says you have to disable Auto-Tool 2) When Auto-Tool is checked, clicking "Tools" should automatically disable Auto-Tool and let you select a tool. I like solution #2 personally.