Feature Requests

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.

Clients are seeking a chatbot that can answer FAQs on their web sites. Currently, they'd have to use another tool. Would be great to extend the Hatz agents to offer this.

Providing a mobile-friendly version or dedicated app for the platform would allow users to access tools and features on the go, ensuring flexibility and convenience across devices. Request from PCH Customer

For our clients that are 100+ users they would like visibility into the usage dasboard for thier tenant/organization. This is in addition to the ability to audit chats for complience needs.

Not sure if I'm misunderstanding the instructions, but it seems to require creating an api user with a designated set of permissions and then sharing the credentials to everyone who needs to add the connectwise integration. So not only are the permissions the same for everyone, the creds are also shared with everyone. Seems very sketchy, unfriendly and insecure. Would expect some kind of filter to talk to Connectwise using my existing permissions not an admins level of access.

I'd like to create an agent with integrations that could be shared org wide. Currently that isn't possible.

I raised this with Lark M and confirmed it is a current gap, so posting here to get it on the roadmap. When using a Hatz agent with the ConnectWise integration, the agent cannot see internal notes or discussion notes on a ticket. Hatz support confirmed that the current tools only pull top-level ticket data and do not access the notes that live separately in ConnectWise. Our specific use case is an agent we built to look up similar past tickets and how they were resolved, so our technicians can reference real troubleshooting history instead of starting from scratch. Right now that agent is not useful because the resolution detail, the diagnostic steps, and the actual fix are all documented in the internal notes, none of which the agent can see. What we are asking for is the ability for a Hatz agent to read ticket notes, including internal notes and discussion notes, when looking up a ticket in ConnectWise. The ability to write a note back to a ticket from an agent would also be valuable.

Right now ConnectWise Manage integration supports reading core ticket fields (e.g., summary/description/status/priority), but it does not currently expose ticket notes/entries (Internal, Discussion, or Resolution) to Hatz AI. We need to access these notes to see who worked on a ticket (since often times there are multiple people collaborating on one ticket). It also shows what the fix was, which we would like to track.

It would be amazing to have shared "Editor" permissions so teams can build together in one file. For this to work and users feel good about contributing, it would be important to have: Audit Trail: A change log showing who updated specific prompts or API tool calls (e.g., "Kris updated the Ingram Micro integration"). Contribution Sidebar: Credit the builder in the chat output. Identify which team member authored the specific logic or tool that generated the response. This transforms AI development into a team effort. It ensures accountability, simplifies maintenance and recognizes "AI Champions" within the company.

This request proposes adding optional, session-scoped memory to secure chat sessions in Hatz AI. Allowing the system to retain relevant context across interactions would create a more continuous, user-friendly experience comparable to what users expect from leading AI platforms. Problem At present, secure chats in Hatz AI operate as isolated sessions with no retained context. Users must repeatedly re-explain background information, preferences, and ongoing work. This creates friction and discourages adoption of secure chat for longer workflows. Additionally, many end users are accustomed to memory-enabled experiences in other AI platforms such as ChatGPT. When they switch to Hatz AI’s secure chat, the lack of continuity feels like a step backward, reducing engagement and limiting the perceived value of the secure environment. Proposed Solution Introduce an optional memory system for secure chat sessions that allows relevant context to persist across interactions. Users should have explicit controls to enable or disable memory and to view, edit, or delete stored items. Memory categories should be configurable, allowing users to decide what types of information can be retained. All data must remain encrypted and isolated, maintaining Hatz AI’s existing security guarantees while enhancing usability. Benefits A persistent memory feature would significantly improve conversational efficiency and consistency. It would reduce repetitive setup, support ongoing workflows, and create a user experience aligned with what customers already expect from modern AI tools. By making secure chat feel more familiar and intuitive, Hatz AI can encourage wider adoption and deliver a more competitive, high-quality experience. Use Cases Teams working on multi-step projects could maintain evolving context across secure chats without starting from scratch. Support scenarios could preserve relevant details across multiple interactions. Professionals using Hatz AI for research, planning, or iterative drafts would benefit from persistent preferences and project history, allowing secure chat to match the fluid experience they are used to in other AI platforms.