Feature Requests

There is no ability to write to sharepoint, one drive, post files in teams. This is really killing automation flows as I cannot properly create anything. I have gone round and round and all the permissions are good, everything is setup. Except hatz cannot write/upload anything to sharepoint/onedrive or teams. There by killing agents and workflows! I have talked to larper and I have worked with support.

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.

Currently, when a chat, agent, or workflow generates a document or file-based deliverable on the Hatz.ai platform, it produces a randomly generated AWS link. This link is publicly accessible to anyone who has it, which constitutes "security by obscurity" which is not a recognized or acceptable security control. This creates several critical concerns for enterprise and regulated customers: • Data Exposure Risk o Generated files are not access-controlled, meaning sensitive outputs could be accessed by unintended parties. • No Integration with Customer Storage o There is currently no ability to write outputs directly to customer-owned storage repositories such as Microsoft 365 (SharePoint/OneDrive) or internal/external file systems. • Compliance & Regulatory Gaps o Without the ability to route files to governed storage, customers cannot maintain their compliance posture or meet data residency and handling requirements. • Security Framework Control Failures o This limitation makes it difficult or impossible to satisfy technical controls required by frameworks such as SOC 2, ISO 27001, NIST, HIPAA, and others. Requested Features: Implement access-controlled, authenticated file links (at minimum) to replace open AWS URLs. Enable native integrations with customer storage repositories, starting with Microsoft 365 (SharePoint/OneDrive) and common file systems. Allow customers to define where file outputs are stored, ensuring data stays within their governed environments. This is a foundational capability for enterprise adoption and security-conscious customers. Thank you for considering this request!

We would like to have the ability to create user groups that would prevent them to use high cost LLMs and restrict them to what the admin wants. VIPs want high token cost LLMs available Regular users would only have access by cost. Some restricted to medium, some restricted to low. The idea is for the customer to have some control of usage and token consumption.

Need the ability to save outputted files to OneDrive and to folders that are shared to the user

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

Scalepad MCP is not providing warranty and purchase information from any of the retrieved computers, so we end up having issues pulling some of the important information.

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.

Liongard has a newly announced MCP server that would be excellent if it could be integrated with Hatz. With Direct Integration we could remove the need for a separate AI sub for Liongard and streamline the process for both platforms.