M-Files launches Custom Agents for auditable document AI workflows
The beta feature embeds natural-language AI agents into governed document workflows with permissions, metadata trails, and future MCP support.
Key takeaways
M-Files announced Custom Agents Beta on June 24, 2026, expanding its agentic AI portfolio for document-centric automation.
M-Files announced new agentic AI capabilities on June 24, 2026, including M-Files Custom Agents in beta. The feature brings natural-language AI instructions into document workflows so organizations can automate validation, routing, and content-driven decisions.
According to M-Files, a Custom Agent can read a document and related business context, update only properties it is permitted to change, and move work forward automatically. Values set by the agent are recorded on the metadata card with reasoning and source information, creating an auditable trail.
The release matters because enterprise AI agents are moving beyond retrieval into controlled workflow execution. For teams evaluating AI tools, the practical questions are permission boundaries, metadata quality, auditability, human review, and interoperability with standards such as MCP.
What this means for everyday users
For ENHE readers, the release shows that practical AI agents require governed content, permissions, metadata, and audit trails, not only chat interfaces.
Tools you may use
Windows Desktop Workflow | Personal AI Agent Companion
Value:Windows Desktop Workflow | Personal AI Agent Companion is an AI software app
LumiOS Personal AI Companion
Value:LumiOS is not another chat window
Your AI account needs, covered. Contact customer service if you need assistance.
Value:Your AI account needs
Related tutorials
LumiOS Personal AI Companion guide
LumiOS Personal AI Companion
High-Frequency AI Prompts | Daily Life | Work | Learning | Teaching guide
High-Frequency AI Prompts | Daily Life | Work | Learning | Teaching
AI Monetization Course | Practical AI Side Hustle Skills guide
AI Monetization Course | Practical AI Side Hustle Skills
Related reading
From Chat Boxes to Personal AI Companions: AI Assistants Are Entering the Desktop Execution Era
AI assistants are moving from answering questions toward continuing real tasks. AI agents, MCP tool ecosystems, personal memory, and local workbenches are pushing this shift together. For users, the real value is not another chat box, but less repeated context setup and more continuity from thinking to doing.
Google Cloud and the Philippines DICT Bring Public Sector AI Agents Into Deployment
Google Cloud and the Philippines Department of Information and Communications Technology announced an expanded multi-year collaboration in June 2026. The program includes public sector AI agents, Gemini Enterprise, Google Workspace, a cross-agency cyber defense alliance and connectivity infrastructure. For AI tool users, the case highlights governance, permissions, data grounding and measurable workflow impact.
Alibaba Cloud SMS Skill Brings AI Agents Into Messaging Operations
Alibaba Cloud SMS Skill is a concrete example of cloud product capabilities becoming callable through AI Agent Skills, with practical implications for workflow automation and account governance.
GLM-5.2 Launches With 1M Context for Long-Horizon AI Agents
Z.ai released GLM-5.2 on June 17, 2026, describing it as a flagship long-horizon model with 1M-token context, stronger coding capability, flexible reasoning effort and an MIT open-source license. The model weights are listed on Hugging Face and ModelScope, with deployment support noted for frameworks such as SGLang, vLLM, Transformers, KTransformers and Unsloth.
Desktop AI Operating Companions Are Moving Assistants Into the Execution Era
AI assistants are shifting from one-off chat interfaces toward personal AI operating companions. MCP standardizes connections to tools and data, local AI brings some capability closer to the device, and LumiOS provides a concrete desktop product example for this shift.
GitHub Copilot CLI GA Brings AI Coding Agents Deeper Into Terminal Workflows
GitHub announced on June 23, 2026 that the redesigned terminal interface for GitHub Copilot CLI is generally available. The interface adds terminal tabs for sessions, gists, issues and pull requests, plus in-session configuration for MCP servers, skills and plugins. On the same day, the GitHub Copilot app added BYOK support for model providers including OpenAI, Azure OpenAI, Microsoft Foundry, Anthropic, LM Studio, Ollama and OpenAI-compatible endpoints.
Summary
M-Files Custom Agents highlight a broader shift from AI-assisted search to auditable AI workflow automation inside business systems.