A Guth Labs publication ↗
Back to News

FlowForma announces Agent Trust hub for monitoring AI agents

Three green glass prisms linked to a central gold control gate on a cream pedestal
AI-generated editorial illustration

FlowForma announced Agent Trust on November 18, describing an available governance hub for monitoring AI agents across different software platforms.

The Dublin company lists prebuilt connections for Microsoft Copilot Studio, Power Automate and n8n, plus support for custom agents. Connected agents receive an identity and owner so teams can track responsibility alongside activity and cost.

FlowForma says the system evaluates work against business outcomes and human corrections rather than relying on an agent's own confidence. Operators can pause an agent or route its output for human review, with intervention and policy changes recorded.

Its product page also describes monitoring run costs by model and comparing autonomy with how often people correct results. These are vendor-described capabilities, not independently tested guarantees that every unauthorized agent will be discovered.

The company plans a demonstration on November 24 at 3 p.m. GMT. The November 18 release is the dated launch announcement; product information was already publicly indexed earlier.

The useful distinction is between observing technical activity and judging whether an agent delivered acceptable work. A shared register and documented intervention path can help teams connect those two questions.

Sources and citations

Revision history

Published .