Role and scope limits
Each agent gets a defined role and a list of the tools, data and actions it may use. Anything outside that list is blocked.
Forge Guard
Forge Guard helps organisations decide whether a specific AI agent is safe to use in a specific context, and keeps it within the limits they agree. It packages the controls we built and tested in Forge.
The problem
AI agents can read files, call systems and send things on your behalf. Most security teams have no consistent way to judge that risk, so they decide case by case or say no. Forge Guard gives them a method, and the controls to back it up.
The method
What it does, the tools and data it can reach, how much it acts on its own, and the context it will work in.
Rate the agent’s permissions, data access, autonomy and likely failure modes, covering both cyber security and operational resilience.
Map each risk to controls such as tighter scope, approval gates, monitoring or rollback, and show the risk that remains.
Produce a record that security, audit and service owners can sign off, and review it when the agent or its context changes.
The controls
Each agent gets a defined role and a list of the tools, data and actions it may use. Anything outside that list is blocked.
High-risk actions wait for a named person. Approvals reset if the work changes after review.
Every output says where it came from: a source document, the agent’s own proposal, or a gap that needs a person.
Before an agent acts on the outside world, the reviewer confirms a fingerprint (SHA-256) of exactly what they checked.
Agents see only the data the task needs. Personal data can be pseudonymised before an agent reads it.
Every tool call, output and approval is logged. Actions can be stopped, and changes can be rolled back.
Tested on live work
In 2026 we used these controls on live UK public-sector tenders.
tender answers drafted by an agent, each labelled by source, with legal declarations never pre-filled
human confirmations, tied to a fingerprint, before the agent could submit anything
tender documents read in one pass, with every finding linked to its source clause
Open source
We will release the core risk method and control framework as open source, so any organisation can use, check and improve it. We are looking for UK public bodies to test it with us.