Exclusive: Mate Security launches Gamebooks to govern how AI agents run investigations

Security operations startup Mate Security Ltd. today launched Gamebooks, a set of structured investigation procedures that govern what its artificial intelligence agents are allowed to do while working an alert.

Mate is aiming Gamebooks at two failures that have shaped security automation. Security orchestration playbooks break whenever an environment changes, and keeping them current is constant work.

The AI-driven security operations tools that arrived to replace them brought a different problem. An agent free to reason its own way through an incident can also disable a legitimate account or shut down a production system. Most deployments handle that risk by routing consequential actions through a human analyst, which slows the response down.

A Gamebook describes investigative intent instead of an execution path. It sets out what has to be investigated, what evidence must be established, which conditions should redirect the investigation, which actions an agent may take and when that agent has to escalate, stop or request approval. How the agent gets there is left open.

The architecture separates that intent from execution. An orchestrator reads an incoming investigation and assembles the Gamebooks that fit it. Capabilities give agents reusable security skills that are not tied to any one vendor’s product. Flows handle the actual contact with tools and systems, so agents never hold open access to real systems. Grounding comes from Mate’s Security Context Graph, an earlier product that holds an organization’s current state and its history of prior decisions.

Replacing a security tool or absorbing an acquired company’s stack normally means rebuilding workflows. Mate said the same Gamebook keeps running through those changes because only the execution layer has to adapt. Analyst turnover is treated the same way. Decisions made by a departed analyst stay in the context graph, along with the reasoning behind them.

Customers can write their own Gamebooks. Teams can convert existing playbooks into investigative intent or extend the ones Mate ships, and proprietary tools and data can be plugged in. New procedures are written in natural language. Mate keeps the underlying agent engineering, evaluation and testing on its side of the line.

Every investigation also feeds the loop. Evidence, relationships and outcomes land back in the context graph. Useful patterns can be promoted into new detections, and noisy detections get tuned against what investigations actually turned up.

Oren Saban, co-founder and chief product officer at Mate, said the move to agentic investigations “requires a different architecture,” one that lets AI reason and adapt while staying anchored to how a particular organization investigates. Security teams should not have to trade control for speed, he said.

Mate cited July’s intrusion at Hugging Face Inc., where OpenAI Group PBC models under evaluation escaped their test environment and breached Hugging Face’s production systems, as evidence that AI-driven attacks can outrun an approval queue.

Gamebooks is generally available on the Mate platform from today. The company also plans to show it at CrowdStrike Holdings Inc.’s Fal.Con conference in Las Vegas, which runs Aug. 31 through Sept. 3.

Founded in 2025 by veterans of Wiz Inc. and Microsoft Corp., Mate is based in Tel Aviv. Canaan Partners led a $35 million Series A round for the company in July. Its total funding stands at more than $50 million.

Image: Mate Security