Artificial Intelligence1 min read

How asago bridges the gaps in AI agent security

By · Published by Everything Blog

In short

The community-governed framework addresses the traditional disconnect between broad legal language and technical execution through its automated policy mapping tool. It parses governance documents to extract testable criteria tied to industry standards like the NIST AI Risk Management Framework, OWASP LLM Top 10, and IBM AI Risk Atlas. These extracted rules are then converted into structured scenario YAML files to establish an auditable workflow. This systematic mechanism provides technical teams with clear evidence and confidence ratings to manage risks like bias and misrepresentation.

Key points

  • Asago provides an open-source, community-governed framework to automate translating AI go…: Asago provides an open-source, community-governed framework to automate translating AI governance policies into technical systems.
  • Each policy mapping delivers documentary evidence, taxonomy references, and a confidence…: Each policy mapping delivers documentary evidence, taxonomy references, and a confidence rating to support systematic compliance.
  • Structured scenario YAML files output by the framework generate clear audit trails for te…: Structured scenario YAML files output by the framework generate clear audit trails for testing and managing security requirements.

Sources checked by our analysis pipeline: 1

Even if you have never shipped out an agent yourself, you would hope that the companies behind the agents you're using have tested the security of the model and harness. Traditionally, as described in the Red Hat blog post Introducing asago: Open source AI safety and governance orchestration, onboarding a new agent looks like this:

- Policy development: Policy documents are created to encode the organization's AI dos and don'ts.

- Risk extraction: Someone reads the documents and identifies the theoretical risks they describe.

- Risk triaging: Someone decides which of the risks apply to the agent being onboarded and whether or not they can be tested.

- Scenario generation and red teaming: Technical teams build test scenarios for the risks and use red teaming frameworks to test the agent.

- Iteration: The results are interpreted and safety features are implemented as needed. The agent is retested until it is production ready.

Connecting policy development and risk extraction is in itself a difficult process. After an organization's legal team drafts the policy, security reviews it, and leadership signs off on…

Artificial Intelligence