Skip to content
Blueprint Catalog

    ↑↓ move · Enter open · Esc close

    04 — Product · PR-790

    Cisco AI Defense

    A security product for AI applications and agents that finds the models, agents and MCP servers in use, attacks them in automated tests before release, scans model files and AI components for tampering, and inspects prompts, responses and tool calls at run time. Runs across the major clouds and on-premises.

    // FIG. 04 · Capability coverage

    Each tile is an L1; the bar is how many of this product's capabilities realize something beneath it. Our judgment, not a vendor claim.

    Direct & Govern

    Finance

    People & Workplace

    Customer & Market

    Products & Services

    Operations & Supply

    Technology & Data

    Resilience & Responsibility

    Industry L1s

    Product capabilities · 7

    How to read maturity and confidence

    Maturity · how much it covers

    core
    What the product is built around; the capability is covered end to end.
    strong
    Covered well, with a few gaps a buyer would notice.
    partial
    Covers part of the capability; expect to pair it with something else.
    emerging
    New or thin; on the roadmap more than in the product.

    Confidence · how well it is evidenced

    Evidence confidence: high
    The vendor's own documentation describes this module doing it.
    Evidence confidence: medium
    Documented, but how far it reaches into the capability is our reading.
    Evidence confidence: low
    Our judgment; we found no public page that confirms it.

    Sources · checked

    The public vendor documentation this mapping is based on. Maturity and confidence are our judgment, not the vendor's claim.