chore: add ai-bom agentic enrichment doc

snyk-data-and-governance/how-snyk-incorporates-generative-ai-into-the-platform.md

@@ -55,6 +55,10 @@ Snyk uses LLMs from established AI providers, including OpenAI and Anthropic, th
 
 <table><thead><tr><th width="230.15625">Attribute</th><th>Details</th></tr></thead><tbody><tr><td><strong>Purpose</strong></td><td>Allows the EVO AI-BOM to detect customer-specific AI assets, such as fine-tuned models.</td></tr><tr><td><strong>AI models / deployment</strong></td><td>Anthropic’s Claude models through GCP Vertex or AWS Bedrock.</td></tr><tr><td><strong>Data processed</strong></td><td>Code snippets used to label whether patterns are AI assets.</td></tr><tr><td><strong>Data retention</strong></td><td>Customer proprietary software code is not retained by the provider of these AI models.</td></tr><tr><td><strong>Additional information</strong></td><td>More information about Evo AI-BOM Pattern Detection is available via the Customer portal.</td></tr></tbody></table>
 
+#### Evo AI-BOM Agentic Enrichment
+
+<table><thead><tr><th width="230.15625">Attribute</th><th>Details</th></tr></thead><tbody><tr><td><strong>Purpose</strong></td><td>AI-powered agent that operates in two parts: (1) Agentic Discovery - discovers first-party AI components (agents, tools, MCP servers/clients/resources, models) and the relations between them that static analysis misses; (2) Agentic Metadata Gathering - extracts tool descriptions and agent system prompts from already-discovered components by reading their source code.</td></tr><tr><td><strong>AI models / deployment</strong></td><td>Anthropic’s Claude models through GCP Vertex or AWS Bedrock.</td></tr><tr><td><strong>Data processed</strong></td><td><ul><li>Repository source code</li><li>Existing inventory of AI components and relations from static analysis</li><li>Source code locations of already-discovered tools and agents for metadata extraction</li></ul></td></tr><tr><td><strong>Data retention</strong></td><td>Customer proprietary software code is not retained by the provider of these AI models. Tool descriptions and agent system prompts are stored in Snyk’s database as properties of their respective components.</td></tr><tr><td><strong>Additional information</strong></td><td>More information about Evo AI-BOM Agentic Enrichment is available via the Customer portal.</td></tr></tbody></table>
+
 ## Additional AI safeguards and controls
 
 Snyk has taken a proactive approach to AI governance by implementing robust policies, procedures, and technical controls to encompass AI-specific considerations. In addition to Snyk's internal policies and controls, we maintain an overarching AI Governance Program managed by our cross-functional AI Advisory Board.