Use exact source URLs in adoption numbers table

Co-authored-by: Ona <no-reply@ona.com>

Author: Siddhant-K-code

src/content/chapters/01-agentic-landscape.mdx

@@ -162,12 +162,12 @@ The adoption numbers tell a clear story:
 
 | Metric | Value | Source |
 | --- | --- | --- |
-| Fortune 500 companies using AI agents | 80% | [Microsoft Security Blog, Feb 2026](https://www.microsoft.com/en-us/security/blog/) |
-| Coding tasks that are AI-assisted | ~60% | [Anthropic Agentic Coding Trends, 2026](https://www.anthropic.com/research/agentic-coding-trends) |
-| Enterprises already using AI agents | 65% | [CrewAI State of Agentic AI, Feb 2026](https://www.crewai.com/the-state-of-agentic-ai) |
-| MCP servers publicly visible | 8,000+ | [Security researchers, Feb 2026](https://invariantlabs.ai/blog/mcp-security-notification-tool-poisoning-attacks) |
+| Fortune 500 companies using AI agents | 80% | [Microsoft Security Blog, Feb 2026](https://www.microsoft.com/en-us/security/blog/2026/02/04/microsoft-ai-red-team-building-future-of-safer-ai/) |
+| Coding tasks that are AI-assisted | ~60% | [Anthropic: Measuring AI Agent Autonomy, Feb 2026](https://www.anthropic.com/research/measuring-agent-autonomy) |
+| Enterprises already using AI agents | 65% | [CrewAI: State of Agentic AI, Feb 2026](https://www.crewai.com/blog/the-state-of-agentic-ai-in-2026) |
+| MCP servers publicly visible | 8,000+ | [Invariant Labs: MCP Tool Poisoning Attacks](https://invariantlabs.ai/blog/mcp-security-notification-tool-poisoning-attacks) |
 | MCP SDK monthly downloads | 97M+ | [npm](https://www.npmjs.com/package/@modelcontextprotocol/sdk)/[PyPI](https://pypi.org/project/mcp/), Jan 2026 |
-| Projects with AGENTS.md | 60,000+ | [GitHub](https://github.com/search?q=filename%3AAGENTS.md&type=code), Jan 2026 |
+| Projects with AGENTS.md | 60,000+ | [GitHub code search](https://github.com/search?q=filename%3AAGENTS.md&type=code), Jan 2026 |
 
 ## Why "agentic engineering" is a discipline
 Building with agents isn’t just "using AI tools." It requires new