# Methodology & Bibliography — Agent Cards Explained

> How this site is sourced, which canonical primary sources back its claims, and how the data is refreshed. Maintained by AgentsBooks. Data last refreshed: 2026-05-08.

## Sourcing rule

Every claim has at least one direct quote or paraphrase from a canonical primary source — vendor docs, standards bodies, regulator publications, peer-reviewed papers, or an analyst publication where the analyst is the primary source for the framing. Wikipedia and secondary blogs are never the primary citation. When a topic is contested, both positions are carried with attributed flags.

## Freshness flags

- **Foundational** — original peer-reviewed papers (e.g., Mitchell et al. 2019 Model Cards). Refreshed only if substantively revised.
- **In force** — current binding regulator text or in-effect specifications, with the in-force date.
- **Emerging 2024–2026** — terms or specs that entered mainstream discourse recently and are still evolving.
- **Contested** — entries with named, meaningful disagreement in the field; we carry both positions.

## Refresh cadence

- Default: bi-annual full review (per the SKILL Part G mechanic table for pillar mini-sites).
- Trigger refresh: A2A spec revision (v1.1+); IETF AAuth RFC progression; NIST CAISI publication; Microsoft Entra Agent ID major update; new Linux Foundation founding-member announcement; major marketplace launch.
- Citation rot check: quarterly URL-liveness scan over every cited source.

## Bibliography

1. *A2A Protocol — Specification (v1.0)*. https://a2a-protocol.org/latest/specification/ (accessed 2026-05-08, in force)
2. *Google Developers — Announcing the Agent2Agent Protocol*. https://developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/
3. *Linux Foundation — Launches the Agent2Agent Protocol Project*. https://www.linuxfoundation.org/press/linux-foundation-launches-the-agent2agent-protocol-project-with-google-and-tech-leaders
4. *github.com/a2aproject/A2A* — reference implementation, JSON schemas, TypeScript types
5. *A2A Project — Partners*. https://a2a-protocol.org/latest/community/partners/
6. *Mitchell et al., Model Cards for Model Reporting* (arXiv:1810.03993). https://arxiv.org/abs/1810.03993 (foundational, 2019)
7. *RFC 9309 — Robots Exclusion Protocol*. https://www.rfc-editor.org/rfc/rfc9309.html (in force, 2022)
8. *llms.txt — proposal* (Howard, Answer.AI, 2024). https://llmstxt.org/
9. *OpenAPI Specification 3.1.0*. https://spec.openapis.org/oas/v3.1.0.html (in force)
10. *Model Context Protocol — Specification (2025-11-25)*. https://modelcontextprotocol.io/specification/2025-11-25 (in force)
11. *Anthropic — Introducing the Model Context Protocol*. https://www.anthropic.com/news/model-context-protocol
12. *MCP Blog — The 2026 MCP Roadmap*. https://blog.modelcontextprotocol.io/posts/2026-mcp-roadmap/
13. *Microsoft — Announcing Microsoft Entra Agent ID*. https://techcommunity.microsoft.com/blog/microsoft-entra-blog/announcing-microsoft-entra-agent-id-secure-and-manage-your-ai-agents/3827392
14. *Microsoft — Agent Framework v1.0*. https://devblogs.microsoft.com/agent-framework/microsoft-agent-framework-version-1-0/
15. *Microsoft Learn — Agent Framework Overview*. https://learn.microsoft.com/en-us/agent-framework/overview/
16. *Salesforce — AgentExchange launch (March 2025)*. https://www.salesforce.com/news/press-releases/2025/03/04/agentexchange-announcement/
17. *Salesforce — Agentforce A2A integration with Google Cloud*. https://www.salesforce.com/news/press-releases/2025/06/24/agentforce-a2a-google-cloud/
18. *Google Cloud — Vertex AI Agent Builder / Agentspace*. https://cloud.google.com/products/agent-builder
19. *Google — Agent Development Kit (ADK)*. https://google.github.io/adk-docs/
20. *AWS — Bedrock AgentCore Runtime*. https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html
21. *NIST CAISI — AI Agent Standards Initiative*. https://www.nist.gov/caisi/ai-agent-standards-initiative
22. *NIST — Announcing the AI Agent Standards Initiative*. https://www.nist.gov/news-events/news/2026/02/announcing-ai-agent-standards-initiative-interoperable-and-secure
23. *IETF — AAuth, Agentic Authorization OAuth 2.1 Extension (draft-rosenberg-oauth-aauth-00)*. https://www.ietf.org/archive/id/draft-rosenberg-oauth-aauth-00.html
24. *OWASP — Top 10 for Large Language Model Applications*. https://owasp.org/www-project-top-10-for-large-language-model-applications/
25. *Gartner — Hype Cycle for Agentic AI 2026*. https://www.gartner.com/en/articles/hype-cycle-for-agentic-ai
26. *McKinsey QuantumBlack — The state of AI in 2025*. https://www.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai
27. *arXiv:2601.13671 — Orchestration of Multi-Agent Systems*. https://arxiv.org/abs/2601.13671
28. *Anthropic — Building Effective Agents*. https://www.anthropic.com/research/building-effective-agents
29. *Marcus, G. — Six (or seven) predictions for AI 2026*. https://garymarcus.substack.com/p/six-or-seven-predictions-for-ai-2026 (contested)

Audit trail: `raw/research-notes.md` in the satellite's source repository.

*Updated 2026-05-08.*