# Methodology & Bibliography — Agentic Glossary Quick Reference

> How this quick-reference glossary is built, what counts as a canonical citation, how this site relates to the deep glossary, and how we keep entries fresh.

**Data last refreshed:** 2026-05-07. **Next scheduled refresh:** Q3 2026 (or sooner on regulator / vendor trigger).

## What this site is — and isn't

This is the *quick-reference* sibling of the [Agentic Glossary](https://agentic-glossary.roei-020.workers.dev/). The deep glossary publishes 31 hand-curated flagship terms with paragraph-long entries and full primary-source block-quotes. This site publishes 88 terms with one-to-three-sentence definitions and one canonical citation each — optimized for fast lookup, copy-paste, and clean LLM citation.

For flagship terms (Agent, MCP, A2A, RAG, Constitutional AI, the 8 Primitives, Reliability Gap, the Frameworks triad, ADLC, AX, Context Graph, Agent Management Platform, AI RMF, EU AI Act high-risk system, and others), each entry on this site carries a *Compare with deep glossary →* link to the deeper, narrative entry.

## What counts as a "term"

The bar for inclusion in v1:

1. It is searched for, currently, by builders / operators / buyers of AI agents.
2. At least one canonical primary source defines it directly.
3. It either (a) connects to one of the AgentsBooks 8 Primitives or a current pillar topic, or (b) appears recurrently in agentic-system architecture, evaluation, or compliance literature.

## Sourcing rule

Every entry has at least one direct citation to a canonical primary source — meaning:

- The vendor's own published documentation, blog, or research paper (Anthropic, Google, OpenAI, Microsoft, Meta).
- The standards body's own specification (Linux Foundation A2A / MCP, NIST, ISO).
- The regulator's own publication (European Commission, NIST, FATF, FCA).
- The peer-reviewed paper of record.
- An analyst publication where the analyst is the primary source for the framing (Gartner, McKinsey).

Wikipedia, secondary blogs, and content farms are *never* the primary citation.

## Freshness flags

- **Foundational** — original peer-reviewed papers (2017 Transformer, 2020 RAG, 2022 CoT, 2022 ReAct, 2022 Constitutional AI). Refreshed only on substantive revision.
- **In force** — current binding regulator text or in-effect specifications, with the in-force date.
- **Emerging 2026** — terms that entered mainstream discourse in 2026 (ADLC, AX, context graph, agent management platform, AI Agent Interoperability Profile).
- **Contested** — entries with named, meaningful disagreement (Agentic AI, Reliability Gap).

Anything older than six months that doesn't carry one of the four flags is considered stale and gets retired or refreshed.

## Refresh cadence

| Trigger | Action |
|---|---|
| Quarterly | Full audit: every cited URL pinged, every primary source re-read, new vocabulary added |
| Vendor canonical-source publication | Targeted refresh within 7 days |
| Regulator publication or in-force date change | Same-week update |
| New peer-reviewed paper that supersedes a cited claim | Same-week update |
| URL 404 or vendor pivot | Immediate fix |

## Bibliography

- Anthropic — *Building Effective Agents* — https://www.anthropic.com/research/building-effective-agents — accessed 2026-05-07
- Anthropic — *Introducing the Model Context Protocol* — https://www.anthropic.com/news/model-context-protocol — accessed 2026-05-07
- Anthropic — *Measuring AI agent autonomy in practice* — https://www.anthropic.com/research/measuring-agent-autonomy — accessed 2026-05-07
- Anthropic — *Many-shot jailbreaking* — https://www.anthropic.com/research/many-shot-jailbreaking — accessed 2026-05-07
- Hubinger et al. (Anthropic) — *Sleeper Agents*, arXiv:2401.05566, 2024 — accessed 2026-05-07
- Bai et al. (Anthropic) — *Constitutional AI*, arXiv:2212.08073, 2022 — accessed 2026-05-07 — Foundational
- Vaswani et al. — *Attention Is All You Need*, arXiv:1706.03762, 2017 — accessed 2026-05-07 — Foundational
- Lewis et al. — *Retrieval-Augmented Generation*, arXiv:2005.11401, 2020 — accessed 2026-05-07 — Foundational
- Wei et al. — *Chain-of-Thought*, arXiv:2201.11903, 2022 — accessed 2026-05-07 — Foundational
- Yao et al. — *ReAct*, arXiv:2210.03629, 2022 — accessed 2026-05-07 — Foundational
- Yao et al. — *Tree of Thoughts*, arXiv:2305.10601, 2023 — accessed 2026-05-07
- Schick et al. — *Toolformer*, arXiv:2302.04761, 2023 — accessed 2026-05-07
- Park et al. — *Generative Agents*, arXiv:2304.03442, 2023 — accessed 2026-05-07
- Shinn et al. — *Reflexion*, arXiv:2303.11366, 2023 — accessed 2026-05-07
- Chen et al. — *HumanEval / Codex*, arXiv:2107.03374, 2021 — accessed 2026-05-07 — Foundational
- Jimenez et al. — *SWE-bench*, arXiv:2310.06770, 2023 — accessed 2026-05-07
- Mialon et al. — *GAIA*, arXiv:2311.12983, 2023 — accessed 2026-05-07
- Model Context Protocol — *Specification (2025-11-25)* — https://modelcontextprotocol.io/specification/2025-11-25 — accessed 2026-05-07 — In force
- Google Developers — *Announcing the A2A Protocol* — https://developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/ — accessed 2026-05-07
- A2A Protocol — *Specification* — https://a2a-protocol.org/latest/specification/ — accessed 2026-05-07 — In force
- OpenAI — *Function calling docs* — https://platform.openai.com/docs/guides/function-calling — accessed 2026-05-07
- OpenAI — *Evals framework* — https://github.com/openai/evals — accessed 2026-05-07
- NIST — *AI Risk Management Framework (AI 100-1)* — https://nvlpubs.nist.gov/nistpubs/ai/nist.ai.100-1.pdf — accessed 2026-05-07 — In force
- NIST — *Generative AI Profile (AI 600-1)* — https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf — accessed 2026-05-07 — In force
- NIST — *AI RMF program (AI Agent Standards Initiative)* — https://www.nist.gov/itl/ai-risk-management-framework — accessed 2026-05-07
- European Commission — *EU AI Act Implementation Timeline* — https://ai-act-service-desk.ec.europa.eu/en/ai-act/timeline/timeline-implementation-eu-ai-act — accessed 2026-05-07 — In force 2 August 2026 (subject to deferral)
- ISO — *ISO/IEC 42001:2023* — https://www.iso.org/standard/81230.html — accessed 2026-05-07 — In force
- Gartner — *Hype Cycle for Agentic AI 2026* — https://www.gartner.com/en/articles/hype-cycle-for-agentic-ai — accessed 2026-05-07
- McKinsey QuantumBlack — *State of AI 2025* — https://www.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai — accessed 2026-05-07
- Gary Marcus — *Six (or seven) predictions for AI 2026*, Substack — https://garymarcus.substack.com/p/six-or-seven-predictions-for-ai-2026 — accessed 2026-05-07 — Contested
- LangChain — *LLM observability tools* — https://www.langchain.com/articles/llm-observability-tools — accessed 2026-05-07
- Pecollective — *AI agent frameworks compared (2026 survey)* — https://pecollective.com/blog/ai-agent-frameworks-compared/ — accessed 2026-05-07
- Firecrawl — *Best vector databases (2026 survey)* — https://www.firecrawl.dev/blog/best-vector-databases — accessed 2026-05-07
- AgentsBooks — *Anatomy of a Firm* — https://agentsbooks.com/anatomy — accessed 2026-05-07
- AgentsBooks — *Tasks & Triggers* — https://agentsbooks.com/features/tasks-triggers — accessed 2026-05-07
- AgentsBooks — *Knowledge & Learning* — https://agentsbooks.com/features/knowledge-learning — accessed 2026-05-07
- AgentsBooks — *Control & Friends* — https://agentsbooks.com/features/control-friends — accessed 2026-05-07

## Relationship to the deep glossary

The [Agentic Glossary](https://agentic-glossary.roei-020.workers.dev/) is the canonical narrative entry-point for AgentsBooks vocabulary; this site is its breadth layer and copy-paste surface. Where the two sites cover the same flagship term, the deep glossary's definition is the authoritative one — this site defers to it via a *Compare with deep glossary →* link on every flagship entry.

## How to suggest a term or correction

Email hello@agentsbooks.com with the term, what you'd like it defined as, and the canonical source you want cited.

*Updated 2026-05-07.*