Every source cited across the topic catalog, consolidated and alphabetized. Sources are primary documentation, standards bodies, peer-reviewed or preprint research, and named engineering organizations' own published data: not marketing content, SEO content, or generic consultant thought leadership. This list is a lookup appendix; the in-context citation for each source appears under the relevant topic's "Recommended Learning" entry in the catalog. - [A Timeline of Model Context Protocol (MCP) Security Breaches](https://authzed.com/blog/timeline-mcp-breaches) - [A2A and MCP: A2A Protocol](https://a2a-protocol.org/latest/topics/a2a-and-mcp/) - [A2A Protocol Surpasses 150 Organizations...: Linux Foundation](https://www.linuxfoundation.org/press/a2a-protocol-surpasses-150-organizations-lands-in-major-cloud-platforms-and-sees-enterprise-production-use-in-first-year) - [Access Foundry Models and Other Language Models Through a Gateway: Azure Architecture Center](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/azure-openai-gateway-guide) - [Activating your internal AI champions (GitHub)](https://github.com/resources/insights/activating-internal-ai-champions) - [Agent Authority Least Privilege Framework: FINOS](https://air-governance-framework.finos.org/mitigations/mi-18_agent-authority-least-privilege-framework.html) - [Agentic AI: Threats and Mitigations](https://genai.owasp.org/resource/agentic-ai-threats-and-mitigations/) - [AgentOps: Enabling Observability of LLM Agents (arXiv)](https://arxiv.org/html/2411.05285v2) - [AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases](https://arxiv.org/abs/2407.12784) - [agents.md: the open standard](https://agents.md/) - [AI Act: Shaping Europe's digital future (European Commission)](https://digital-strategy.ec.europa.eu/en/policies/regulatory-framework-ai) - [AI Agents as Users: Nielsen Norman Group](https://www.nngroup.com/articles/ai-agents-as-users/) - [AI Agents Have an Authorization Problem, Not Just an Identity Problem](https://blog.spruceid.com/ai-agents-have-an-authorization-problem-not-just-an-identity-problem/) - [AI Chatbots Discourage Error Checking: Nielsen Norman Group](https://www.nngroup.com/articles/ai-chatbots-discourage-error-checking/) - [AI gateway capabilities in Azure API Management](https://learn.microsoft.com/en-us/azure/api-management/genai-gateway-capabilities) - [AI Red Teaming Initiative: OWASP Gen AI Security Project](https://genai.owasp.org/initiatives/ai-red-teaming-initiative/) - [AI Risk Management Framework (NIST)](https://www.nist.gov/itl/ai-risk-management-framework) - [AI RMF: Generative Artificial Intelligence Profile (NIST)](https://www.nist.gov/publications/artificial-intelligence-risk-management-framework-generative-artificial-intelligence) - [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) - [Anthropic: Claude Code best practices](https://www.anthropic.com/engineering/claude-code-best-practices) - [Anthropic: Effective harnesses for long-running agents](https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents) - [Anthropic: How we built our multi-agent research system](https://www.anthropic.com/engineering/multi-agent-research-system) - [appleinsider.com](https://appleinsider.com/articles/26/01/14/gemini-trained-apple-intelligence-will-work-like-other-llms-says-unsurprising-report) - [Article 4: AI literacy: EU Artificial Intelligence Act](https://artificialintelligenceact.eu/article/4/) - [Auditing and Logging AI Agent Activity: A Guide for Engineers: LoginRadius Engineering Blog](https://www.loginradius.com/blog/engineering/auditing-and-logging-ai-agent-activity) - [Authorization and Governance for AI Agents: Runtime Authorization Beyond Identity at Scale](https://techcommunity.microsoft.com/blog/microsoft-security-blog/authorization-and-governance-for-ai-agents-runtime-authorization-beyond-identity/4509161) - [Bersin](https://joshbersin.com/2025/10/sap-jumps-ahead-in-ai-agents-with-joule-hcm-features-and-more/) - [BIRD-SQL benchmark](https://bird-bench.github.io/) - [Block denied topics to help remove harmful content: Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-denied-topics.html) - [Building Effective AI Agents: Anthropic](https://www.anthropic.com/engineering/building-effective-agents) - [Canaries Dashboard (Stanford Digital Economy Lab)](https://digitaleconomy.stanford.edu/project/indicators/canaries-dashboard/) - [Canaries in the Coal Mine? Six Facts about the Recent Employment Effects of AI (Stanford Digital Economy Lab)](https://digitaleconomy.stanford.edu/publication/canaries-in-the-coal-mine-six-facts-about-the-recent-employment-effects-of-artificial-intelligence/) - [Chargeback vs. Showback: Cloud Cost Allocation Models Explained: CloudZero](https://www.cloudzero.com/blog/chargeback-vs-showback/) - [Claude Enterprise](https://claude.com/solutions/enterprise) - [Claude prompting best practices (Claude Platform Docs)](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices) - [Cloud Security Alliance: The Vibe Coding Governance Gap](https://labs.cloudsecurityalliance.org/research/csa-research-note-vibe-coding-ai-governance-gap-20260602-csa/) - [cloud.google.com](https://cloud.google.com/blog/products/ai-machine-learning/announcing-agents-to-payments-ap2-protocol) - [Computer use tool: Claude Platform Docs](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) - [Computer-Using Agent: OpenAI](https://openai.com/index/computer-using-agent/) - [Contextual Retrieval (Anthropic)](https://www.anthropic.com/engineering/contextual-retrieval) - [deloitte.com](https://www.deloitte.com/us/en/what-we-do/capabilities/applied-artificial-intelligence/articles/agentic-ai-enterprise-2028.html) - [Deloitte: The State of AI in the Enterprise](https://www.deloitte.com/us/en/what-we-do/capabilities/applied-artificial-intelligence/content/state-of-ai-in-the-enterprise.html) - [developers.googleblog.com](https://developers.googleblog.com/en/google-cloud-donates-a2a-to-linux-foundation/) - [Diving Into the MCP Authorization Specification: Descope](https://www.descope.com/blog/post/mcp-auth-spec) - [Donating the Model Context Protocol and establishing the Agentic AI Foundation: Anthropic](https://www.anthropic.com/news/donating-the-model-context-protocol-and-establishing-of-the-agentic-ai-foundation) - [DORA 2025: State of AI-assisted Software Development](https://dora.dev/dora-report-2025/) - [DORA AI Capabilities Model report](https://dora.dev/ai/capabilities-model/report/) - [DORA Insights](https://dora.dev/insights/) - [DORA research on AI](https://dora.dev/research/ai/) - [DORA: Balancing AI tensions: moving from adoption to effective SDLC use](https://dora.dev/insights/balancing-ai-tensions/) - [Effective context engineering for AI agents: Anthropic](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents) - [en.wikipedia.org](https://en.wikipedia.org/wiki/Figure_AI) - [Enterprise AI Operating Model: Hub-and-Spoke, Federated, or Centralized?](https://aiassemblylines.com/resources/ai-initiatives-operating-model) - [EU agrees Digital Omnibus deal to simplify AI rules: White & Case](https://www.whitecase.com/insight-alert/eu-agrees-digital-omnibus-deal-simplify-ai-rules) - [EU AI Act implementation timeline: AI Act Service Desk](https://ai-act-service-desk.ec.europa.eu/en/ai-act/timeline/timeline-implementation-eu-ai-act) - [Explainable AI in Chat Interfaces: Nielsen Norman Group](https://www.nngroup.com/articles/explainable-ai/) - [Factory.ai: From coding agents to software factories](https://factory.ai/news/software-factory) - [Fine-tuning (OpenAI Developers guide)](https://developers.openai.com/learn/fine-tuning) - [FinOps for AI Overview: FinOps Foundation](https://www.finops.org/wg/finops-for-ai-overview/) - [Forrester](https://www.forrester.com/blogs/announcing-the-evaluation-of-the-adaptive-process-orchestration-market/) - [Gartner](https://www.gartner.com/en/newsroom/press-releases/2025-06-25-gartner-predicts-over-40-percent-of-agentic-ai-projects-will-be-canceled-by-end-of-2027) - [Gartner Predicts 40% of Enterprise Apps Will Feature Task-Specific AI Agents by 2026](https://www.gartner.com/en/newsroom/press-releases/2025-08-26-gartner-predicts-40-percent-of-enterprise-apps-will-feature-task-specific-ai-agents-by-2026-up-from-less-than-5-percent-in-2025) - [gartner.com](https://www.gartner.com/en/newsroom/press-releases/2023-03-01-gartner-says-20-percent-of-inbound-customer-service-contact-volume-will-come-from-machine-customers-by-2026) - [Gemini 3: Introducing the latest Gemini AI model (Google)](https://blog.google/products-and-platforms/products/gemini/gemini-3/) - [Generative AI at Work: Brynjolfsson, Li, Raymond (NBER Working Paper 31161)](https://www.nber.org/papers/w31161) - [Generative Artificial Intelligence and Copyright Law: Congressional Research Service](https://www.congress.gov/crs-product/LSB10922) - [GitClear: AI Copilot Code Quality 2025 research](https://www.gitclear.com/ai_assistant_code_quality_2025_research) - [GitHub MCP Exploited: Accessing private repositories via MCP](https://invariantlabs.ai/blog/mcp-github-vulnerability) - [GitHub Octoverse 2025](https://github.blog/news-insights/octoverse/octoverse-a-new-developer-joins-github-every-second-as-ai-leads-typescript-to-1/) - [GitHub Octoverse 2025](https://github.blog/news-insights/octoverse/) - [Glean](https://docs.glean.com/administration/search/faq) - [Glean](https://developers.glean.com/api-info/indexing/documents/permissions) - [Google Cloud](https://docs.cloud.google.com/gemini-enterprise-agent-platform/agents/use-deep-research) - [Google: NotebookLM Adds Deep Research](https://blog.google/innovation-and-ai/models-and-research/google-labs/notebooklm-deep-research-file-types/) - [GPT-5.1 System Card Addendum (OpenAI)](https://openai.com/index/gpt-5-system-card-addendum-gpt-5-1/) - [GraphRAG: Unlocking LLM discovery on narrative private data (Microsoft Research)](https://www.microsoft.com/en-us/research/blog/graphrag-unlocking-llm-discovery-on-narrative-private-data/) - [HHEM v2: A New and Improved Factual Consistency Scoring Model: Vectara](https://www.vectara.com/blog/hhem-v2-a-new-and-improved-factual-consistency-scoring-model) - [How we built our multi-agent research system: Anthropic](https://www.claude.com/blog/building-multi-agent-systems-when-and-how-to-use-them) - [Hybrid search (Weaviate Documentation)](https://weaviate.io/developers/weaviate/concepts/search/hybrid-search) - [Identifying Token Costs Hiding in Your Agentic Loop: MachineLearningMastery](https://machinelearningmastery.com/identifying-token-costs-hiding-in-your-agentic-loop/) - [InfoQ: Agentic fitness functions: extending evolutionary architecture beyond deterministic rules](https://www.infoq.com/articles/agentic-fitness-functions-evolutionary-architecture/) - [InfoWorld: How Google is using LLMs for complex internal code migrations](https://www.infoworld.com/article/3804552/heres-how-google-is-using-llms-for-complex-internal-code-migrations.html) - [Inside the LLM Call: GenAI Observability with OpenTelemetry: OpenTelemetry Blog](https://opentelemetry.io/blog/2026/genai-observability/) - [Introducing Claude Opus 4.5 (Anthropic)](https://www.anthropic.com/news/claude-opus-4-5) - [Introducing the Model Context Protocol (Anthropic)](https://www.anthropic.com/news/model-context-protocol) - [Introduction: Model Context Protocol](https://modelcontextprotocol.io/introduction) - [ISO/IEC 42001 explained](https://www.iso.org/home/insights-news/resources/iso-42001-explained-what-it-is.html) - [ISO/IEC 42001:2023: AI management systems](https://www.iso.org/standard/42001) - [ISO/IEC 42001:2023: Microsoft compliance overview](https://learn.microsoft.com/en-us/compliance/regulatory/offering-iso-42001) - [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena (arXiv)](https://arxiv.org/abs/2306.05685) - [learn.microsoft.com](https://learn.microsoft.com/en-us/entra/agent-id/what-is-microsoft-entra-agent-id) - [Least privilege for AI agents with Microsoft Entra Agent ID](https://learn.microsoft.com/en-us/security/zero-trust/sfi/least-privilege-for-ai-agents) - [Least privilege for AI agents: Identity, access, and tool binding](https://www.microsoft.com/en-us/security/blog/2026/07/16/least-privilege-for-ai-agents-identity-access-and-tool-binding/) - [Levels of Autonomy for AI Agents: Knight First Amendment Institute](https://knightcolumbia.org/content/levels-of-autonomy-for-ai-agents-1) - [Leveraging model distillation to fine-tune a model (OpenAI Cookbook)](https://developers.openai.com/cookbook/examples/leveraging_model_distillation_to_fine-tune_a_model) - [Llama 4 Community License Agreement](https://www.llama.com/llama4/license/) - [LLM Agent Evaluation Metrics: Tool Calling, Task Completion, Reasoning, and Trace-Based Evals: Confident AI](https://www.confident-ai.com/blog/llm-agent-evaluation-complete-guide) - [LLM Evaluation: Best Practices and Methods: Databricks Engineering Blog](https://www.databricks.com/blog/best-practices-and-methods-llm-evaluation) - [LLM Routing and Model Cascades: How to Cut AI Costs Without Sacrificing Quality](https://tianpan.co/blog/2025-11-03-llm-routing-model-cascades) - [LLMOps Guide: Build Fast, Cost-Effective LLM Apps: Redis Engineering Blog](https://redis.io/blog/large-language-model-operations-guide/) - [MCP Authorization specification](https://modelcontextprotocol.info/specification/2025-11-25/) - [MCP Security Notification: Tool Poisoning Attacks: Invariant Labs](https://invariantlabs.ai/blog/mcp-security-notification-tool-poisoning-attacks) - [MCP Tool Poisoning: OWASP Foundation](https://owasp.org/www-community/attacks/MCP_Tool_Poisoning) - [Measuring AI agent autonomy in practice: Anthropic](https://www.anthropic.com/research/measuring-agent-autonomy) - [MemGPT: Towards LLMs as Operating Systems (arXiv)](https://arxiv.org/abs/2310.08560) - [Memory for Claude Managed Agents (Anthropic)](https://claude.com/blog/claude-managed-agents-memory) - [merics.org](https://merics.org/sites/default/files/2026-04/MER-RZ-Report-Embodied-AI-260422-Web.pdf) - [Meta's Llama license is still not Open Source (Open Source Initiative)](https://opensource.org/blog/metas-llama-license-is-still-not-open-source) - [METR: Measuring the impact of AI on experienced open-source developer productivity](https://metr.org) - [Microsoft Agent 365 Overview](https://learn.microsoft.com/en-us/microsoft-agent-365/overview) - [Microsoft GraphRAG project page](https://microsoft.github.io/graphrag/) - [Microsoft Learn: Overview of Process Mining in Power Automate](https://learn.microsoft.com/en-us/power-automate/process-mining-overview) - [Microsoft Support: Use Researcher in Copilot Notebooks](https://support.microsoft.com/en-us/microsoft-365-copilot/use-researcher-in-microsoft-365-copilot-notebooks) - [Microsoft: Catch Up on Meetings with Copilot in Teams](https://support.microsoft.com/en-us/teams/copilot/catch-up-on-meetings-with-microsoft-365-copilot-in-teams) - [Migrating Code At Scale With LLMs At Google (arXiv 2504.09691, FSE 2025)](https://arxiv.org/abs/2504.09691) - [MIT NANDA](https://www.media.mit.edu/projects/mit-nanda/overview/) - [MIT report: 95% of generative AI pilots at companies are failing](https://finance.yahoo.com/news/mit-report-95-generative-ai-105412686.html) - [Model router for Microsoft Foundry: concepts](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-router) - [n8n Docs](https://docs.n8n.io/) - [NIST AI 600-1: Artificial Intelligence Risk Management Framework: Generative AI Profile](https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf) - [NIST AI RMF Playbook](https://airc.nist.gov/AI_RMF_Knowledge_Base/Playbook) - [NSA/CISA: Model Context Protocol (MCP) Security](https://www.nsa.gov/Portals/75/documents/Cybersecurity/CSI_MCP_SECURITY.pdf) - [One Year of MCP (Model Context Protocol blog)](https://blog.modelcontextprotocol.io/posts/2025-11-25-first-mcp-anniversary/) - [OpenAI](https://openai.com/index/introducing-deep-research/) - [OpenTelemetry GenAI Semantic Conventions: MLflow documentation](https://mlflow.org/docs/latest/genai/tracing/opentelemetry/genai-semconv/) - [OSWorld 2.0 (arXiv 2606.29537)](https://arxiv.org/html/2606.29537v1) - [Overview of model routing: Google Cloud API Gateway](https://docs.cloud.google.com/api-gateway/docs/model-routing-overview) - [OWASP Gen AI Security Project: Resources](https://genai.owasp.org/resources/) - [OWASP LLM01:2025 Prompt Injection](https://genai.owasp.org/llmrisk/llm01-prompt-injection/) - [OWASP LLM04:2025 Data and Model Poisoning](https://genai.owasp.org/llmrisk/llm04-data-and-model-poisoning/) - [OWASP LLM05:2025 Improper Output Handling](https://genai.owasp.org/llmrisk/llm05-supply-chain-vulnerabilities/) - [OWASP LLM06:2025 Excessive Agency](https://genai.owasp.org/llmrisk/llm06-sensitive-information-disclosure/) - [OWASP LLM08:2025 Vector and Embedding Weaknesses](https://genai.owasp.org/llmrisk/llm08-vector-and-embedding-weaknesses/) - [OWASP Top 10 for LLM Applications 2025](https://genai.owasp.org/llm-top-10/) - [OWASP Top 10 for LLM Applications 2025](https://genai.owasp.org/resource/owasp-top-10-for-llm-applications-2025/) - [pgvector (GitHub)](https://github.com/pgvector/pgvector) - [Prompt engineering best practices for 2026 (Anthropic)](https://claude.com/blog/best-practices-for-prompt-engineering) - [Prompt injection: Wikipedia](https://en.wikipedia.org/wiki/Prompt_injection) - [RAG Security Cheat Sheet (OWASP)](https://cheatsheetseries.owasp.org/cheatsheets/RAG_Security_Cheat_Sheet.html) - [RAG with Permissions (Supabase Docs)](https://supabase.com/docs/guides/ai/rag-with-permissions) - [RAGAS: Automated Evaluation of Retrieval Augmented Generation (arXiv)](https://arxiv.org/abs/2309.15217) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://react-lm.github.io/) - [Regulation (EU) 2024/1689 (EUR-Lex, official text)](https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:32024R1689) - [Remove PII from conversations by using sensitive information filters](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-sensitive-filters.html) - [Replay: reconstructing an agent action from the audit log: Deixic](https://www.deixic.com/blog/replay-reconstructing-an-agent-action) - [research.google](https://research.google/blog/generative-ui-a-rich-custom-visual-interactive-user-experience-for-any-prompt/) - [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (Lewis et al., 2020)](https://arxiv.org/abs/2005.11401) - [Rising AI Adoption Spurs Workforce Changes (Gallup)](https://www.gallup.com/workplace/704225/rising-adoption-spurs-workforce-changes.aspx) - [Safety and content filters: Vertex AI](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/multimodal/configure-safety-filters) - [salesforce.com](https://www.salesforce.com/agentforce/agentexchange/) - [salesforce.com](https://www.salesforce.com/news/stories/new-collaborative-workforce-humans-agents/) - [Salesforce: Agentforce Developer Guide: Get Started](https://developer.salesforce.com/docs/ai/agentforce/guide/get-started.html) - [Securing Agentic Applications Guide 1.0](https://genai.owasp.org/resource/securing-agentic-applications-guide-1-0/) - [Security Degradation in Iterative AI Code Generation (arXiv 2506.11022, IEEE ISTAS 2025)](https://arxiv.org/html/2506.11022v2) - [Security, Guardrails, and Observability in Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/security.html) - [Shadow deployment vs. canary release of machine learning models](https://mikulskibartosz.name/shadow-deployment-vs-canary-release) - [Simon Willison's prompt-injection archive](https://simonwillison.net/tags/prompt-injection/) - [SPIFFE: Securing the identity of agentic AI and non-human actors](https://www.hashicorp.com/en/blog/spiffe-securing-the-identity-of-agentic-ai-and-non-human-actors) - [State of UX 2026: Nielsen Norman Group](https://www.nngroup.com/articles/state-of-ux-2026/) - [stripe.com](https://stripe.com/newsroom/news/stripe-openai-instant-checkout) - [Structured Outputs (OpenAI API)](https://platform.openai.com/docs/guides/structured-outputs/how-to-use) - [Team Topologies as the "infrastructure for agency" with AI](https://teamtopologies.com/keynote-talks/team-topologies-as-the-infrastructure-for-agency-with-ai) - [Team Topologies: the book's site](https://teamtopologies.com/book) - [Techzine](https://www.techzine.eu/blogs/applications/135190/sap-presents-15-joule-agents-for-finance-hr-and-supply-chain/) - [The 2026 MCP Roadmap: Model Context Protocol Blog](https://blog.modelcontextprotocol.io/posts/2026-mcp-roadmap/) - [The AI Champion role (OpenAI Academy)](https://academy.openai.com/public/clubs/champions-ecqup/resources/the-ai-champion-role) - [The lethal trifecta for AI agents](https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/) - [The New York Times v. Microsoft and OpenAI: case background and status](https://en.wikipedia.org/wiki/The_New_York_Times_v._Microsoft_and_OpenAI) - [The Non-Human Identity Governance Vacuum](https://labs.cloudsecurityalliance.org/research/csa-whitepaper-nonhuman-identity-agentic-ai-governance-v1-cs/) - [The Register, "AI coding tools make developers slower, study finds"](https://www.theregister.com/2025/07/11/ai_code_tools_slow_down/) - [The State of AI: Global Survey 2025 (McKinsey)](https://www.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai) - [The Vulnerable MCP Project](https://vulnerablemcp.info/) - [Token Economics: The Atomic Unit of AI Value: FinOps Foundation](https://www.finops.org/insights/token-economics-the-atomic-unit-of-ai-value/) - [Tool use with Claude: Claude Platform Docs](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) - [TRAJECT-Bench: A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use (arXiv)](https://arxiv.org/abs/2510.04550) - [UiPath](https://docs.uipath.com/agents/automation-cloud/latest/user-guide/about-agents) - [UiPath: What is Agentic Orchestration?](https://www.uipath.com/ai/what-is-agentic-orchestration) - [Understanding intelligent prompt routing in Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-routing.html) - [Understanding the context window (Anthropic docs)](https://docs.anthropic.com/en/docs/build-with-claude/context-windows) - [US Supreme Court declines to consider whether AI alone can create copyrighted works: Morgan Lewis](https://www.morganlewis.com/pubs/2026/03/us-supreme-court-declines-to-consider-whether-ai-alone-can-create-copyrighted-works) - [vectara/hallucination-leaderboard (GitHub)](https://github.com/vectara/hallucination-leaderboard) - [When Should We Trust AI? Magic-8-Ball Thinking and AI Hallucinations: Nielsen Norman Group](https://www.nngroup.com/articles/ai-magic-8-ball/) - [Workato: Agentic (docs)](https://docs.workato.com/agentic/agentic.html)