Guides
- Audit log for AG2: signing ConversableAgent's safeguard hooks
- Audit log for Agno agents: recording tool calls and agent runs
- Audit trail for AI agents: what to record and how to make it hold up
- Audit log for AutoGen and AG2 agents: recording multi-agent conversations
- Audit log for Amazon Bedrock Agents: turning InvokeAgent traces into evidence
- Audit log for Azure AI Foundry Agent Service
- Audit log for Claude Code sessions: hooks that record and block tool calls
- Audit log for CrewAI: tracing multi-agent crews for compliance
- Audit log for Dify apps: what the console shows and what an auditor needs
- A DPO checklist for AI agents: 20 questions before an agent goes live
- Audit log for DSPy programs: recording every LM call a module makes
- EU AI Act Annex III: the high-risk use case list, explained
- EU AI Act Annex IV: what goes in the technical documentation
- EU AI Act Article 10 for LLM agents: data governance when you did not train the model
- EU AI Act Article 101: fines for GPAI model providers
- EU AI Act Article 11 and Annex IV: technical documentation for AI agents
- EU AI Act Article 12: what 'automatic logging' means for AI agents
- EU AI Act Article 13: transparency and instructions for use, including how deployers read the logs
- EU AI Act Article 14: turning human oversight into evidence for AI agents
- EU AI Act Article 15: accuracy, robustness and cybersecurity for LLM agents
- EU AI Act Article 16: the full list of provider obligations
- EU AI Act Article 17: quality management system evidence for AI agents
- EU AI Act Article 18: keeping documentation for ten years
- EU AI Act Article 19: how long providers must keep AI system logs
- EU AI Act Article 2: who is in scope, including outside the EU
- EU AI Act Article 20: corrective actions and duty of information
- EU AI Act Article 22: authorised representatives for non-EU providers
- EU AI Act Article 23: importer obligations for high-risk AI systems
- EU AI Act Article 25: when a distributor or deployer becomes a provider
- EU AI Act Article 26: what deployers of high-risk AI agents must do
- EU AI Act Article 27: fundamental rights impact assessment for AI agents
- EU AI Act Article 3: provider vs. deployer, and why it changes your duties
- EU AI Act Article 4: AI literacy and the evidence you can keep
- EU AI Act Article 43: which conformity assessment route applies
- EU AI Act Article 47: the EU declaration of conformity
- EU AI Act Article 49: registering in the EU database
- EU AI Act Article 5: prohibited practices and how to show an agent avoids them
- EU AI Act Article 50: transparency obligations for chatbots and generated content
- EU AI Act Article 53: obligations for providers of general-purpose AI models
- EU AI Act Article 55: extra duties for GPAI models with systemic risk
- EU AI Act Article 6: is your AI agent high-risk?
- EU AI Act Article 72: post-market monitoring for AI agents
- EU AI Act Article 73: serious incident reporting and the logs you need in the first 48 hours
- EU AI Act Article 74: market surveillance authority powers
- EU AI Act Article 8: how compliance with Chapter III is judged
- EU AI Act Article 86: the right to an explanation of individual decisions
- EU AI Act Article 9: a risk management system for AI agents that produces evidence
- EU AI Act Article 99: the penalty tiers
- EU AI Act deadlines after the Digital Omnibus: what moved, what did not
- EU AI Act log retention: the six-month rule for deployers (Art. 26 and 19)
- Arize Phoenix to audit evidence: attest the OTLP traces you already collect
- Helicone logs vs audit evidence: add an attested OTLP trail next to your proxy
- From Langfuse to signed audit evidence: export your OTLP traces and attest them
- LangSmith traces as audit evidence: keep an OTLP copy and get it countersigned
- Audit log for Flowise chatflows: the LangChain layer underneath is your hook
- GDPR and AI agent logs: keeping traceability without keeping everything
- Audit log for Google Agent Development Kit (ADK) agents
- Hash chain vs. WORM storage for AI logs: which one do you need?
- Audit log for Haystack pipelines: recording retrieval, generation and tool calls
- ISO/IEC 42001 evidence for AI agents: what the auditor will ask to see
- Audit log for LangChain agents: a callback handler that records every call, signed
- Audit log for LangGraph agents: signing every node, edge and tool call
- Audit log for LiteLLM: proxy and SDK, both routes to a signed ledger
- Audit log for LlamaIndex agents: record LLM and tool calls in a tamper-evident ledger
- Audit log for Mastra agents
- Audit log for MCP servers: signing every tool call at the source
- Audit log for n8n AI Agent workflows: closing the gap in the execution log
- NIST AI RMF for AI agents: turning Govern, Map, Measure, Manage into records
- Audit log for the OpenAI Agents SDK: a trace processor that signs every span
- OpenTelemetry GenAI traces as compliance evidence: what they cover and what they miss
- Audit log for Pydantic AI agents
- Audit log for Semantic Kernel agents: from OTel traces to a signed ledger
- Audit log for smolagents: signing every step of a code-writing agent
- Tamper-evident logs: hash chains and signatures, explained with one changed word
- Audit log for Vercel AI SDK apps
Also: free tools · docs.