exploring-llm-traces
Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs. Also use when raw SQL/HogQL against events.properties.$ai_input / $ai_output_choices returns empty — message content lives only on the dedicated posthog.ai_events table.
Pinned to revision 4e8964e24a5a, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/exploring-llm-traces/SKILL.md
- skills/exploring-llm-traces/references/events-and-properties.md
- skills/exploring-llm-traces/references/example-llm-trace.md
- skills/exploring-llm-traces/references/example-llm-traces-list.md
- skills/exploring-llm-traces/scripts/extract_conversation.py
- skills/exploring-llm-traces/scripts/extract_span.py
- skills/exploring-llm-traces/scripts/print_summary.py
- skills/exploring-llm-traces/scripts/print_timeline.py
- skills/exploring-llm-traces/scripts/search_traces.py
- skills/exploring-llm-traces/scripts/show_structure.py
Every link opens the file at its source, pinned to the revision this page describes.