mirror of
https://github.com/hanzoai/insights.git
synced 2026-11-03 00:52:32 +00:00
zeekay
1b367e2b62
The tree was a debranded snapshot of upstream taken around 2026-02-20, and upstream has moved about five months since. This replaces it with upstream master, mechanically re-derived: bin/debrand does the rename, and the pipeline and squashed migrations are restored from the shipped tree. Not a merge. The previous import replaced the tree wholesale in a single commit, so there is no shared content history to merge against. Reproducing the rename on the new tree is what actually converges. What survives: .hanzo/workflows, the Dockerfiles and bin/docker* entrypoints, compose files, LLM.md, and insights/migrations. The squashed initial migration is load-bearing — the live database records it by name, so upstream's ~918 individual migrations cannot come back. Nine products are dropped as unreferenced. Twenty-one more that we do not run are kept anyway because the core app still imports them; unpicking those is a refactor and does not belong in a rebase. This base does not build yet, and the reasons are not in the rename: upstream now wants Python 3.13.13 against our 3.12.12 and Django 5.2 against our 4.2, and the dependency manifests still name upstream packages that we republish under our own names. Those are decisions, not renames.
1.9 KiB
1.9 KiB
AI observability skills
Agent skills for the AI observability product.
Built by insightscli build:skills and installed into sandbox containers for background agents.
Also available to Claude Code / Codex via insightscli sync:skill.
Skills
- exploring-llm-traces — how to query, inspect, and debug LLM traces via MCP tools.
Covers the
$ai_*event schema, where message content lives (eventsvs theai_eventstable), content detail levels, and step-by-step debugging workflows. - exploring-llm-clusters — how to investigate AI observability clustering results, compare cluster behavior, compute metrics, and drill into individual traces.
- exploring-llm-costs — how to investigate LLM spend: total cost, breakdowns by model/provider/user/trace/custom dimension, token and cache economics, cost regressions, and materializing cost insights, dashboards, and alerts.
- analyzing-expensive-users — how to analyze the most expensive users in AI observability, compare them against baseline usage, inspect trace/model/token/cache patterns, and explain what drives their spend.
- exploring-llm-evaluations — how to manage and investigate AI observability
evaluations (
script,llm_judge, andsentiment), run them on specific generations, query individual results, and generate AI-powered summaries of pass/fail/N/A patterns for boolean evaluations.
Skills for managing skills themselves (skills-store, working-with-skills) now live in
the standalone Skills product — see products/skills/skills/.
Adding a new skill
insightscli init:skill -- --product ai_observability --name my-new-skill
See products/insights_ai/scripts/build_skills.py for the build pipeline
and AGENTS.md for conventions.
Local testing
insightscli sync:skill -- --name exploring-llm-traces
This copies the built skill to .agents/skills/ for Claude Code to discover.