Agent Insights
Overview

Agent Insights Beta

Visibility into every agent run

Your org bought Claude Code, Cursor, and Codex seats. Adoption dashboards from those tools tell you who logged in. They don't tell you whether a session ended in shipped code or three retries and a dead end. Agent Insights aggregates session-level behavior across every agent your team uses — into one dashboard that shows adoption, spend, and effectiveness, without anyone reading a single transcript.

This is a coaching tool, not a surveillance one — Entelligence never sends raw session transcripts, only computed metrics (token counts, tool-call patterns, retry rates, and similar signals).


🎥 Video demo — coming soon

Tour of team health, spend, and per-member breakdowns


Adoption isn't the same question as "is it working"

What a seat-count dashboard tells you

12 of 15 engineers used Claude Code this week.

What Agent Insights tells you

Those 12 had a 40% retry rate on one project this week — up from 10% last week — which is where the friction actually is.

What's in the dashboard

TabWhat it shows
OverviewTeam health at a glance — adoption, activity trends, and a session activity map. Per-member breakdown for drilling into any individual's usage. Coding-behavior signals like tool-call efficiency and retry rates. Skill/command usage across the team. Spend patterns across connected agents.
BudgetProject-level budgets versus actual spend, with targets you can set per project.
OutcomesWhere agent-driven work actually lands — spend-to-production tracking by outcome category, plus activity themes and heatmaps showing where usage concentrates.
Entelligence WrappedA personal, shareable year-in-review card per developer — usage patterns, wins, and coding persona — exportable as a standalone page.

Supported agents

Claude Code, Cursor, Codex, GitHub Copilot, Gemini, Aider, and Windsurf.

How data gets in — and what never leaves the machine

Agent Insights runs on the same engine behind the open-source cinsights project, driven from each developer's machine via entelligence insights in the CLI. It reads session files that already exist locally (~/.claude, ~/.codex) — or connects through Entire.io for cross-machine/cross-agent coverage, or Arize Phoenix for centralized trace observability — scores them locally, and syncs only the computed result up to your org's dashboard.

Sent to your dashboardNever leaves the developer's machine
Token countsRaw prompts
Tool-call names and countsRaw agent responses
Efficiency and retry scoresTool input/output (where code, commands, or secrets could appear)

This isn't a policy promise — the sync mechanism is built around an explicit allow-list of computed fields, so there's nothing to accidentally over-share.

What "efficiency" and "friction" actually measure

Rather than lines of code or session duration — numbers that go up whether a session went well or in circles — Agent Insights tracks behavioral signals that actually correlate with whether an agent session worked:

SignalWhat it catches
Tool-call efficiencyPurposeful tool use vs. flailing — how many calls it takes to actually get something done
Reads-before-editsWhether context gets gathered before changes are made, or an agent edits blind
Retry rateHow often a task needs multiple attempts before succeeding
Context pressureEarly signs a conversation is running up against a model's context limit

These roll up into per-developer behavior patterns and team-wide health tiles — framed as coaching signals ("here's where the friction is"), not individual performance scores.

💡

Some sections (like detailed outcome-to-production tracking) are still rolling out during the beta — you may see a "coming soon" state on parts of the dashboard depending on your org.

See Setup to get your team connected.