Dashboard

Read-only

Agent Performance Intelligence

Deterministic comparison of AI coding agents. No vibes — just math. Every metric is grounded in Intent-to-Outcome linkage.

Executive Summary

Claude Code is the top-performing agent with 89% first-pass success across 54 sessions, contributing 55% of successful executions.

Cursor generates 44% of risk events but only 25% of successful executions. Risk-to-productivity ratio: 1.8x.

Claude Code leads knowledge growth with 42% of promoted patterns — building reusable institutional memory.

Claude Code has the lowest rework rate at 7%, indicating the most stable first-pass behavior.

Top Agent
Claude Code
Highest productivity contribution
Highest Risk
Cursor
Highest risk concentration
Total Sessions
88
Across all agents

Agent Scorecard

AgentFirst-Pass SuccessReworkRiskProductivityPatternsSessionsAttribution
Claude Code
TOP
89%
7%32%55%42%54DETERMINISTIC
Cursor
RISK
76%
14%44%25%33%29DETERMINISTIC
Codex
80%
20%24%5%25%5PARTIAL

Proof of Capability

Every metric above is tagged with its attribution quality. This isn't AI guesswork — it's auditable fact derived from Intent-to-Outcome linkage.

DETERMINISTIC

Agent explicitly identified. Full provenance chain from task to outcome.

PARTIAL

Agent inferred from environment signals. Confidence above 50%.

ADVISORY

Attribution quality below threshold. Data shown but flagged as low-confidence.