Signals & Insights
Signals & Insights
Planwright surfaces two views of your agentic workflow: Signals at the project level — a time-windowed status report showing what shipped, what's at risk, and how agents performed — and Insights at the workspace level, with longer-arc metrics on direction quality, leverage, and team throughput.
Every metric is a signal about human-agent collaboration, not just about what the agent produced. Low first-pass rate, high clarity flags, long review times — these numbers say as much about how well humans are directing agents as they do about agent performance.
Delivery health →
Signals · ProjectPass rate, cycle time, and stage latency tell you where time goes and whether objectives are ready to run.
First-pass acceptance rate →
Insights · WorkspaceThe flagship metric for objective quality — and for the quality of human direction.
Human leverage →
Insights · WorkspaceHow much agent execution is produced per human director. Low leverage is a direction problem, not an agent problem.
Strategic visibility →
Signals · ProjectWhether what the team is actually shipping matches what they said they would ship.
Risk signals →
Signals · ProjectEarly warning indicators that let teams intervene before the audit trail fills with rework.
Audit chain health →
Signals · ProjectThe integrity indicator for every state transition in the system.
Intent Fidelity →
Insights · WorkspaceWhether completed work matches what was actually asked for — using the agent's own account of its work at handoff, not an automated computation. When a strategic bucket's average drift creeps up, the next agent claiming a same-bucket objective sees a stay-scoped advisory before writing any code.
Codebase Fragility →
Signals · ProjectAgent-iteration count mapped onto your repo's directory tree — a fragility signal GitHub's churn metrics can't show, with drill-in to the objectives behind any file or module.