c16
c16 / wf5.m1 - Agent Control Plane — hi-fi (wf5.m1) / Effectiveness·control-plane-v1/effectiveness·draft

Engineering · Effectiveness

Is it working? — are agents accomplishing the task

Fleet success 89% across 1212 signal-bearing tasks — but only 63% of agents emit a measured signal (2 inferred, 1 dark). 8% of tasks needed a human. Biggest lift: fix support-copilot first (~56 failed tasks).

Outcome signal — known vs guessed

Outcome signals need run-outcome instrumentation. 5/8 agents emit a measured signal; 2 are inferred from retries / abandons / errors; 1 are dark (shadow). Values are projected where signal ≠ measured — treat inferred rates as directional, not exact.

5 measured2 inferred1 dark
89%

fleet success rate

1212 tasks, signal-bearing

8%

needed a human

intervention / handoff

13%

rework rate

retried / redone

86

quality score

63% measured coverage

Fleet success rate — 6-week trend

projected · signal-bearing

Up +10 pts over 6 weeks (79% → 89%), still climbing this week.

−6w: 79%now: 89%

Fix this first — by failed-task volume

tasks × (1 − success) · biggest absolute lift

Where the most goals are actually missed — a high-volume agent at 82% can fail more tasks than a low-volume one at 48%. Fixing the top row moves the most outcomes.

By workflow

Workflow
Tasks
Success
Intervene
data-sync
measured
54097%2%
support-triage
measured
31082%12%
code-review
measured
26092%7%
content-gen
inferred
6448%34%
infra-ops
inferred
3866%21%

By agent

Agent
Tasks
Success
Intervene
Quality
support-copilot
measured
31082%12%79
marketing-gpt
inferred
6448%34%
data-pipeline-agent
measured
54097%2%91
Codex CLI
inferred
3866%21%
Claude Code
measured
14293%6%88
Cursor
measured
9690%8%84
Claude Desktop
measured
2295%5%90
Zed Agent
none

This is task success, not speed. Latency and cost say how fast and cheap a model is; this asks whether the agent actually accomplished the goal. Latency & cost live in Performance →.

Derived: effectivenessCoverage · fleetEffectiveness · lowestEffectiveness — from app/data/c16-fleet.ts (proposed run-outcome signal; measured / inferred / none provenance per agent).