Question 1

What is Agentic Engineering Intelligence?

Accepted Answer

Agentic Engineering Intelligence measures the combined work of human engineers and their AI agents — capturing where time actually goes, every agent run and token cost, at the source, across all repos, and tying it to shipped output.

Question 2

How is DevClocked different from Waydev?

Accepted Answer

Waydev reads your Git history and infers which commits were AI. That's the artifact after it lands. We sit in the work session and capture it as it happens — real hours, every agent run, the tokens — including everything that never became a commit. They measure the code; we measure the working. And they're top-down for managers, while we land bottom-up with the developer — which is the data they can't get.

Question 3

How is DevClocked different from Tokscale?

Accepted Answer

Tokscale tells you what you spent. We tell you what you shipped for it. Measuring spend is the easy half and it's free; tying it to real human hours and shipped output — the leverage — is the hard half, and the part that matters.

Question 4

How is DevClocked different from Jellyfish or LinearB?

Accepted Answer

Same data limit as Waydev — they're built on Git and pull requests about humans, with AI bolted on as adoption stats. We're built on the work session itself, captured at the source.

Question 5

How is DevClocked different from Langfuse or agent observability?

Accepted Answer

Different end of the pipe. Langfuse traces what the model does, for people building agents. We measure the output and cost of people using them to ship software.

Question 6

What is the Leverage Score?

Accepted Answer

Your Leverage Score is the ratio of total shipped output, human and agent combined, to the human hours you invested. It shows whether AI is acting as a true force multiplier or mostly adding cost. DevClocked calculates it automatically from work blocks, agent sessions, and commit activity.

Question 7

How does agent session capture work?

Accepted Answer

When you run Claude Code, Cursor, Windsurf, or other AI coding tools, DevClocked captures the full session: duration, tokens in and out, cost, and project attribution. Agent sessions appear as their own work blocks beside manual coding sessions so you can see orchestration vs hands-on work clearly.

Question 8

What token and cost data does DevClocked track?

Accepted Answer

DevClocked tracks token usage across your AI tools and maps it to projects and sessions. You can see total tokens per month, cost per shipped feature, and agent efficiency ratios to understand whether spend is compounding output or being lost to context resets and low-value runs.

Mac App + Sidecar Guide

Main Mac App vs Sidecar

What Each Component Does

How Tracking Works

How to Use It Day to Day

Best Practices for Accurate Data

Troubleshooting