Devology attributes every line of code to AI or human, joins that with what each AI tool actually costs, and tells you what your $/PR merged, $/story point, and bug ratelook like — across Cursor, Copilot, Claude Code, Codex, and Windsurf.
// Co-Authored-By: Claude <noreply@anthropic.com>import { sleep } from './utils';export async function retryWithBackoff<T>( fn: () => Promise<T>, opts = { max: 5, base: 200, cap: 8000 }): Promise<T> { let attempt = 0; while (true) { try { return await fn(); } catch (err) { if (++attempt >= opts.max) throw err; const delay = Math.min(opts.cap, opts.base * 2**attempt); await sleep(delay + Math.random()*100); } }}
You're paying for Cursor, Copilot, Claude Code, Codex, and Windsurf seats and tokens. But none of that data is joined to your repo. So when the CFO asks "is this working?" the honest answer is "we don't know — it feels faster."
Devology closes the loop. We attribute every commit, line, and PR to a human or an AI assistant — then divide the actual token bill by what shipped.
Devology ingests AI tool usage logs, joins them with your Git history, and produces a single picture of what AI is actually doing in your codebase. No judgment, no slop-shaming — just the numbers.
We don't ask your engineers to label anything. Devology reads provenance directly from three independent signals and reconciles them into a single confidence-scored verdict per line.
We integrate read-only with Cursor, Copilot, Claude Code, Codex, and Windsurf. Every prompt, completion, and accepted suggestion comes with author, timestamp, model, and exact token count.
Every commit is parsed for Co-Authored-By trailers (Claude, Copilot, Aider, …) plus stylometric fingerprints — keystroke cadence, comment density, function arity — that flag AI authorship even when trailers are stripped.
When a PR opens, Devology classifies each hunk: AI-authored, AI-assisted (edited by human), or human-only — and ships an inline label so reviewers know what they're reading.
Direct integrations with the five biggest AI coding sources, plus a generic webhook for in-house assistants and CI bots.
Token spend and PR throughput are easy to count separately. Joining them is the hard part. Devology does it per author, per team, per project, every day.
Devology posts a GitHub / GitLab check on each PR with the provenance breakdown, the token cost, and the model used. Reviewers see what they're reading. Managers see what was actually shipped.
We were spending almost $90k a quarter on Copilot, Cursor, and Claude Code seats. The board kept asking what we were getting back. Devology gave us the first honest number — $71 per merged PR, 1.06× bug rate vs human. That ended the debate.
"Finance finally stopped treating AI tools like a marketing line item. We can show $/PR and $/story point on the same page as Slack and Notion."
"The PR check is the killer feature. Reviewers know what's AI before they start reading. Our review time on AI-heavy PRs dropped 31%."
Per seat. Predictable. No clawback if your team uses AI well.
Up to 10 engineers · single repo
Start freeUp to 500 engineers · unlimited repos
Book a demoSelf-hosted or VPC · unlimited everything
Talk to sales