How Evinova drafted regulated GxP documentation and fixed bugs with Devin
Evinova, an AstraZeneca clinical-trial technology company, used Devin to draft GxP documents from Jira and source code and to run a scheduled bug-fixing playbook. Senior engineers moved from writing these documents to reviewing them.
The problem
Under GxP rules, documents such as User Requirement Specifications took many hours of coordination between engineering, product and QA. Bug triage was manual, and test automation was moving slowly.
How they did it
- Had Devin draft User Requirement Specifications and Disaster Recovery Plans from Jira tickets and source code.
- Had senior engineers review the drafts instead of writing them.
- Built an 'AutoFixer' playbook that runs several times a day: Devin reads tickets, explores code, implements fixes, runs tests and opens PRs.
- Used Devin for TypeScript/Next.js migrations and for Playwright and Cucumber tests mapped to requirements.
Results
- As reported by Cognition: URS documents that took '35 to 40 hours' came out as first drafts 'at roughly 90% accuracy', a reported '8x faster GxP documentation'.
- Within 22 days, AutoFixer attempted '79 bugs', with clean fixes merged for about half.
- Cognition also cites '3x faster code migrations' and '2–3x faster test-writing'.
As reported by the source (Cognition (Devin) customer story); AgentGid did not measure these figures.
This suits teams in regulated environments with well-kept Jira tickets and code, plus senior reviewers who can check every draft. Note that the 8x, 90% and 3x figures come from Cognition, and only about half of AutoFixer's 79 attempts merged cleanly, so budget for review time. Devin starts at $20/mo for Pro; Jules (Free + $19.99/mo) is a cheaper option to try on bug fixing.
The agent used here
Similar use cases
How RV Tech sped up vehicle software test generation with Devin
The Rivian–Volkswagen joint venture uses Devin to generate software-in-the-loop tests from requirements and to pre-triage vehicle access tickets. As reported by Cognition, test ou…
As reported by Cognition: a '10-15x increase in test generation velocity'.
How an OpenAI team built a product with Codex writing all of the code
A small OpenAI team built an internal beta product starting from an empty repository, with Codex writing the code and humans steering. The post covers how they set up the reposito…
As reported by OpenAI: 'roughly 1,500 pull requests have been opened and merged with a small team of just three engineers'.
How Stripe's homegrown Minions agents turn Slack requests into merged PRs
Stripe built unattended coding agents, called Minions, on a fork of Block's goose agent. They take a task from Slack or an internal tool and return a CI-checked pull request for h…
As reported by Stripe: 'over a thousand pull requests merged each week' are produced entirely by Minions and reviewed by humans.
Guides
Best AI Agents in 2026: Live Rankings by Category
The leading AI agents for coding, design, research, data, marketing, sales, support, HR, finance, legal, DevOps and security, ranked by public usage data that refreshes daily, with prices and free options.
Best AI Coding Agents in 2026: Ranked by Usage, Benchmarks and Price
The AI coding agents developers use most, with live download and install numbers, benchmark results, entry prices and a way to choose between terminal, IDE and cloud agents.