---
title: "One month testing Devin"
canonical: "https://agenticfeats.com/c/one-month-testing-devin/"
agents: ["Devin"]
evidence_grade: "B"
outcome: "partial"
job_type: "Coding"
industry: "Software companies"
roles: ["Developer", "Founder or owner"]
source_url: "https://frontierai.substack.com/p/one-month-of-using-devin"
source_date: "2025-01-23"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# One month testing Devin

Devin was connected to the RunLLM GitHub repo and given small bug fixes and one larger full-stack task over a month.

Result: Small scoped fixes took about five minutes to test and merge versus roughly an hour by hand; the full-stack task failed and was rewritten.

## How it was set up

Devin connected to the GitHub repo, scanned it to infer build steps, and opened pull requests. Tasks were typed into its chat interface.

## Worth knowing

Devin struggled with a multi-layer task, ignored taught practices, and its code was unworkable. Backend work went worse than frontend.

## Evidence note

Author's firsthand account with time estimates; no repo or demo

## Sources

- Original: https://frontierai.substack.com/p/one-month-of-using-devin

## The receipt

- Agent: Devin
- Evidence: Numbers (grade B, a specific number stated)
- Outcome: Partial
- Job type: Coding
- Industry: Software companies
- Roles: Developer, Founder or owner
- Source: Blog
- Published: 2025-01-23
- Added: 2026-10-13