---
title: "Month of Devin tasks"
canonical: "https://agenticfeats.com/c/month-of-devin-tasks/"
agents: ["Devin"]
evidence_grade: "B"
outcome: "failed-with-lesson"
job_type: "Coding"
industry: "Software companies"
roles: ["Developer"]
source_url: "https://answer.ai/posts/2025-01-08-devin.html"
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

# Month of Devin tasks

Devin was given more than 20 real coding, research, and code-modification tasks over a month by an Answer.AI team to test its autonomy.

Result: Out of 20 tasks, Devin had 14 failures, 3 successes, and 3 inconclusive results, with no pattern predicting which would work.

## How it was set up

Devin, driven through Slack and its web interface, running in its own Docker environment with browser, editor, and shell.

## Worth knowing

Failed tasks often took days. Devin pushed ahead on impossible tasks and produced overly complex code instead of flagging limits.

## Evidence note

Team write-up with counts and an appendix of tasks; no output repo

## Sources

- Original: https://answer.ai/posts/2025-01-08-devin.html

## The receipt

- Agent: Devin
- Evidence: Numbers (grade B, a specific number stated)
- Outcome: Failed, with a lesson
- Job type: Coding
- Industry: Software companies
- Roles: Developer
- Source: Blog
- Added: 2026-10-13