← back
Software Development Agents: What Works and What Doesn't - Robert Brennan, OpenHands
Takeaway
Coding agents become genuinely productive when you scope tasks tightly, sandbox aggressively, and treat the agent as the inner-loop coder while humans own architecture.
Summary
- OpenHands (formerly OpenDevin) creator argues coding is going away but software engineering isn't—humans shift to architecture and intent while agents run the inner loop.
- Agent = LLM + editor/terminal/browser tools in a loop; smart tool design (diff editors, accessibility trees, screenshot-with-labels) doubled web-browsing accuracy.
- All execution sandboxed in Docker with tightly-scoped third-party tokens; least-privilege is critical when agents act autonomously for minutes.
- Best practices: start small (lint fixes, merge conflicts, single-commit chores), give specific 'what+how' instructions, expect ~90% of code to flow through the agent for power users.
coding-agentsopenhandssandboxing
Original description
The adoption of AI into software development has been bumpy. While autocomplete tools like Copilot have gone mainstream, autonomous agents like Devin and OpenHands have generated both enthusiasm and skepticism. Some engineers claim they generate a 10x productivity boost; others that they just create noise and tech debt. The difference between the enthusiasts and the skeptics is that the enthusiasts have reasonable expectations for what these agents can do, and have both practical and intuitive knowledge for how to use them effectively. In this session, we'll talk about what tasks are appropriate for today's software agents, what tasks they might start to succeed at in 2025, and what tasks are best left to humans no matter how good they get. Session Outline: Learn how to use software development agents like OpenHands (fka OpenDevin) effectively, without creating noise and tech debt. ---related links--- https://x.com/rbren_dev https://linkedin.com/in/robert-a-brennan https://www.openhands.dev/blog https://www.openhands.dev