Getting Humans Out of the Way: How to Work with Teams of Agents

MLOps Community
MLOps CommunityMay 1, 2026

Why It Matters

By automating validation and QA, developers can scale output and accelerate product cycles while minimizing human bottlenecks, fundamentally reshaping software engineering productivity.

Key Takeaways

  • Define validation processes to let agents self‑verify work.
  • Use screenshot‑based feature walk‑throughs for rapid human approvals.
  • Implement custom lint rules; agents generate and enforce coding standards.
  • Leverage agents for automated unit tests and comprehensive documentation.
  • As models improve, grant agents more autonomy, reducing human oversight.

Summary

The conversation centers on how developers can "get humans out of the way" by building robust validation pipelines for AI‑driven coding agents. Rather than manually QA every feature, engineers define clear criteria—such as visual regression walk‑throughs and custom lint rules—so agents can self‑check and report results. Key insights include creating a feature walk‑through document composed of cropped screenshots with explanatory text, then having a second sub‑agent verify each image before presenting it to the human manager. This approach streamlines approvals, catches regressions automatically, and enables agents to iterate until the walkthrough passes. Custom lint rules and agent‑written unit tests further enforce style, complexity limits, and test coverage without human micromanagement. The speakers cite concrete examples: Erica downloading skills from a coding‑agents conference, using Claude to generate them, and the presenter relying on screenshot docs to approve merges without opening the code. They also discuss a short‑form video generator that repeatedly failed dimension checks until an agent‑driven validation caught the error early. Implications are profound: as large‑language models evolve, developers can progressively hand over more responsibilities—from autocomplete to autonomous QA and documentation—freeing human time for higher‑level design. This shift demands new workflows and verification scaffolds but promises faster releases, higher code quality, and scalable AI‑agent teams.

Original Description

Rob Ennals is the creator of Broomy, an open-source IDE designed for working effectively with many agents in parallel. He previously worked at Meta, Quora, Google Search, and Intel Research. He has a PhD in Computer Science from the University of Cambridge.
Getting Humans Out of the Way: How to Work with Teams of Agents // MLOps Podcast #368 with Rob Ennals, the Creator of Broomy
// Abstract
Most people cripple coding agents by micromanaging them—reviewing every step and becoming the bottleneck.
The shift isn’t to better supervise agents, but to design systems where they work well on their own: parallelized, self-validating, and guided by strong processes.
Done right, you don’t lose control—you gain leverage. Like paving roads for cars, the real unlock is reshaping the environment so AI can move fast.
// Bio
Rob Ennals is the creator of Broomy, an open-source IDE designed for working effectively with many agents in parallel. He previously worked at Meta, Quora, Google Search, and Intel Research. He has a PhD in Computer Science from the University of Cambridge.
// Related Links
https://learnai.robennals.org/ (not yet announced, but should be by the time of the podcast)
~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~
Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore
Join our Slack community [https://go.mlops.community/slack]
Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]
Sign up for the next meetup: [https://go.mlops.community/register]
Connect with Demetrios on LinkedIn: /dpbrinkm
Connect with Rob on LinkedIn: /robennals/
Timestamps:
[00:00] Agent Optimization Strategies
[00:21] Visual Regression Explanation
[05:35] Automated QA for Videos
[13:05] Verification System Design
[19:48] Agent Selection Strategies
[30:48] Parallel Agent Management
[35:30] Containerization and Cost Estimation
[42:48] Shifting to Agent Orchestration
[50:10] Wrap up

Comments

Want to join the conversation?

Loading comments...