Demo: The Human + AI-Agent Dev Team

Henrik Kniberg
Co-founder & Chief Scientist
ยท1 min read
Demo: The Human + AI-Agent Dev Team

In this article

How we use AI agents internally at Abundly - both for coding, backlog management and release management. It's a system of AI agents & human engineers working together, building on each other's strengths. This not only enables us to release a new version of our platform every day, but also makes the work really fun.

What happens when coding is no longer the bottleneck in product development?

I made a new demo video showing how we use AI agents internally at Abundly - both for coding, backlog management and release management. It's a system of AI agents & human engineers working together, building on each other's strengths.

This not only enables us to release a new version of our platform every day, but also makes the work really fun, since we can focus on the higher level stuff (design/architecture/ux) and ship value every day.

For each agent I demonstrate what they do, what value they provide, and what we learned when making them.

How our agents and human engineers collaborate
  • Cursor: writes most of the code
  • Backlogger: turns messy Slack threads into clean, well-structured Notion tickets
  • Releaser: manages our daily release process end-to-end: PRs, release notes, changelog, announcements
  • Grace: a higher-level "colleague" agent that handles stakeholder requests from Slack all the way to pull request, coordinating with Cursor and the other agents

Grace is particularly fascinating. She does things proactively, and improves herself regularly based on our feedback. Since she is running on the Abundly platform (along with Backlogger and Releaser), and can edit code, she is also effectively improving the platform that she is running on.

This is of course only a snapshot in time - we are continuously learning and experimenting with how to use agents effectively, while still staying in control of architecture and quality.

Here is the video.



Read more

How to not AI Slop

How to not AI Slop

Illustrated by two extremes: an unedited voice transcript of Henriks sitting on a rock talking, vs an AI-written article

Henrik Kniberg
May 9, 2026
The Trust Ladder: how to onboard AI agents like new colleagues

The Trust Ladder: how to onboard AI agents like new colleagues

What data should we let them access? What if the agent gets it wrong? What holds organisations back is rarely the technology โ€” it's the uncertainty. Think of AI agents as new colleagues and extend their remit one rung at a time, along the Trust Ladder.

Hans Brattberg
April 24, 2026
The First 100 Days as an AI Lead: The Playbook in 5 Minutes

The First 100 Days as an AI Lead: The Playbook in 5 Minutes

You got the role. The mandate is clear: make AI agents work across the organization. Now what? A short teaser of the four conditions, three phases, and the patterns that separate AI initiatives that ship from the ones that stall โ€” with a link to the full 100-day playbook.

Nils Janse
April 24, 2026
Webinar slides: AI Powered Software Development from the Trenches

Webinar slides: AI Powered Software Development from the Trenches

Slides and recording from Henrik's webinar "AI Powered Software Development from the Trenches.

Henrik Kniberg
April 10, 2026
One File to Rule Them All โ€” A Lesson in AI Agent Unsafety

One File to Rule Them All โ€” A Lesson in AI Agent Unsafety

2.3 million AI agents on a social network, most running on people's personal computers with full access to files and credentials, reading and obeying instructions from a single public web page. What can possibly go wrong?

Henrik Kniberg
February 10, 2026
How an AI Agent Extended My Healthy Lifespan

How an AI Agent Extended My Healthy Lifespan

A story about a special agent, one that has added years to my healthy lifespan through concrete research and action.

Henrik Kniberg
January 9, 2026

Related courses

AI-powered software development from the trenches ๐Ÿ‡ฌ๐Ÿ‡ง