Webinar slides: AI Powered Software Development from the Trenches

Henrik Kniberg
Co-founder & Chief Scientist
·1 min read
Webinar slides: AI Powered Software Development from the Trenches

In this article

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

On Mar 26 I did a webinar called “AI Powered Software Development from the Trenches”, showing how we use AI and agents internally to ship a new version of our platform every day. Content links:

If you want to learn more and go deeper into the hands-on aspects of this, I’m giving a 1 day course on April 16 (online).

Key points from the webinar:

  • Coding productivity has evolved through four stages: Manual coding → copy-paste → AI in the IDE → autonomous agents. Each one a major productivity jump.
  • For us, coding is no longer the bottleneck, the constraint has shifted to deciding what to build and getting stuff to production.We built agents for the rest of the workflow — Backlogger (Slack → tickets), Releaser (daily releases + changelog), and Grace (a higher-level agent that reads Slack, makes judgment calls, and fires up coding agents)
  • Context engineering matters more than prompt engineering. Good context + sloppy prompt beats bad context + perfect prompt.
  • The most important skill is the meta-skill: knowing when to let AI just do it vs. when to carefully review.
  • The nature of software development has changed — as a sw engineer, your job is more about design, architecture, and UX, and less about reading/writing specific lines of code

Here are some sample slides:

Dont just spray out new features
Developer productivity levels


Quality


Read more

What does 10x engineering productivity look like in practice?

What does 10x engineering productivity look like in practice?

Concrete and surprising data on how AI agents in Cursor and Abundly affect our productivity and quality.

Henrik Kniberg
May 22, 2026
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 — 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 — with a link to the full 100-day playbook.

Nils Janse
April 24, 2026
Demo: The Human + AI-Agent Dev Team

Demo: The Human + AI-Agent Dev Team

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.

Henrik Kniberg
April 23, 2026
One File to Rule Them All — A Lesson in AI Agent Unsafety

One File to Rule Them All — 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

Related courses

AI-powered software development from the trenches 🇬🇧