AI Agents Need Help. Here’s 4 Ways To Ship Software Reliably
We’re so glad you’re here. You can expect all the best TNS content to arrive Monday through Friday to keep you on top of the news and at the top of your game.
Check your inbox for a confirmation email where you can adjust your preferences and even join additional groups.
This post is a written deep-dive of the talk I gave at the 2025 AI Engineer World’s Fair in San Francisco. Based on my experience with software delivery and agents as co-founder of Dagger and first employee at Docker.
As LLMs generate ever more code — from more intelligent autocompletion to fully autonomous coding agents — the cost of writing code plummets. Pressure then shifts to the delivery pipeline, because every new line must still clear the test suite and code review on its way to production.
Software-delivery automation has always been a bottleneck — that’s why we launched Dagger — but the bottleneck is tightening now that anyone can churn out large volumes of decent code.
