In developing the content for our May 8 virtual conference Coding with AI: The End of Software Development as We Know It, we couldn’t help but want to feature Harper Reed, whose recent post “My LLM Codegen Workflow ATM” so perfectly encapsulates the kind of experimentation that developers are going through as they come to grips with the transformation that AI is bringing to how they work, what they can accomplish, and which tools they should be adopting. Harper lays out his current workflows and tools with detailed examples for both greenfield code and legacy code that make it easy for others to learn from what he’s done. It’s a great model for the kind of information sharing we hope to engender with the upcoming event and others that will follow. If you haven’t read it yet, go do so now.
In an email to me, my old friend Nat Torkington had this to say about Harper’s post:
Learn faster. Dig deeper. See farther.
I feel like there are ascending levels of nerd in this:
– prompt hacks
– tools to integrate into your workflow
– context hacks (e.g., build a requirements document with the LLM, then get it to code to those requirements)
– use of specific models/features (e.g., reasoning vs. non-reasoning LLMs)
– custom workflows/tools assembled from pieces, but which really are custom-built to that person’s workflow
ALL of these are things that we want to cover in our upcoming event. So I’d like to use Harper’s piece as a prompt and context hack to all of you, to clarify what we’re looking for at the event. Coding with AI will feature fireside chats with folks like Jay Parikh, Addy Osmani and Gergely Orosz, Chip Huyen, and Shawn @swyx Wang, and talks by Harper, Simon Willison, Camille Fournier, Chelsea Troy, Steve Yegge, Birgitta Boeckeler, Andrew Stellman, and others. But we’re still looking for more reports from the trenches, presented as five-minute lightning talks (a format Nat Torkington originally developed for our Perl Conference nearly 30 years ago, and that was a beloved feature of all our conferences thereafter).
Categories we’re interested in include “my favorite AI tool,” “my favorite AI prompt or context hack,” “my workflow,” “my project that I would never have thought to try without the ease of experiment I get with AI,” and so on. In addition to the lightning talks at this event, we’re also planning a future recurring event that’s entirely devoted to a live version of the kind of full show-and-tell that Harper did so well.
So, go read Harper, and show us what you’ve got! Ideally, you will not only give us the full version but also distill particular, usable lessons from it. Here’s some additional wisdom from Nat’s email to get you started:
The more the mechasuit is designed for your cortex, the less transferable it is to other people. The risk is you start with “here are six tools I use in my own complex workflow in a language you don’t recognise to solve problems you don’t have” and lose people in a flood of random tool names.
[We want to be] able to look at different people’s “I code with AI!” workflows and break them down [as Harper does] so [our viewers] can go “well, that’s cool but I’m not using vi and command-line tools don’t play well with Visual Studio, so I’ll just steal your context hacks for working with big code bases in Copilot.”
Addy Osmani added to our email conversation:
Building on the “ascending levels of nerd” framework (which I love!), we could structure some of the “how I work” content to specifically address different developer experience levels. For example:
- Junior devs: focus on building that critical evaluation mindset and understanding when/how to effectively use AI tools
- Mid-level: exploring workflow integration and context optimization
- Senior: deep dives into custom tooling and advanced prompt engineering
Submit your proposals (including, ideally, a post modeled on Harper’s that we can publish here on the O’Reilly Radar blog) at the existing call for presentations link. We’ve updated the submission deadline to March 12 and the event date from April 24 to May 8 to give you a bit more time to do your reasoning and then respond to this revised prompt.
On May 8, O’Reilly Media will be hosting Coding with AI: The End of Software Development as We Know It—a live virtual tech conference spotlighting how AI is already supercharging developers, boosting productivity, and providing real value to their organizations. If you’re in the trenches building tomorrow’s development practices today and interested in speaking at the event, we’d love to hear from you by March 12. You can find more information and our call for presentations here.