Could 8 AI Codecon was an enormous success. We had superb audio system and content material. We additionally had over 9,000 dwell attendees and one other 12,000 who signed up to have the ability to view the content material in a while the O’Reilly studying platform. (Right here’s a put up with video excerpts and a few of my takeaways.)
So we’re doing it once more. The subsequent AI Codecon is scheduled for September 9. Our focus this time goes to be on agentic coding. Now I do know that Simon Willison and others have derided “agentic” as a advertising and marketing buzzword, and that nobody may even agree on what it means (Simon has collected dozens of competing definitions), however regardless of the time period involves imply to most individuals, the truth is one thing all of us have to come back to grips with. We now have LLMs with specialised system prompts, utilizing instruments, chained collectively in pipelines or working in parallel, working in loops, and modifying their environments. That looks like a reasonably good start line for a working definition.
Within the September 9 AI Codecon, we’ll be concentrating on 4 vital frontiers of agentic improvement:
- Agentic interfaces: Shifting past chat UX to classy agent interactions. New paradigms don’t simply require new infrastructure; additionally they allow new interfaces. We’re trying to spotlight improvements in AI interfaces, particularly as agentic AI purposes prolong far past easy chat.
- Instrument-to-tool workflows: How brokers chain throughout environments to finish advanced duties. As an outdated Unix/Linux head, I really like the thought of pipelines (and now networks) of small cooperating packages. We at the moment are reinventing that type of network-enabled strategy to purposes for AI.
- Background coding brokers: Asynchronous, autonomous code technology in manufacturing. When AI duties begin working within the background, anticipate both magic or mayhem. We’d favor the previous, and wish to present the slicing fringe of find out how to construct safer, extra dependable brokers.
- MCP and agent protocols: The infrastructure enabling the agentic net. Whereas the primary technology of AI purposes have been centralized monoliths, we’re satisfied that the agentic future is one in all cooperating AIs, interoperating not solely with purposes designed for people but in addition with AI-native endpoints designed to be consumed by AI brokers. MCP is a superb begin, but it surely’s removed from the tip of protocols for agent-to-agent communication. (See my put up “Disclosures. I Do Not Assume That Phrase Means What You Assume It Means.” for an account of how communication protocols allow participatory markets. I’m tremendous enthusiastic about the way in which that AI is creating new alternatives for builders and entrepreneurs that aren’t capital-intensive, winner-takes-all races just like the preliminary race for chatbot supremacy. These alternatives come from the community protocols that allow cooperating AIs.)
The first convention monitor will probably be organized very like the Could occasion: a curated assortment of hearth chats with senior technical executives, sensible engineers, and entrepreneurs; sensible talks on the brand new instruments, workflows, and hacks which are shaping the rising self-discipline of agentic AI; demos of how skilled builders are utilizing the brand new instruments to supercharge their productiveness, their revolutionary purposes, and person interfaces; and lightning talks that are available in from our name for proposals (see under). We’ll even have a collection of in-depth tutorials on separate days as a way to go deeper if you’d like. You possibly can join right here. The mainstage occasion is free. Tutorials can be found to O’Reilly subscribers and will also be bought à la carte—trial memberships may also get you within the door. 🙂 The separate demo showcase will probably be sponsored (and thus free).
Name for proposals
Do you’ve gotten a narrative to share about how you might be utilizing brokers to construct revolutionary and efficient AI-powered experiences? We wish to hear it. The AI Codecon program will probably be a mixture of invited talks and your proposals, so we’re asking you to submit your concept for a fast five-minute lightning speak about cutting-edge work. We aren’t on the lookout for high-level discussions; we wish conflict tales, demos of merchandise and workflows, revolutionary purposes, and accounts of latest instruments which have modified how you’re employed. You (collectively) are inventing the longer term at a livid charge. We’d love to listen to about work that may make folks say “wow!” and rush to be taught extra. Your objective needs to be to make the rising future occur quicker by sharing what you’ve discovered.
After studying your proposal, we might ask you to current it as proposed, modify it, develop it into an extended discuss, be part of a dialogue panel, or seem in our related demo day program.
Matters we’re interested by embrace:
- UI/UX—How are you or your organization exploring agentic interfaces and shifting past chatbot UX?
- The way you’re utilizing brokers right now—Are you handing off whole duties to brokers? What duties are you handing off, and the way are you integrating the brokers’ work into the SDLC?
- Your tool-to-tool workflows—How are you chaining brokers throughout environments and providers to finish duties end-to-end?
- Background coding brokers—What’s rising from extra asynchronous and autonomous code technology, and the place is that this headed?
- MCP and the way forward for the net—How are agentic protocols unlocking revolutionary workflows and experiences?
- Shock us. With the market shifting this quick, it’s possible you’ll be doing one thing superb that doesn’t match this system as we’re envisioning it right now however that the AI coding group wants to listen to about. Don’t be afraid to paint exterior the strains.
We’re additionally nonetheless interested by listening to about subjects we explored in our earlier name for proposals:
- What has modified about the way you code, what you’re employed on, and the instruments you employ?
- Are we working towards a brand new improvement stack? How are your architectures and patterns altering as you progress towards AI-native purposes?
- How is AI altering the make-up and workload of your dev groups?
- What have you ever achieved to keep up high quality requirements with AI-generated code?
- What forms of duties are you taking up that have been beforehand too time-consuming to perform?
- What issues have you ever encountered that you simply want others had advised you about while you have been beginning out in your journey?
- What sorts of enjoyable tasks are you taking up in your free time?
So submit your proposal for a chat by July 18. And when you’ve got a product you’d wish to demo as a part of our sponsored demo showcase, please tell us at AI-Engineering@oreilly.com.
Thanks!
