[ad_1]
May 8 AI Codecon was an enormous success. We had superb audio system and content material. We additionally had over 9,000 stay 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. (Here’s a publish 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 return 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 as if a fairly good place to begin for a working definition.
In the September 9 AI Codecon, we’ll be concentrating on 4 vital frontiers of agentic improvement:
- Agentic interfaces: Moving past chat UX to classy agent interactions. New paradigms don’t simply require new infrastructure; additionally they allow new interfaces. We’re seeking to spotlight improvements in AI interfaces, particularly as agentic AI functions prolong far past easy chat.
- Tool-to-tool workflows: How brokers chain throughout environments to finish complicated duties. As an outdated Unix/Linux head, I like the thought of pipelines (and now networks) of small cooperating packages. We are actually reinventing that form of network-enabled method to functions for AI.
- Background coding brokers: Asynchronous, autonomous code era in manufacturing. When AI duties begin working within the background, count on both magic or mayhem. We’d want the previous, and wish to present the slicing fringe of the best way to construct safer, extra dependable brokers.
- MCP and agent protocols: The infrastructure enabling the agentic internet. While the primary era of AI functions have been centralized monoliths, we’re satisfied that the agentic future is certainly one of cooperating AIs, interoperating not solely with functions designed for people but additionally with AI-native endpoints designed to be consumed by AI brokers. MCP is a superb begin, but it surely’s removed from the top of protocols for agent-to-agent communication. (See my publish “Disclosures. I Do Not Think That Word Means What You Think 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. Those alternatives come from the community protocols that allow cooperating AIs.)
The main convention observe will probably be organized very like the May 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 functions, and consumer interfaces; and lightning talks that are available from our name for proposals (see under). We’ll even have a set of in-depth tutorials on separate days in an effort to go deeper if you need. You can enroll 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 can even get you within the door. 🙂 The separate demo showcase will probably be sponsored (and thus free).
Call for proposals
Do you may have 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 thought for a fast five-minute lightning discuss cutting-edge work. We aren’t in search of high-level discussions; we would like conflict tales, demos of merchandise and workflows, revolutionary functions, and accounts of latest instruments which have modified how you’re employed. You (collectively) are inventing the longer term at a livid fee. We’d love to listen to about work that can make individuals say “wow!” and rush to be taught extra. Your aim must be to make the rising future occur sooner by sharing what you’ve realized.
After studying your proposal, we could ask you to current it as proposed, modify it, broaden it into an extended speak, be part of a dialogue panel, or seem in our related demo day program.
Topics we’re all for embody:
- UI/UX—How are you or your organization exploring agentic interfaces and transferring past chatbot UX?
- How you’re utilizing brokers in the present day—Are you handing off complete 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 era, and the place is that this headed?
- MCP and the way forward for the net—How are agentic protocols unlocking revolutionary workflows and experiences?
- Surprise us. With the market transferring this quick, you might be doing one thing superb that doesn’t match this system as we’re envisioning it in the present day however that the AI coding group wants to listen to about. Don’t be afraid to paint outdoors the strains.
We’re additionally nonetheless all for listening to about matters 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 utilize?
- Are we working towards a brand new improvement stack? How are your architectures and patterns altering as you progress towards AI-native functions?
- 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 sorts of duties are you taking over that had been beforehand too time-consuming to perform?
- What issues have you ever encountered that you just want others had informed you about while you had been beginning out in your journey?
- What sorts of enjoyable initiatives are you taking over in your free time?
So submit your proposal for a chat by July 18. And when you’ve got a product you’d prefer to demo as a part of our sponsored demo showcase, please tell us at AI-Engineering@oreilly.com.
Thanks!