Tools-in-Action30min
Beyond Code: The Intent-Driven IDE for the Agentic Age
This session explores intent-driven development environments where specifications guide autonomous agents in parallel workspaces. Through a live demo, it shows a task moving from spec to pull request, plus custom workflow extension. It also examines architecture, automation, context management, model choices, and the developer’s evolving role.
talk.summaryAiDisclaimer
Bruno BorgesGitHub
talkDetail.whenAndWhere
Monday, October 5, 17:35-18:05
Room 4
For decades, IDEs have organized software development around files, editors, plugins, code completion, and automation. But what happens when the developer’s primary input is no longer code, but intent?
In this live, demo-driven session, we’ll examine the emerging shape of intent-driven development environments: specifications become executable context, agents work concurrently in isolated workspaces, and developers shift from producing every line to directing, reviewing, and integrating work.
We’ll take a task from specification to pull request, delegate parts of it to specialized agents, and build an extension for a custom workflow the environment did not previously support. We’ll also explore the architectural choices behind these systems, including agent harnesses, model selection, local inference, automation, context management, and human approval boundaries.
Rather than presenting agents as a replacement for developers, we’ll examine where this model works, where it breaks down, and what skills developers need when intent becomes the starting point for software creation.
In this live, demo-driven session, we’ll examine the emerging shape of intent-driven development environments: specifications become executable context, agents work concurrently in isolated workspaces, and developers shift from producing every line to directing, reviewing, and integrating work.
We’ll take a task from specification to pull request, delegate parts of it to specialized agents, and build an extension for a custom workflow the environment did not previously support. We’ll also explore the architectural choices behind these systems, including agent harnesses, model selection, local inference, automation, context management, and human approval boundaries.
Rather than presenting agents as a replacement for developers, we’ll examine where this model works, where it breaks down, and what skills developers need when intent becomes the starting point for software creation.
Bruno Borges
Bruno Borges is a Principal Product Manager at GitHub with over 30 years of experience in Software Engineering, Product Management, Developer Relations, and Cloud & AI developer experience. Currently, he leads developer relations and product management programs for AI and GitHub Copilot at Microsoft, driving initiatives like the GitHub Copilot SDK for Java, and AI-assisted modernization workflows for enterprise developers. Bruno also continues to shape Microsoft's Java strategy, having led the public announcement of the Microsoft Build of OpenJDK and new tools like Azure Command Launcher for Java. Prior to his current focus on AI, he spent years building Microsoft Azure into a top destination for Java workloads, and before that served nearly six years at Oracle influencing developer relations strategy. A recognized Java Champion and top Java influencer, Bruno is a frequent conference speaker and open-source contributor with projects like Java Evolved, JairoSVG, JLib Inspector, ghx, and more. Visit github.com/brunoborges