In 2025 AI reshaped how groups suppose, construct, and ship software program. We’re now at a degree the place “AI coding assistants have rapidly moved from novelty to necessity [with] as much as 90% of software program engineers us[ing] some form of AI for coding,” Addy Osmani writes. That’s a really completely different world to the one we had been in 12 months in the past. As we look forward to 2026, listed here are three key developments we’ve seen driving change and the way we predict builders and designers can put together for what’s forward.
Evolving Coding Workflows
New AI instruments modified coding workflows in 2025, enabling builders to jot down and work with code sooner than ever earlier than. This doesn’t imply AI is changing builders. It’s opening up new frontiers to be explored and expertise to be mastered, one thing we explored at our first AI Codecon in Might.
AI instruments within the IDE and on the command line have revived the controversy concerning the IDE’s future, echoing previous arguments (e.g., VS Code versus Vim). It’s extra helpful to give attention to the instruments’ goal. As Kent Beck and Tim O’Reilly mentioned in November, builders are in the end chargeable for the code their chosen AI software produces. We all know that LLMs “actively reward present high tier software program engineering practices” and “amplify present experience,” as Simon Willison has identified. And coder will “consider” questions that AI doesn’t. Does it actually matter which software is used?
The vital transferable talent for working with any of those instruments is knowing methods to talk successfully with the underlying mannequin. AI instruments generate higher code in the event that they’re given all of the related background on a venture. Managing what the AI is aware of about your venture (context engineering) and speaking it (immediate engineering) are going to be key to doing good work.
The core expertise for working successfully with code received’t change within the face of AI. Understanding code overview, design patterns, debugging, testing, and documentation and making use of these to the work you do with AI instruments would be the differential.
The Rise of Agentic AI
With the rise of brokers and Mannequin Context Protocol (MCP) within the second half of 2025, builders gained the flexibility to make use of AI not simply as a pair programmer however as a complete staff of builders. The audio system at our Coding for the Agentic World stay AI Codecon occasion in September 2025 explored new instruments, workflows, and hacks which are shaping this rising self-discipline of agentic AI.
Software program engineers aren’t simply working with single coding brokers. They’re constructing and deploying their very own customized brokers, usually inside complicated setups involving multi-agent eventualities, groups of coding brokers, and agent swarms. This shift from conducting AI to orchestrating AI elevates the significance of really understanding how good software program is constructed and maintained.
We all know that AI generates higher code with context, and that is additionally true of brokers. As with coding workflows, this implies understanding context engineering is crucial. Nevertheless, the differential for senior engineers in 2026 can be how nicely they apply intermediate expertise resembling product pondering, superior testing, system design, and structure to their work with agentic methods.
AI and Software program Structure
We started 2025 with our January Superstream, Software program Structure within the Age of AI, the place speaker Rebecca Parsons explored the architectural implications of AI, dryly noting that “given the tempo of change, this might be old-fashioned by Friday.” By the point of our Superstream in August, issues had solidified a little bit extra and our audio system had been capable of share AI-based patterns and antipatterns and clarify how they intersect with software program structure. Our December 9 occasion will take a look at enterprise structure and the way architects can navigate the influence of AI on methods, processes, and governance. (Registration remains to be open—save your seat.) As these occasions present, AI has progressed from being one thing architects might need to contemplate to one thing that’s now important to their work.
We’re seeing profitable AI-enhanced architectures utilizing event-driven fashions, enabling AI brokers to behave on incoming triggers slightly than mounted prompts. This implies it’s extra essential than ever to know event-driven structure ideas and trade-offs. In 2026, matters that align with evolving architectures (evolutionary architectures, health features) may even grow to be extra essential as architects look to seek out methods to modernize present methods for AI with out derailing them. AI-native architectures may even deliver new concerns and patterns for system design subsequent yr, as will the development towards agentic AI.
As was the case for his or her engineer coworkers, architects nonetheless need to know the fundamentals: when so as to add an agent or a microservice, methods to take into account price, methods to outline boundaries, and methods to act on the information they have already got. As Thomas Betts, Sarah Wells, Eran Stiller, and Daniel Bryant observe on InfoQ, in addition they “nee[d] to know how an AI aspect pertains to different elements of their system: What are the inputs and outputs? How can they measure efficiency, scalability, price, and different cross-functional necessities?”
Firms will proceed to decentralize duties throughout completely different features this yr, and AI brings new units of trade-offs to be thought of. It’s true that regulated industries stay understandably cautious of granting entry to their methods. They’re rolling out AI extra rigorously with higher guardrails and governance, however they are nonetheless rolling it out. So there’s by no means been a greater time to know the foundations of software program structure. It would put together you for the complexity on the horizon.
Sturdy Foundations Matter
AI has modified the way in which software program is constructed, but it surely hasn’t modified what makes good software program. As we enter 2026, a very powerful developer and structure expertise received’t be outlined by the software you realize. They’ll be outlined by how successfully you apply judgment, talk intent, and deal with complexity when working with (and typically towards) clever assistants and brokers. AI rewards sturdy engineering; it doesn’t exchange it. It’s an thrilling time to be concerned.
Be part of us on the Software program Structure Superstream on December 9 to discover ways to higher navigate the influence of AI on methods, processes, and governance. Over 4 hours, host Neal Ford and our lineup of consultants together with Metro Financial institution’s Anjali Jain and Philip O’Shaughnessy, Vercel’s Dom Sipowicz, Intel’s Brian Rogers, Microsoft’s Ron Abellera, and Equal Specialists’ Lewis Crawford will share their hard-won insights about constructing adaptive, AI-ready architectures that assist steady innovation, guarantee governance and safety, and align seamlessly with enterprise objectives.
O’Reilly members can register right here. Not a member? Join a 10-day free trial earlier than the occasion to attend—and discover all the opposite assets on O’Reilly.
