TL;DR
Get the latest gadgets delivered free — and shop member deals
- Fast, free delivery on millions of items
- Access to Prime Big Deal Days deals on October 6–7
- Prime Video, Amazon Music and more included
A report based on a keynote to engineering leaders describes AI as the defining force reshaping software development in 2026. Engineers are increasingly directing multiple coding agents rather than writing code by hand, but the report also flags weaker reliability and code reviews that may not provide meaningful scrutiny. The scale of these changes is based on interviews and industry observations, not a representative survey.
A report on the tech industry in 2026 says AI coding agents are changing how software engineers work, with some experienced developers managing five to 10 agent sessions at once instead of writing code line by line. The account, based on a keynote to engineering leaders and interviews with practitioners, also warns that code quality, reliability and review practices have not kept pace with the new tools.
The report was drawn from a keynote at LDX3 in New York, a conference attended by more than 2,000 engineering leaders and senior technical staff, according to its author at The Pragmatic Engineer. The author said the snapshot also drew on visits to OpenAI and Anthropic, conversations with startups and companies including Ramp and Uber, and unpublished data from GitHub, Factory AI and Linear. The material is an industry account, not a published representative survey.
Several developers described running coding agents in parallel. Boris Cherny, identified in the report as the creator of Claude Code, said he uses five terminal tabs and runs five to 10 Claude sessions on the web alongside local sessions. Peter Mattis, co-founder of Cockroach Labs, described a similar capacity for handling five to 10 concurrent agent sessions, sometimes with subagents. Linear software engineer Dima Zaytsev said he keeps multiple local worktrees and switches between tasks while agents produce or test code.
The report groups the shift with changes in coding tools and team practices, including what it calls the fading of the IDE and growing use of agent-based workflows. It also lists problems: assumptions about the quality of generated code have broken down, reviews can become performative, and quality and reliability are declining. Those are the author’s reported observations; the supplied material does not quantify the changes or establish how widespread they are.
AI Changes the Engineer’s Day
If these practices spread, the central engineering task may shift from producing each line of code to specifying work, coordinating agents and checking their output. Parallel agents can let developers work on several tasks at once, but they also increase the volume of generated code that teams must understand, test and maintain.
The report’s concerns about review and reliability point to a practical risk for organizations adopting the tools: faster code production does not by itself show that software is correct, secure or fit for users. Teams may need to adapt how they assign responsibility and verify changes. The report does not provide measured productivity gains or a causal estimate of how AI has affected defects.
As an affiliate, we earn on qualifying purchases.
A Faster Shift in Software Work
The account places today’s AI adoption alongside earlier changes such as the spread of the internet, smartphones, cloud computing and new programming languages and frameworks. Its author argues that AI’s impact is moving at an unusually large scale and pace, particularly after improvements in models’ coding abilities around the end of 2025.
That comparison is an interpretation rather than a measured ranking of technological shifts. Martin Fowler, an industry veteran quoted in the report, said AI’s magnitude was unlike earlier changes he had experienced. The report’s broader point is that established engineering tools and practices are changing quickly, while teams and planning remain important and many parts of software work have not been replaced.
“Nothing has hit with the magnitude of AI. This is a whole size difference from anything that we’ve faced before.”
— Martin Fowler, industry veteran, speaking at The Pragmatic Summit
software development code review software
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
How Broad Is the Shift?
The source material does not provide a representative survey, sample size or detailed methodology for claims that most engineers have stopped writing code by hand. Its examples come from selected practitioners, company access and the author’s observations. It is not clear how typical those workflows are across companies, job levels or types of software.
The reported declines in quality and reliability are also not accompanied by figures, a baseline or a time window. The source does not establish whether those problems are caused by AI use, how organizations measure them, or whether some teams have improved outcomes. The extent to which non-engineers are using agents to ship code is likewise not quantified.
integrated development environment (IDE) alternatives
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
Agent Tools and Practices Ahead
The report expects cloud-based coding agents and new AI infrastructure to develop further, alongside changes in the tools and practices engineers use. These are forecasts in the report, not confirmed outcomes or a dated product roadmap. It also suggests engineers may spend less time reading code directly, a prediction whose implications for accountability and maintenance remain unsettled.
The next useful evidence will be broader data on adoption, engineering output and software defects, as well as details on how companies review and test agent-generated changes. The source describes the industry as changing rapidly, but it does not identify a single forthcoming event or milestone that will resolve these open questions.
AI code testing and reliability tools
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
Key Questions
What is the main change in software engineering described?
Some developers are using multiple AI coding agents in parallel, shifting part of their work from writing code directly to directing and checking agent output.
Does the report show that most engineers no longer write code by hand?
No. The report says there are signs of that shift and provides examples from individual developers, but it gives no representative survey or adoption figures to establish how common the practice is.
What problems does the report identify?
It flags concerns about generated-code assumptions, code review, quality and reliability. The material does not quantify these issues or prove that AI caused them.
What is expected to change next?
The report anticipates further development of cloud coding agents and AI infrastructure, along with changes in engineering workflows. These are forecasts, not confirmed outcomes.
Source: rss
Halloween Picks
halloween
As an affiliate, we earn on qualifying purchases.
