Producing code has never been easier, but AI-generated bugs and rising debugging workloads are slowing software delivery

Undo research finds 81% of organizations have had a production incident or service outage linked to their use of AI coding tools, with 35% of code reaching production before engineers have fully comprehended it

Cambridge, UK, September 28, 2026 – New research from Undo, the technology that gives developers the runtime context needed to solve the most challenging problems in the most complex codebases, finds that almost four in five (79%) engineering leaders say their release cycles are no faster than before, despite their teams being able to produce code more easily than at any time in their careers. 

As AI agents have increased the volume of code they can create, engineers now spend nearly twice as long debugging it as they do producing it, averaging 16.9 hours a week. That accounts for 42% of the average working week. Engineers are simply unable to keep up with their agents, leading to more than a third (35%) of AI-generated code reaching production before they’ve fully comprehended it. 

Adding to the risk, AI agents frequently hallucinate the cause of failures or fail to identify problems in the codebase entirely. In the past six months, as a result of their use of AI coding tools:

• 81% of organizations have had a production incident or service outage affecting internal users or customers
• 93% have had the root cause of an issue incorrectly diagnosed because of an AI hallucination
• 91% have had test escapes, serious defects or poorly optimized code enter production

“When code is obviously broken, the cause is usually easy to find,” said Greg Law, founder and CEO of Undo. “Where engineers struggle is with code that’s almost, but not quite right. Those are the times they lose days trying to unravel what went wrong and why. Their challenge is that while agents are great at writing reams of code quickly, they’re less capable at debugging it. The result is engineers are being buried in an avalanche of code that’s well beyond human capacity to debug. That’s why we have to give them a way to make AI better at debugging, by feeding agents with the rich context of what code actually does at runtime.” 

Four in five (80%) engineering leaders say coding agents struggle to solve difficult problems in large-scale, complex codebases. The arrival of more powerful models doesn’t offer a realistic solution, with a strong degree of cynicism about the impact the planned IPOs of Anthropic and OpenAI will have on AI affordability. The majority (82%) of engineering leaders think the costs of coding agents will go ‘through the roof’ as the AI labs prioritize making Wall Street happy.

However, engineering leaders widely agree that improving model context is more important than increasing their capability to make AI more powerful. More than four in five (82%) say AI agents would be far more useful for code comprehension and debugging if they were grounded in the context of what happened during runtime.

“AI doesn’t have an intelligence problem; it has an evidence problem,” continued Law. “An agent asked to explain why a program behaved the way it did without ever being shown what actually happened will fill in the gaps with confident guesses. That’s how days are lost with humans and agents going down blind alleys in a futile search for the root cause of critical issues that must be fixed. Give an agent a complete recording of what happened at runtime and it can see the precise sequence of steps leading to what went wrong, rather than have it trying to guess. The right context even makes a mid-tier model more capable of providing an accurate diagnosis than a top-end model working from source code or logs alone. The result is AI that is smarter, faster and cheaper.”

To learn more, download the full Overcoming the limitations of coding agents in complex software systems report here: https://undo.io/research-report-2026

Methodology

The research was conducted on behalf of Undo by independent research firm Coleman Parkes during July and August 2026. It surveyed 300 senior engineering leaders at organizations with revenues of $250m or above that deliver mission-critical software built on large, complex codebases, 93% of whom work with C/C++. Respondents were based in the United States (200) and the UK (100), across financial services, networking, semiconductor design, computational software and data management.

About Undo

Undo enables coding agents to solve the most complex problems on the most complex codebases. By providing a deterministic, self-contained, portable recording of complete program execution, Undo enables engineering teams to give their agents the runtime context they need to reason about dynamic application behavior in the same way they already reason about static code. The result: fully automated root-cause analysis. With Undo, developers have been able to solve problems up to 100x faster in some of the world’s most demanding software environments including at AMD, AWS, Cisco, and Palo Alto Networks.

To find out how Undo could help your engineering team unlock the potential of AI agents, visit: https://undo.io/