While code generation tools have improved considerably, veteran developers still worry about system boundaries and behavior during real-world failures. This persistent wariness reflects a demand for strict operational guardrails rather than a dismissal of automated coding assistants. To examine these dynamics, a recent Thoughtworks experiment tasked senior staff with guiding agents to develop an airline application entirely from autonomous code. That project reached 80 percent completion, requiring the engineers to trade manual coding for extensive whiteboard sessions focused on system architecture.
Key points
Organizations lack historical experience managing production infrastructure that has been…: Organizations lack historical experience managing production infrastructure that has been constructed entirely by autonomous agents rather than humans.
Experienced engineers continue to supply critical domain context and pattern recognition…: Experienced engineers continue to supply critical domain context and pattern recognition that automated agents cannot successfully replicate.
Implementing agentic development shifts human engineering effort away from manual syntax…: Implementing agentic development shifts human engineering effort away from manual syntax writing toward domain modeling and boundary definition.
Sources checked by our analysis pipeline: 1
TL;DR
Good developers’ caution about agentic development comes from knowing that built isn’t the same as working in production.
I’ve been surprised by how many excellent developers have been hesitant to go all in on coding agents. These are people who usually try new ways of working before anyone else and in many cases invent new tools and practices that support building the application well. So why have we had so much reluctance?
The easy (lazy?) answer is that they love writing code, or they’re worried about their jobs. I’m sure that’s true for some people, some of the time. And I know it is true for some of the developers I talk to but I always felt there was something else, another fear hiding behind those obvious ones. When we put together the Technology Radar every six months I try to block out a chunk of time for us to do an open space. In September, a discussion we had on agentic development, which pushed it to its limits, finally helped me see clearly what that fear is.
Computational researchers have long relied on standard FP32 precision to prevent trajectory instability and maintain physical accuracy in molecular simulations, leaving specialized GPU hardware underutilized. By splitting full-precision operands into lower-precision components, new techniques leverage Tensor Core matrix-multiplication throughput without degrading physical fidelity. This approach delivers substantial inference acceleration while maintaining strict quantum-mechanical conservation laws without requir…
Meta has integrated an automated testing architecture into its live development environment to catch regressions across its massive codebase before changes are merged. The system uses large language models to construct executable, failing tests that reveal unexpected behavioral shifts introduced by newly submitted code updates. By combining algorithmic filtering with focused engineer oversight, the initiative aims to safeguard massive systems without overwhelming developers with unnecessary alerts.
The release of the 120-billion-parameter Nemotron 3.5 Super VL brings advanced multimodal intelligence and long-context processing directly to enterprise cloud environments. By open-sourcing the model weights, datasets, and post-training recipes, developers can tailor the system to internal workflows while hosting it securely on their own clusters. This setup enables high-throughput agentic tasks such as cybersecurity analysis and automated coding with reduced operational overhead.