A developer outlines a test automation strategy for keeping pipelines in step with AI-accelerated coding, arguing the bottleneck has shifted from development to testing. The approach starts with measu…
A hands-on developer outlines a workflow for leading AI coding agents that begins with documenting project rules in a repository-root instruction file the agent loads at the start of every session, co…
A developer's analysis of coding agent architecture shows that swapping only the harness around a fixed model — keeping weights, tasks and context window constant — raised SWE-bench Verified bug-fixin…
A RubyConf 2026 keynote and a widely-read essay by a veteran practitioner argue that AI code generation is eroding developers' understanding of the software they ship, invoking Giambattista Vico's Ver…
An LLM-based test-locator healer produced false-heals roughly one-quarter of the time, according to a preprint cited by the author of a cross-layer observability analysis, meaning tests kept passing w…
Birgitta Böckeler's October 2025 analysis of spec-driven development tools Kiro, spec-kit and Tessl sorted approaches into three levels — spec-first, spec-anchored and spec-as-source — and found that …
A developer argues that spec-driven development is not inherently waterfall, distinguishing the practice from waterfall by focusing on batch size and phase gates rather than whether software intent is…
Thoughtworks' Birgitta Böckeler argues that AI's surge in code production—Meta reported a 106% increase in significant lines of code per human-landed diff in a year, and DX data shows median pull requ…
Spec-driven development tools like Amazon Kiro, GitHub Spec Kit, and BMad Method fail in enterprise settings because they assume greenfield projects, according to a post promoting the AI Unified Proce…
A new analysis argues that as AI coding tools make implementation cheap, software architecture becomes more important and visible, with verification replacing code generation as the bottleneck. Dex Ho…
Answers are now cheap and instant with large language models, but the bottleneck has shifted to framing questions well, according to a senior engineer's essay. The piece argues that stating constraint…
Martin Fowler says context is the bottleneck for coding agents, and a developer's experience shows that inconsistent code stems from ambiguous domain vocabulary, not weak models. In an enterprise NL-t…
AI agents now perform real work, but companies lack automated checks for judgment-based tasks like writing and strategy, according to an essay by an unnamed author on Inside AI Native. The author argu…
Software development is shifting from writing code to orchestrating AI agents, and human attention has become the bottleneck, according to Martin Fowler's CTO, who compares the role to a conductor. De…
Thoughtworks' podcast episode on the future of software engineering highlighted open problems in agentic engineering, and a developer responded by detailing how their IRC-A architecture addresses thes…
An agent run is stochastic gradient descent over solution space, and steering is how the true objective enters the loop, according to a July 26, 2026 post that grounds the industry ladder of prompt, c…
Generative AI has made writing code nearly free, shifting software engineering's value from code production to clarity, specifications, architecture, and code review. Developer Kodel introduces Spec D…
Programming undergoes a technology shift roughly every decade, but the engineering fundamentals remain unchanged, argues Fagner Brack in a Medium essay. Each cycle—from punch cards to AI agents—rename…
The bottleneck in AI-assisted engineering is spec review and definition, not code review, according to engineer Jelmer Snoeck, who argues that code generation has become cheap while review remains exp…
Honeycomb completed a multi-month migration of its Kafka infrastructure from self-hosted Confluent Platform and ZooKeeper on AWS EC2 to open-source Apache Kafka 4.1.1 running in KRaft mode on AWS EKS.…