The cost of writing code is collapsing, changing software development dynamics.
“The cost of writing code collapsed, and the cost of reviewing, fixing and operating it is following.”
agentic-engineering
13 tracked signals on agentic-engineering.
Datasette releases security patches addressing critical vulnerabilities.
“We'll be incorporating security audits by frontier models into all of our development work going forward.”
DHH reversed AI skepticism after Claude Opus 4.5, calling it the dividing line to agentic coding
“I give it a couple of tasks, and I realize that the quality of the output is uncannily close to what I would've written. And I remember just leaning back and thinking, "What just happened?"”
Block transformed its 3,500-person engineering org toward autonomous, agent-driven workflows despite AI adoption not yet boosting shipping speed.
“But our CEO was convinced that engineering wasn't using AI at all.”
Coding agents will make general-purpose platforms obsolete by generating bespoke implementations from specifications on demand.
“The product is no longer the implementation. The product is the specification, the protocol.”
Cognition launches FrontierCode, a benchmark grading code quality and maintainability over passing-test 'slop'.
“Many SWE-bench-Passing PRs Would Not Be Merged into Main”
Professional AI-assisted coding needs a new term—'agentic engineering'—distinct from casual 'vibe coding,' with verification as the core challenge.
“when you fully give into the vibes, embrace exponentials, and forget that the code even exists”
Effective coding agent use requires confident instruction and verification, not just line-by-line review
“The key skill required to make productive use of coding agents is being able to confidently instruct them on how to make changes and then confidently verify that those changes have been applied in the correct way.”
Teams should stay model-agnostic because the best AI model can change weekly
“the incentives of the people selling you tokens aren't really aligned”
Jon Udell argues we should reframe 'human in the loop' as inviting agents into our development loop, not joining theirs.
“I dislike the phrase “human in the loop” because it cedes authority to the machines.”
NearForm uses AI agents and spec-driven development to iteratively build more reliable, secure AI agents.
“an agent is an LLM inside a an agentic loop, which is connected to tools and can retrieve context. That's it.”
Decision records like ADRs help both humans and LLMs overcome limited context and lost institutional knowledge.
“People forget. LLMs context compact. Humans leave. LLMs have no memory.”
Simon Willison and Jesse Vincent are hosting an informal SF show-and-tell for people building experiments on top of coding agents.
“This isn't about product pitches, it's about much earlier explorations than that. This agentic AI stuff is weird! Let's celebrate and lean into that weirdness.”