Tag: codegeneration
-
Enterprise architect as context engineer
Sadly: the major issue with EA has always been cost of delay. The big problem is not that architecture tells development teams to change direction — development teams do this routinely. The problem is that architecture historically has taken too long. We have validated that assertion repeatedly with many chief EA pros. Now with agentic…
-
programmers are managers now
The central task becomes describing an objective precisely enough for the system to divide it, establishing the rules under which the agents operate, and judging whether their collective output belongs in the codebase. 🔗 Claude Code Turns Software Development Into a Management Job
-
Inside OpenAI’s agentic software factory
We’re talking about roughly a 10x increase in load on some systems. At most companies, that kind of growth might happen over two or three years. At OpenAI, we see it in about six months. 🔗 Inside OpenAI’s agentic software factory
-
The Interfaces Are Arriving
For an engineering organization, the immediate consequence is reuse. An MCP server for an internal ticketing system can serve every compatible IDE, chat application, and agent. Models and hosts will keep changing; the interface contract, server implementation, schemas, and authorization wiring can endure. The integration becomes an asset shared across applications. Language servers followed the…
-
Slop Is Really Good Now. Slop Is Where We Start Now
When the baseline is good enough, being intentional about which aspects need to be great is the whole job. The floor is rising; our job is to spot how to raise it further. Design here is knowing how to articulate and leverage craft. That’s a real opportunity for designers to be articulate, and to work…
-
Your coding agent got the onboarding your developers never did
before you tune the tone of your next prompt, look at the AGENTS.md file your team wrote this quarter, and ask why the onboarding doc for your newest hire still doesn’t exist. 🔗 Your coding agent got the onboarding your developers never did
-
the programmer’s boss is not competition
Perhaps more intriguing is the makeup of that adoption, and how it appears to be blurring roles. Senior leaders are doing more of the hands-on IC work, adopting AI aggressively to help them do it, and non-engineers are committing code. The suggestion that everyone in an organization is becoming a “builder” seems to be directionally…
-
We need more than a metaphor: here are testable diagnostics for comprehension debt
“Comprehension debt” In Sonar’s State of Code Developer survey from January, 96% of developers said they don’t fully trust that AI-generated code is correct, but only 48% of them check it before committing. This stat is old now relative to the pace of AI adoption, but based on my continual interviews and conversations with development…
-
There is no organizational-level ROI for AI, just IC ROI
The best theory of elusive enterprise AI ROI yet: AI makes workers more productive, not organization: “How can you reconcile the failure of AI in the enterprise with the individual claims of skilled technologists who insist that AI is helping them do great work?” The answer is that these AI users are “centaurs” — experienced…
-
Reorganizing the dev teams at Visa to take advantage of AI
When you speed up the SDLC process, you should collapse silo’ed teams into one team to prevent human bottlenecks based on handoffs. Here’s that at Visa: As a result of the unlocks we can realize with this new tooling, we are re-forming our product development teams that used to be 10 or more into smaller…
-
Relative to your interests, Wednesday
After reading many of the below and other links in elusive enterprise AI ROI, I wrote this theory on how to be successful with enterprise AI projects. It’s the usual “culture” cliché, but hopefully a little more practical than usual. Are PMs becoming irrelevant? – Once you remove the need for a bunch of “paperwork,”…
-
Relative to your interests, Tuesday
I have been on vacation for a little while, in Finland for the third time. Finland feels different than the other parts of Europe I have been to. Perhaps it’s because I spent my time there in rural Finland. But it also feels like most of Finland is rural. In that way, it feels a…
-
short feedback loops always works
Using short feedback loops to experiment and direct software development is always a good idea, especially with AI: What survives from Agile is the feedback logic. Short cycles still matter. Thin vertical slices still matter. Customer or stakeholder review still matters. Working software is still better than progress theater because agents can generate a lot…
-
Enterprise Java apps are much more than just code, AI benchmarks don’t measure the Java SDLC enough
There’s countless dependencies in other frameworks and libraries, plus the build pipeline and even production platform are part of the app. Enterprise Java applications frequently span hundreds or thousands of modules connected through Maven or Gradle builds, Spring dependency injection, Jakarta EE services, annotation processors, generated code, legacy XML configuration, container orchestration, proprietary build plugins,…
-
Harness engineering is the new DevOps
Are we going to see harness engineering teams? Yes: these are already emerging. It’s too early to say, but that feels wrong in the same way that DevOps teams were a misunderstanding of DevOps-the-movement. My belief is that while there is friction in having every team create their own harness, that friction is generative and…
-
training your replacement
Yes: the work is moving from writing code to specifying, verifying, and curating knowledge. But: the code is the better spec. Their point: code is the only artifact that’s unambiguous, executable, and – this is the big one – deterministic. A prose spec is fuzzy and an agent will interpret it a little differently every…
-
Reducing token usage
Better Defaults (not Usage Caps) — Engineers can choose any model they want, but defaults matter. We’re experimenting with defaulting to open weight models like GLM 5.2 and Kimi 2.7 through our LLM gateway, while still encouraging engineers to choose the right model for the task. 91% of our employees were never hitting their usage…
-
Developer Productivity in the Age of Generative AI: A Psychological Perspective
Developer productivity in the age of generative AI, examined from a psychological perspective rather than a throughput one. Summarized by AI. 🔗 Developer Productivity in the Age of Generative AI: A Psychological Perspective
You must be logged in to post a comment.