Jev is TypeSafe AI’s first public “System One” model. Instead of generating text, it answers typed questions about the context you provide. For example, which team should handle a support ticket, how frustrated the customer sounds, or whether the message is urgent. Its answers include probabilities.

That makes it worth considering for workflows where software needs a judgment rather than a written response. This article looks at the API, several implementation patterns, and the limitations you should evaluate before using it in production.

The examples reflect documentation and community material available as of September 28, 2026. Jev was still in early access, so check the current SDK reference before using the code.

Continue reading →

Script from my podcast at – AI – AI Development Life Cycle

Teams using AI are shipping more than they ever have. They’re also breaking things more than they ever have. And the burnout that all this speed was supposed to fix? That still exists.

The 2025 DORA report notes that AI adoption among software development professionals is at ninety percent now. That’s not a trend anymore; that’s the baseline. The same report found that higher AI adoption correlates with increased delivery but it also correlates with increased delivery instability. Output is up. But the health of the system around that output hasn’t caught up. Speed rose; the structure around it didn’t.

Continue reading →

I am really excited about GitHub Copilot, a AI code pair programming capability. While good editors do provide some inbuilt code completion features, this is the first one I used that leans on AI to suggest code completions.

Continue reading →

I will begin by saying ” DON’T EVER DO THIS IN THE REAL WORLD”. https://github.com/auchenberg/volkswagen will detect if your build is running inside a CI tool and then force all tests to pass; even if they fail. Now you know why I said “DON’T EVER DO THIS IN THE REAL WORLD”. Hey just having some fun … code quality purists you have been warned not to read further! 🙂

Continue reading →

Just came across a nice dev tool to build and deploy Docker’ized applications. A developer may want to independently build/deploy to a local docker container or another Kubernetes cluster vs. waiting for a remote CI/CD process to deploy to a dev environment. This involves some repetitive tasks such as building the binary, packaging into a Docker container, pushing to a Docker registry and all the way to deploying to a running container. If you run this often it can be a time suck for developers. forge.sh takes away those repetitive steps and lets you build/deploy locally or to another cluster.

Continue reading →

Have you worked in a high performance engineering (HiPeE) team, how do you know you are in one and why is it so hard to replicate that?  Are there factors that make it possible for HiPeE teams to grow and sustain. This was a topic of discussion at a recent chat with a few folks. I speak from my own experiences having seen HiPeE teams and was lucky enough to be part of it couple of times. It came down to a few dimensions for me.

Continue reading →