Parallel isn't coordinated: the real bottleneck in agentic coding
“Analysis is running in parallel (4 agents)…”
“Analysis is running in parallel (4 agents)…”
Here’s a small, uncomfortable fact about the AI agents everyone is rushing to deploy.
I tagged a Go module v1.0.0, pushed it, and watched a teammate’s go get come back with invalid version: unknown revision. The tag was sitting right there on GitHub. The commit e...
Every Goose session I run that touches infrastructure is authenticated with my credentials. My kubeconfig, my AWS profile, my GitHub token sitting in the shell environment. When...
Every MCP server I’ve added to my Goose setup has been its own small project. Some are a git clone and a config path. Some need pip install and the right virtual environment. A ...
I spent a big part of the last year integrating supply chain security into SDLC pipelines - provenance with SLSA, attestation with in-toto, SBOMs with CycloneDX, signing with Si...
There’s a pattern I keep seeing in tutorials for Goose: the author installs it, gives it their default kubeconfig or shell, and runs a demo. In my first post I framed agents as ...
I’ve spent twenty years designing and evolving large-scale, business-critical systems. Mostly platform engineering, DevSecOps, IAM, and lately software supply chain security. Th...