Route every Claude Code message to the right model with Jev
jev-router asks Jev, a System One model, which Claude model each Claude Code message needs, and routes it there for a fraction of a cent.
Engin Diri


As a Principal Solutions Architect at Pulumi with over 15 years of experience in the IT industry, including roles at the Schwarz Group and W&W Versicherungen, I bring extensive expertise with an end-user and enterprise focus. Currently working for a startup while collaborating with enterprise clients has further enriched my experience!
I began my career as a Java backend developer, transitioned to frontend development, and ultimately specialized in CI/CD and DevOps. Working with ANT and Cruise Control to switch to Jenkins and Microsoft Team Foundation Server added some traumas on top! But as they say, what doesn’t kill you makes you stronger.
I have now embraced the dynamic world of DevOps and Platform Engineering, leveraging cloud technologies and Kubernetes.
jev-router asks Jev, a System One model, which Claude model each Claude Code message needs, and routes it there for a fraction of a cent.
Engin Diri

Ten coding agent habits checked against the research behind them, from AGENTS.md drift and /compact to model switching, subagents, and review.
Engin Diri

Prompt guardrails fail right when coding agents get dangerous. How Docker Sandboxes make YOLO mode safe, plus a ready-made kit for infrastructure work.
Engin Diri

Manage PagerDuty teams, schedules, escalation policies, and services with Pulumi, and wire alerting to the AWS infrastructure in the same program.
Engin Diri

Google's Open Knowledge Format: a one-page spec for the LLM wiki. Markdown, one required field, git. Why knowledge as code is your agent loop's missing layer.
Engin Diri

A zero-touch Ollama GPU inference server on AWS, Azure, or Google Cloud as one Pulumi program, with OIDC credentials from Pulumi ESC and no static keys.
Engin Diri

Deploy a self-hosted Hermes agent as one Pulumi program across Render, Modal, and Tailscale — a code-executing AI agent with nothing on the public internet.
Engin Diri

The unit of work moved from the prompt to the loop. The five pieces of loop engineering, the memory that makes it compound, and what it won't do for you.
Engin Diri

AI coding has two shapes: 2x is mostly prompting, 10x is mostly plumbing. The parallel coding playbook, translated to Pulumi.
Engin Diri

In a large codebase, the model is the smaller variable. The harness around it does the work: CLAUDE.md, hooks, skills, LSP, MCP, subagents.
Engin Diri
