Solo studio · Since 2015
Wildflower Software is one senior engineer, not an agency. I write the code and make the architecture calls, and I'm still around long enough to find out whether they were the right ones.
What I do
Every engagement starts with a written plan. It ends with code you own and a team that knows how it works without calling me.
Senior Django help for the work your team keeps postponing.
Learn more →Getting an LLM feature from a demo that works to something you can actually run.
Learn more →Getting your deploy process to the point where nobody dreads it.
Learn more →Embedded with your team for a sprint or a quarter. Architecture reviews, pairing, upgrade plans. Mostly it's making a codebase predictable enough that people stop dreading it.
How engagements workNew Django apps and AI features, built end to end: schema, background jobs, evals, deploy pipeline. I write the runbook too, because I'm not going to be here forever.
Talk about a buildNotes
What an AI gateway does, whether the flower shop agents need one, how LiteLLM, Portkey, Cloudflare and Kong compare, and how I put gateways in for clients. For the people buying and the people building.
I moved the flower shop example's tools onto an MCP server with FastMCP. The agents barely changed. The real decision was where the list of safe tools should live.
How I build AI worker-agent systems for businesses of any size: narrow workers, a coordinator, and an approval gate enforced in code, with a working flower shop example.
Slow queries, a Django upgrade you keep postponing, an AI feature that needs to survive production. Tell me about it.