I build resilient software with a craftsman’s care — the kind that holds up when the demo ends. Lately: an in-house agentic AI “code factory,” MCP integrations, and the plumbing that makes AI reliable in production.
Most of my blog's readers are no longer human — they're agents scraping, summarizing, and citing it. Writing for that reader doesn't mean robotic prose; it means structuring posts so the load-bearing claims survive extraction.
After a year of building agents at Axonify, the thing that actually changed how my team ships isn't a smarter model — it's the Model Context Protocol. Here's why.
Prompt engineering was a useful crutch when models were small and dumb. With Claude Opus 4.7 and a million-token window, the real lever is what you put in the context, not how you phrase it.
| may 25, 2026 | Write Your Blog for the Agent That Will Cite It | Most of my blog's readers are no longer human — they're agents scraping, summa… | #agentic-ai#writing#content-strategy |
| may 20, 2026 | MCP Is the Real Unlock for Agentic Engineering | After a year of building agents at Axonify, the thing that actually changed ho… | #mcp#agentic-ai#tooling |
| april 12, 2026 | Stop Prompt Engineering. Start Context Engineering. | Prompt engineering was a useful crutch when models were small and dumb. With C… | #llms#prompting#context |
Six years at Axonify — developer to principal, now leading AI initiatives — plus a healthcare-frontend stint and a startup I co-founded. Full résumé on request.
Two modes. Ask anything about how I work, or paste a job description and get a candid fit assessment. No login. No vendor tracking.