Daniel Zuloaga
Building AI-powered products that solve real business problems.
Software engineer • Technical product manager • MBA. I build AI-first products, automate complex workflows, and turn ambitious ideas into scalable software.
What I'm building now
I'm working on agent orchestration across lending workflows, from lead generation to loan servicing: document ingestion, tool-calling pipelines, custom MCP servers, tailored RAG pipelines and more. The technical complexity is fading away, but the build is just a small part of the equation; the real challenge is the rest: knowing what to work on to get adoption, governance, training, and getting your team and your clients delighted with your products.
What's new
AI collapsed product and engineering into one role for me. I can go from a workflow problem to a shipped agent in hours, not weeks, but the abstractions to solve the real problems and the interfaces that bring a quality experience are harder to get right.
Recent notes
Systems, constraints, and notes from the build.
- Design AI workflows like access can breakAI access is now a business dependency. Dependencies fail. Here is how to build workflows that survive.
- The uneven days of building with agentsSome days agentic coding feels like flight. Other days you wander into alleys you did not mean to enter. A personal note on flow, dread, tools, and what still matters when the frontier keeps moving.
- What changes when an agent can do the boring part?A personal note on loan onboarding, AI agents, and the small shift that happens when software can run the work, show its mistakes, and get corrected.
- 11 illustration styles that work well with AI image modelsThe same scene recreated in 11 styles across GPT Image and Gemini, with the exact prompt blocks I used and notes on what held up.