Daniel Zuloaga
I build useful software, write down what I learn, and spend time in the messy middle where ideas turn into working systems.
Most of my work has lived around finance, software, operations, and lately AI. The through line is making confusing things clearer, then turning that clarity into something people can actually use.
Useful systems, plain language
I tend to orbit problems that have too many tabs open: old workflows, new tools, half-formed ideas, and teams trying to make sense of change.
- Finding the small question underneath the big, vague one.
- Turning repeatable work into tools instead of rituals.
- Writing and building in public enough that the thinking gets sharper.
Learning out loud
I'm spending a lot of time with AI tools, not as a pitch, but as a way to rethink how people work, review, correct, and teach software over time.
Recent notes
Working through software, systems, and how work changes.
- The uneven days of building with agents Some 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 models The same scene recreated in 11 styles across GPT Image and Gemini, with the exact prompt blocks I used and notes on what held up.
- How Git worktrees work A practical mental model for using Git worktrees so you and your AI agents can work in parallel.
Send the unfinished version
You do not need a polished brief. A half-shaped idea, a stuck workflow, or a question you keep circling is usually enough to start a useful conversation.