Independent AI consulting & software engineering
I help founders and product teams turn promising ideas into software that works in the real world, from choosing the right problem to building and integrating the solution.
Led by Austin BurgardBased in St. LouisWorking remotely
Three kinds of work, often in sequence. Each engagement is scoped to your situation, so we start wherever you are.
Before any code, I look at how the work happens today: the workflows, the data, the constraints, and the people involved. Together we decide whether AI fits, what is feasible, and what success should mean.
What you get
I design and build AI features, internal tools, and integrations that connect to the systems you already use. The code is written so your team can read it, run it, and extend it.
What you get
A prototype that works once is a starting point. I test it on real devices, add failure handling and cost limits, and write down why we chose what we chose.
What you get
Illustrative example · Not a client result
As a system
You work with me directly, from the first conversation to the handoff. I build with AI coding agents, and I review and test everything they write before it reaches you.
Before building, I map how things work today and how others solve it, then write it down so we agree.
A short plan. Flags, tables, and services that haven’t earned their place get cut.
Small changes, each reviewed and tried on a real phone or browser. Staging first, then production.
Working code, one-command setup, and a note on what’s done, what’s deferred, and why.
Judgment & responsibility
If a piece isn’t pulling its weight, it comes out. Dead code, unused flags, extra services.
I click through the real thing and try to break it. Clunky, jarring, or generic isn’t done.
AI acts when someone clearly asks, keeps a visible log, and every action can be undone.
The cheapest model that does the job, providers you can swap, and caps on expensive calls.
I’m a senior product engineer with seven years of experience shipping software: full-stack applications, AI pipelines, and platform infrastructure. On my own time I build iOS apps: Offshelf is live on the App Store, and Almost Dawn is in beta.
I started Sólito to work closely with founders and small teams on problems where careful engineering matters as much as the idea. I like problems that are real, scopes that are honest, and work that is measured.
I help you decide where AI belongs in your product, then build it. That means looking at the workflow and data first, picking the smallest feature worth shipping, building it into your existing codebase, and testing it against real examples so you know it works before customers see it.
Start with a free 30-minute conversation. We walk through the idea, the workflow it touches, and the data involved. I’ll tell you plainly whether AI fits, or whether something simpler would do the job better. Sometimes the right answer is a rule, a form, or a better query.
Most first features take two to six weeks. After our first conversation, you get a written proposal within three business days, with the deliverables, what’s excluded, milestones, and acceptance checks you can run yourself. You see a demo and a short written update every week.
Builds are fixed price and fixed scope, agreed in the written proposal before any work starts, so there are no hourly surprises. Ongoing support after launch is available as a monthly arrangement you can cancel with 30 days’ notice.
Yes. Everything lives in your repository and runs in your environment. The handoff includes a README, a runbook, one-command setup, and a walkthrough with your team, so your engineers can run and extend it without me.
The cheapest model that does the job well. Each project includes a model and vendor recommendation with an estimated cost per use and notes on how your data is handled. I build so providers can be swapped later, and I add caps on expensive calls.
It’s planned for. Every build includes an evaluation set of 20 to 50 real examples you can rerun, defined behavior when an answer is wrong or uncertain, and human review where mistakes would matter. Logging shows errors and cost over time.
Yes. Sólito is based in St. Louis and works remotely with teams across the United States. Local teams can meet in person when it helps.
Send me a short note. A few sentences is enough, and I read every message myself. The first conversation is free, and if it’s a fit, you get a written proposal within three business days. It helps to know:
