Location: Austin, TX

Remote: Yes

Willing to relocate: Prefer remote

Technologies: Agnostic. 15 years of backend and full-stack experience, but now focus on the AI integration stack (JavaScript/Python).

Résumé/CV: https://linkedin.com/in/matthewbmay | https://github.com/mzxrai

Email: matt@goodsoftware.dev

--

Hi all, I'm Matt May - a freelance AI consultant with 15 years of software engineering experience. I've worked with Fortune 150 companies, startups, and everything in between, and have done AI research at Stanford & Georgia Tech.

If you're planning or working on an AI implementation, I'd love to chat. My specialities include: AI integration/implementation, complex backend development, APIs, AI strategy, and legacy SaaS replacement.

I've worked remotely for years, but can travel as needed.

Drop me a line. Happy to jump on a video call anytime!

SEEKING WORK - AI integration/implementation - Austin, TX & Worldwide Remote

Hi all, I'm a freelance AI consultant with 15 years of software engineering experience. I work with large companies, startups, and everything in between.

If you're beginning or considering an AI implementation in 2026, I'd love to chat. My specialities include: AI integration/implementation, complex backend development, APIs, AI strategy development, and legacy SaaS replacement.

Drop me a line. Happy to jump on a video call anytime to learn more about your needs.

Text: (512) 417-7608

Email: matt@goodsoftware.dev

LinkedIn: https://www.linkedin.com/in/matthewbmay/

Github: https://github.com/mzxrai

Ratatui is awesome! Just built a little chat client with it, tons of fun.

https://terma.mattmay.dev/

Is the problem the generation step, or the review step?

Memva, Claude Code for sales: https://memva.com/

Neat tool, thanks for sharing your work!

Agreed, it's an interesting model. I wonder what the approval ui looks like for the app end-user? Is it super clear to them that they're financially responsible for their usage?

Yeah I wonder how that actually works - because I would guess people are logging in with their consumer login not an api login, so they’re not really even in the mindset of limits and cost per token.

Precisely. You click on a claude link, and suddenly it's, "You are now financially responsible for your actions from here on..." I'm sure they've spent a lot of time thinking through the ui/ux of this.

Users of Claude-hosted apps can't thereby incur financial liability, because it counts against the usage limit of their consumer Claude plan, which either is free or has a fixed monthly subscription price. The worst that can happen is that they run out of quota and can't use Claude anymore until it resets, which happens every day on free plans and every five hours on paid ones. In no case is usage attributed to an API key with metered pricing.

Ah true. So the push becomes even stronger for people to upgrade to the max plans, when several of the "apps" they're using are consuming their allocated Claude tokens. Brilliant.

Awesome anecdote, thanks for sharing this. How do product marketing and support engineering folks feel about the change?

Nice job! A couple questions for you guys:

- Did you personally end up getting offers using your own tool?

- Anything surprising you learned building it?

Yep, we actually did. reaching out on linkedin DMs to CEOs, has to be thought through though.

Also - the tool does indicate why you're likely not a good fit.

technically - yes: vibe coding doesn't work xD

talking to customer - yes: some people have issues passing interviews, less getting into 1st calls

Interesting, so instruction-following troubles and also uncertainty by the model on which MCPs it should be using for a given task.