I was doing it for Veterinary (ambient recording -> SOAP notes) which has tons of complex domain-specific language AND it is critically important to get right.

“CPR” transcribing as “see pee are” just doesn’t cut it in that industry.

eg https://news.ycombinator.com/item?id=49088205

On the other hand, I have a custom harness agent running an ecommerce business 100% autonomously at this point, but have very little to benefit from trying to “publish” anything about it - and without a Stanford or YC stamp, I doubt anyone would care much anyway

Writing code has never been the hard part.

Not for Bob, not for you.

I acquire and operate ecommerce companies, and build a lot of workflows with openclaw-like agents (my own stack).

When it’s working really well, there’s literally no interface needed besides iMessage and email. I’ve built a SaaS app interface style largely to show it off for demos because invisible tools don’t make for great demos

https://claude.ai/public/artifacts/d49d81d6-7aab-4730-9c3c-4...

Which I’m sharing as a meta point…I think self help books are declining because there’s a better way to get the information without all the filler. But filler makes the books thick enough to sell at the airport

Also - aren’t LLMs the ultimate choose your own adventure version of the information?

I set up my claw to be able to do that and it’s infinitely better than searching through hours of content myself.

I set it up as experts on topics I already know and like to reduce noise. So I can say “ask [NAME] what I should do about XYZ” and I get back contextualized info and cited video clips

The fun part being it worked on mobile too: https://youtube.com/shorts/CmemwDGwpx8?si=xzAJBb8ha7DLIDmY

It was more of a tool for myself but some interest from others inspired me so iterating on it. People interested in this kind of thing should join my slack! https://monetworkspace.com/terminal

Organize and manage dozens of claude code agents for you in a grid. Alerts when the agents need help. Keyboard driven. Dictation native. On Mac at your desktop or iPad/iPhone on the go.

--

This started as a nagging side project — I wanted to spend less time at my desk, improve my own posture and lifestyle and spend less time sitting at my desk and more time standing and dictating, sitting outside, or just making use of downtime.

As Claude Code and other agentic engineering tools have gotten good enough, I spend more time in system architect and product mindset and less time actually writing code..

But as they can run autonomously for longer and longer, I get incredibly bored and open a new tab and start on another feature...multiple sessions got increasingly overwhelming and unorganized. So I built Monet.

Releasing as an alpha at a discount. It's not a subscription. I'm bootstrapped and intend to stay that way. Just a one-year license, hopefully low enough price engineers can expense it.

On that note, it's all SQLlite running on your computer. If you want to use it on your phone you need to use a Tailscale VPN to access it directly. Nothing leaves the machine except to check for updates and validate the license key.

Even with some bugs, I can attest as the number one power user...it's a game changer. I encourage you to try it if you use Claude Code a lot.

Comments URL: https://news.ycombinator.com/item?id=47368568

Points: 1

# Comments: 0

https://www.gophergolfer.com/iphone

NextJS, Rails, GraphQL, React Native

Certainly wasn't one-shot for all of it but case in point it has dozens and dozens of "features" all LLM implemented

I'm genuinely curious, I feel very differently and excited about this agent thing.

Asking because unlike a lot of other commentary, this struck me as being more about the act itself than being depressed/anxious for financial reasons, etc

The stated optimization from Matz (who created Ruby) is “developer happiness”

The important optimization for me is “fidelity to business logic”, eg less cruft and ruby syntactic sugar means you could sit at your computer and read your business rules (in code) out loud in real time and be understood by a non-dev

As CTO at Redo do you demand everything written in assembly? Does your entire company’s code run in one file or do you use abstraction to simplify?

I’m not quite clear on how expressing a really complex and paradigm shifting approach of agents in a more concise way is a bad thing