You can totally ask an agent to orchestrate an existing cloud. But their APIs weren't designed for agentic orchestration, so it'll be more expensive in terms of context / turns (machine0 grammar is simple: new, ls, rm...).
The other thing is if you're running large workloads that span many machines (e.g. software factories, model training or RL environments), then over time you'll end up with orphaned artifacts that will need to be maintained (think security groups, volumes, elastic IPs etc).
Ultimately, most of our customers today just want to be able to spin up a powerful & reliable VM without worrying about DevOps or any other kind of maintenance :)
But, I don’t think this is your strongest argument. The APIs for those providers are pretty easy to orchestrate and don’t take that many tokens to use. (Especially if you are hosting on top of one of these providers)
Instead, I think some strengths you could focus on are (a) not being one of those providers, (b) having a better product mix that people want to use, and (c) keeping a minimal design. Clear use-cases, minimal friction, easy to keep the model in your head.
You definitely have a good product here with plenty of reasons to choose you. But your minimal API isn’t a great moat.
OpenRouter is valuable because it has a large catalogue of competing providers for a fungible service. This does the opposite (lock in with a specific vendor).
Insights are nice for new users but I’m not seeing anything too different from how anyone experienced with Claude Code would use plan mode. You can reject plans with feedback directly in the CLI.
Wow, I've been needing this! The one issue I’ve had with terminals is reviewing plans, and desiring the ability to provide feedback on specific plan sections in a more organized way.
I'm not sure how to mitigate the data selling concern or what to show you there. But we're trying to upsell a paid service via nice free utility. We send your data to use AI to generate the resume, that is part of the deal. So if you wouldn't give your data to ChatGPT, don't give it to us (delete it from linkedin also - because your principles sound weak while you let it reside there). We store the data so that paid users can reference their linkedin profiles. Feel free to request a delete and we'll do so with adequate proof: support at cvgist dot com.
Google in fact allows minified code, not obfuscated.
Using LinkedIn is a highly desired feature in the resume builder business. Highly successful firms are using 3rd party services that scrape your profile (already have) without your consent.
So, no, you can parse the minified code all you like - the advantage we have with my implementation is competitors spend minutes scraping while we dont need to.
- Which as you've inherently figured out, is not that insightful.
- The extension codebase is small and doesnt communicate with any server
Your extension works on people's profiles that are not your own (if you paid for the enterprise ability, according to the extension's code). So is this not aiding with scraping peoples' data?
Tried to use the tool and it never worked (just no reaction after clicking on the "generate" button). Disabled the adblocker to see if it was the cause but with the same result. Getting a "'Save to PDF' button not found
" error in console.
Not sure how to fix it. Thought you might like to know.
It looks like it taps into the LinkedIn pdf resume. Do you have the ability to download that on your profile? There is a button on everyone’s profile (usually) in the header section called “resources”
What are you doing here that my agent couldn't do with: AWS, GCP, Hetzner, DigitialOcean?
Quick read is this is some simple api abstraction? or you're even brokering that compute? Which i would want, why?