Yeah, Google Sheets is a surprisingly powerful interface for business teams, especially when they’re the ones curating the data. Curious to see how Promptrepo fits into your workflow. Happy to help if you explore finetuning on top of your existing setup.
Depends on who’s using the tool. Developers might be fine coding a form into their app, but an HR person needs a form builder. Similarly, the data for training models usually lives with domain experts, but they don’t have a tool to actually do the training. That’s why, in this use case, a simple interface makes sense, IMO.
Don’t want to sound like a shill, but Google doesn’t use data from your Google Sheets to train its models or for advertising. By default, your data stays private and is protected under Google Workspace’s privacy policies.
You are still giving your data away to Google, and it's one line of ToS change from allowing them to do it. And we know this Lind of changes happen all the time.
I understand your concern. We’ve had cases where short-term users abused our product for phishing, which led us to remove the monthly plan initially. To address that without locking out genuine users, we’ve added an option to extend the trial for up to 3 months before choosing a monthly or yearly plan. Feel free to message me if you’d like more time.
When I see a product — especially an early-stage product — trying to funnel me into a yearly subscription, the signal I get is that you think I’ll quit in less than a year which, in turn, implies that your product isn’t very good. It just makes me trust you less.
There's some truth to that. Early stage products often start out rough and part of the journey is finding early users who believe in the potential enough to stick around while we improve.
That said, in our case, the switch away from monthly plans wasn't just about churn. We actually got shut down by GoDaddy due to phishing abuse [1], which forced us to rethink our approach. We've since added a flexible trial extension to avoid punishing genuine users, but I’m open to feedback and willing to change if enough people feel strongly.
This is anecdotal but I often buy yearly plans on products that I've got a pretty good idea that I'll use, even if it's the first time I buy them. Though I'll freely admit it's always been the option of getting 1-2 months for "free" by signing up for the yearly plan. I've done it with various products, Proton, Disney+ (which saved them from my Danish boycot wrath to my daughter's delight) and so on. I've never even thought about it as a way of tricking me into buying the yearly plan, and now that I've thought a bit about it, I don't think your pricing would either. It's hard to say how I would've thought if I'd looked at the pricing page before reading these comments, but I genuinely don't believe I would've thought of it like that.
That being said, I would not base my pricing too much on a few random comments on HN. These responses can be a good indication, but I'd frankly reach out to some of my trial sign-ups who didn't transition into a paying client as well as some of my actual customers to get their view on it. I think pricing is going to be especially tricky in the AI space since it's so new and there is so much competition.
Yes, it does. It recursively walks through the JSON structure, calculating a confidence score for each individual field — whether it’s a top-level key, nested inside objects, or part of an array of objects. Each leaf field gets a {value, score} pair, and parent objects get an aggregated score based on the confidence of their children.
Hi everyone,
I built @promptrepo/score because we’re no longer using generative AI just for suggestions — we’re making decisions with it. But generative AI is probabilistic, not the deterministic systems we’re used to. So when AI makes decisions, we need to know how confident it is, and how much we can trust each field in the output.
This tool looks simple — it just converts OpenAI’s logprobs into field-level confidence scores — but that changes how you use AI in production. It lets you mark low-confidence fields, send them for human review, or retry with better grounding. In high-volume systems, you can also track low-confidence patterns to improve prompts or fine-tune with better data. Its a lightweight npm and has no dependencies, so its easy to integrate it into your AI workflows. Would love to hear your thoughts!
Not yet. @promptrepo/score relies on token-level logprobs, which OpenAI exposes for their models. But, Anthropic’s Claude currently doesn’t expose token-level confidence (like logprobs) in their API. So, we can’t support Claude until they do. We’d love to add support if/when Claude exposes this capability.
OP here. While this logic holds, large companies don’t move fast.
In 2018, I wrote about scaling big while staying small using serverless computing (https://cloud.google.com/blog/products/gcp/scale-big-while-s...). But by 2020, instead of leaner teams, we saw more hiring and even bigger orgs—ironically, even at companies selling serverless services.
Why? Because incentives at large companies favor empire-building (prestige from managing big teams) over efficiency. I expect the same inertia with AI: solo devs will fully embrace AI, serverless, and freemium to race ahead, while big teams will adopt AI at a crawl.
Author of the post here. This is a misunderstanding of CRM given how customer relationships have evolved over the last 20 years. Salesforce didn’t copy Siebel - it moved sales tracking to the cloud. HubSpot didn’t copy Salesforce - it focused on inbound leads.
We’re not trying to build every feature of a traditional CRM. We’re focusing on Google Forms as CRM for SMBs because they already use Forms + Sheets to manage leads. Wrote another post explaining how we use it as a CRM - https://manidoraisamy.com/developer-forever/post/can-you-use...
reply