The problem is I don't trust all those SaaS reviews in sites like G2, TrustRadius, Gartner etc. A lot of them are paid, and incentivized. Heck, I personally wrote a few nonsense ones just to get free gift cards. But I know some people give our free credits or discounts if you write a review for them.

Even a lot of "free" reviews on Reddit are secretly posted by the company, or someone who got paid by the company.

[UPDATE] Just tried the tool. 7 of the 8 bullet points your tool gave me was also given to me by Claude. I think both are using similar data sources, so I fail to see what differentiates this tool

Your landing page is doing the heavy lifting here. Nice design.

You should do side by side comparisons of output from GPT4o/Claude and your product to sell me on why I should care about the RAG you added and your tuned prompts.

If you're giving away inference you should probably tell people how you're intending to make money from them. Free services that use expensive APIs are a big red flag for me.

Wow incredible, could you give a small glimpse in how you collected/normalized/vectorized all the different reviews + information? Just lots of scraping + chucking it into Pinecone etc?

> Me: Give a list of the new and old gene sequencing tools

> Reply: Based on the available reviews, I’ve compiled lists of new and old sequencing products mentioned by users: Genemod, Mixmax (email sequencing...?), HubSpot Sales Hub (????)

Are you guys using a pure RAG for your responses? I think you should have a function caller traverse a tree of topics before retrieving data from the right area/space or you'll have lots of "contamination" of similar phrases across fields

What is this trained on? It doesn't seem to look on the web for my product at all... doesn't quite the reviews...

Are you just using an LLM? I asked to write code, and it did...

Landing page yes but is it actually working with production performance? I have strong doubts after executing your own demo query of "Summarize the reviews you have on products in the OCR category." in the system.

If the idea is just demo and collecting leads, then you could have cached at least your demo queries.

Everybody's too landing-page focused these days.

How is it different from asking chatgpt (or other popular LLM)?

Cool idea, but fails one well known fact:

Customers don't know what they want.

Would you mind sharing a source of the reviews? How your users would know whether your product could be trusted?

Here is some feedback. Your landing page needs samples. After spending 30s I do have some idea about what you're trying to do but some real life samples of input and output will show me exactly what to expect and how good the quality is and eventually if it's worth my time to sign up for it.

Very cool. Can you describe any fine tuning or RAG you did? Did you have to go through a bootstrapping process?

Totally get it if you don’t want to share details.

Well this product is completely useless if it's trained on G2 and Capterra reviews.

neat! what is your data source?

Looks like a useful product. Does it support Facebook and Google My Business reviews?

I have some MBA friends who wanted to do a “AI powered G2 or Gartner” startup. Which makes me feel like this is a tarpit idea

Good stuff, it gave me a very fair review of the SaaS I tested it on and suggested good alternatives. This is useful.

This one seems like a blatant GPT wrapper. Why not just use 4o?

For example, "Ask any question" the use case shown is:

> "What specific python scripts are users running inside HubSpot?"

I could just ask ChatGPT that too, why would I need this product to answer the question?

Seems like everyone is just wrapping ChatGPT, creating even the identical UI down to the icon on the send button, and then making a Loom showcasing essentially white-labeled OpenAI functionality.

Upon reading the title, my brain took a garden path in the direction of the 3M company.

Me:

What do users think about Reviewradar?

Reviewradar:

User feedback on ReviewRadar varies, with many appreciating its functionality while some indicate areas that could use improvement. Here’s a detailed breakdown of sentiments based on user reviews:

Positive Aspects:

User Experience: Many users noted that the interface is intuitive and easy to navigate. One user expressed that ReviewRadar is "the best source of software reviews," highlighting the visibility and transparency it provides.

Comprehensive Review Collection: Users value the centralized nature of reviews, stating it allows for easy tracking and management of their online reputation. One respondent emphasized, "I can point possible customers to ReviewRadar, and they know that I haven't falsified any reviews".

Support and Updates: Some users appreciated the support team, remarking that they were responsive and helpful during the onboarding process. There’s a notable emphasis on the quick resolution time for any issues.

Critical Feedback:

Integration Limitations: A recurring theme in feedback pertains to a need for better integration with other applications. For instance, users have mentioned, "It would be great to see Google My Business integration" as a valuable addition.

Clarity in Reviews: While many find the review process thorough, some users have pointed out that there were instances of what they perceived as biased or unreliable reviews. This is particularly concerning in a landscape where fake reviews can distort genuine customer experiences.

Feature Requests: Certain users expressed the desire for more customization options in dashboards and reporting features, indicating that the current setup could be streamlined to improve usability.

General Sentiment:

The overall impression of ReviewRadar is largely positive, with a community of users who find it helpful in gathering insights and managing their online reviews. However, users desire enhancements in integrations and feature sets to maximize its potential.

Conclusion:

In summary, if you’re contemplating using ReviewRadar, the platform seems to be effective for managing software reviews and tracking customer feedback. Yet, be aware of the requests for improvements in integration and functionality from existing users.

If you have any specific features or areas in mind that you'd like to explore further, let me know!

Just a nitpick: please use lowercase 'm' for 'million'. When I read the title I thought it had something to do with the company 3M (not really known for making SaaS).

Congrats on the good work! Do as https://x.com/levelsio does, keep iterating, and make it better over time.