Today was the first time I tried this product. It reported that it downloaded 16 PDF files from a website and saved them to my computer, but I couldn’t find where they were saved. Could you please clarify that? Also, where can I find information on how to use the tool when needed? And what is the support email address? Thanks in advance
Founder Team
Arjun_RetrieverAI
Aug 21, 2026
A: Hi thanks for trying Retriever AI, and sorry for the confusion.
Where the files go: when the agent "downloads" a PDF in the Chrome extension, it uses Chrome's normal download flow, so the files are saved to your browser's regular download folder (usually ~/Downloads on Mac, C:\Users\<name>\Downloads on Windows). The quickest way to find them is to open chrome://downloads in a new tab — every...
Q: Using your product, I ran into the following error mesage. What does this mean?
Your platform states: "User provider [DeepSeek/deepseek-v4-pro] extraction failed: fetch failed Your configured external provider failed; Rover fell back to a managed provider and credits will be deducted for this request. Fix your provider settings to avoid charges. Extraction falling back to Gemini Vertex AI (credits will be deducted)." what does that mean?
Founder Team
Arjun_RetrieverAI
Aug 21, 2026
A: Hey sorry about that, that day we were migrating our DeepSeek providers, and this could have been a side effect.
I purchased your highest tier but unfortunately must return , based on that decision. Users asked questions about the low amount of credits provided in the deal and was something that I completely agreed with them on, especially with no credit rollover. But your answer was to remove the pro language model (keeping only deepseek)? These flash models are not performing the same way as the pro...
Founder Team
Arjun_RetrieverAI
Aug 11, 2026
A: Hey TetanicRaptor, we removed Gemini Pro because its an outdated model and it was just way too costly inference wise. The Gemini Flash Fast option is the latest Gemini model released so far.
We just got accepted into AWS, Azure, Nvidia, GMI Cloud, Thinking Machines startup programs and so will have a lot more model options offered soon.
We found the DeepSeek Flash mode to perform pretty well...
As we've learned in this business, new and better cannot be confused. The new gemini model is not performing as well as the old pro model. While I'm glad the platform has joined startup programs, you removed models, to save on usage cost in the middle of an active campaign, which changes it's performance. It's an easy way to spook buyers as it indicates financial hardships & instability
I understand cost and as an early adopter I expect things to break from time to time in this stage. I just need to be able to justify the purchase and it takes spending some time with the product without a variable such as which LLM will exist next week. I still the product. But this has been a bit of a rug slip.
1) what can i do with 250 credits? for example, pull 50 leads from linkeding how many may it take? 2) if i dont use do they roll over for next month? thanks
Founder Team
Arjun_RetrieverAI
Aug 11, 2026
A: We have calculator at to estimate based on your usage: https://rtrvr.ai/appsumo
Credits are primarily used for hosted model inference, datasets, proxies, and cloud browser infrastructure.
Can expect tasks on extension to take .5-5 credits, on cloud to take 5-30 credits, and each linkedin record enrichment will take .25 credits.
You can bring your own API key with any model to lessen credit...
Q: Where are the downloaded files stored?
Today was the first time I tried this product. It reported that it downloaded 16 PDF files from a website and saved them to my computer, but I couldn’t find where they were saved. Could you please clarify that?
Also, where can I find information on how to use the tool when needed?
And what is the support email address?
Thanks in advance
Arjun_RetrieverAI
Aug 21, 2026A: Hi thanks for trying Retriever AI, and sorry for the confusion.
Where the files go: when the agent "downloads" a PDF in the Chrome extension, it uses Chrome's normal download flow, so the files are saved to your browser's regular download folder (usually ~/Downloads on Mac, C:\Users\<name>\Downloads on Windows). The quickest way to find them is to open chrome://downloads in a new tab — every...
Share Retriever AI
Q: Using your product, I ran into the following error mesage. What does this mean?
Your platform states: "User provider [DeepSeek/deepseek-v4-pro] extraction failed: fetch failed
Your configured external provider failed; Rover fell back to a managed provider and credits will be deducted for this request. Fix your provider settings to avoid charges.
Extraction falling back to Gemini Vertex AI (credits will be deducted)." what does that mean?
Arjun_RetrieverAI
Aug 21, 2026A: Hey sorry about that, that day we were migrating our DeepSeek providers, and this could have been a side effect.
Share Retriever AI
Q: Why did you lower quality of the LLMs?
I purchased your highest tier but unfortunately must return , based on that decision. Users asked questions about the low amount of credits provided in the deal and was something that I completely agreed with them on, especially with no credit rollover. But your answer was to remove the pro language model (keeping only deepseek)? These flash models are not performing the same way as the pro...
Arjun_RetrieverAI
Aug 11, 2026A: Hey TetanicRaptor, we removed Gemini Pro because its an outdated model and it was just way too costly inference wise. The Gemini Flash Fast option is the latest Gemini model released so far.
We just got accepted into AWS, Azure, Nvidia, GMI Cloud, Thinking Machines startup programs and so will have a lot more model options offered soon.
We found the DeepSeek Flash mode to perform pretty well...
Share Retriever AI
As we've learned in this business, new and better cannot be confused. The new gemini model is not performing as well as the old pro model. While I'm glad the platform has joined startup programs, you removed models, to save on usage cost in the middle of an active campaign, which changes it's performance. It's an easy way to spook buyers as it indicates financial hardships & instability
I understand cost and as an early adopter I expect things to break from time to time in this stage. I just need to be able to justify the purchase and it takes spending some time with the product without a variable such as which LLM will exist next week. I still the product. But this has been a bit of a rug slip.
Q: what can i do with 250 credits?
1) what can i do with 250 credits? for example, pull 50 leads from linkeding how many may it take? 2) if i dont use do they roll over for next month? thanks
Arjun_RetrieverAI
Aug 11, 2026A: We have calculator at to estimate based on your usage: https://rtrvr.ai/appsumo
Credits are primarily used for hosted model inference, datasets, proxies, and cloud browser infrastructure.
Can expect tasks on extension to take .5-5 credits, on cloud to take 5-30 credits, and each linkedin record enrichment will take .25 credits.
You can bring your own API key with any model to lessen credit...
Share Retriever AI
Q: Can we use MCP and API to trigger local chrome browser extension
Can we use MCP and API to trigger local chrome extension ?
Arjun_RetrieverAI
Edited Aug 10, 2026A: Yes exactly!
Can checkout docs/examples here: https://rtrvr.ai/docs/mcp
So from claude code or any MCP client quickly launch and finish browser tasks.
Note: this only works with Google Chrome browsers
Share Retriever AI