Wow, amazing to read this just as we discovered the same capabilities, Andre. We quickly went from ChatGPT to signing up for access to DaVinci. The next step for our platform for researching 3,232 cybersecurity vendors always included ingesting all their products by name and function. But it took 4,000 hours of my time over years to find and categorize those vendors. Categorizing 10,000 products presented an insurmountable task unless I could afford to hire five experienced industry analysts who were willing to take on a mind-numbing task.
We are ingesting 6,500 products right now, derived from careful queries to DaVinci 3.5, fed with json summaries of the current websites of each vendor. (cost=$450) We get all the products and a feature list for each one. This is game changing. We already have a source of new products, also from an AI trained by Feedly, so keeping current is going to be straightforward.
Dear Andre, thank you for the insightful post! I have a question: How do you go about the margin of error that CHAT GPT still has? I noticed that when researching for the founding year of companies, the answers were sometimes incorrect so we needed to double check all answers which created an equally large amount of work. Are there any fixes to this? Thanks and all the best from Vallendar!
Andre, you wrote that you connect ChatGPT to your internal database to lever the outcome and get up to date results. However don’t you have concerns open internal data base to uncontrolled bid data corp? How is data security managed?
Richard, it is amazing. I have tried almost everything.
I have a question. When I ask to summarize a website it give the following answer: I regret to inform you that I cannot give you a summary of a specific website, as I am not able to browse the internet, however, I can give you an idea of what a summary of a Venture Capital Firm website might typically include in a tabular format. What did I do wrong?
I was thinking it could help with capital raising efforts such as finding potential lead targets for investing in fund, email outreach and automated responses for capital raising. The Replies to incoming emails would have a goal to convert emails to calls to intro the fund. Replies would be based on context from the email thread and email history related to that domain, any information available about the investor profile from crm or online, our fund thesis and logistics (derived from deck, ppm, etc), and context of the person/role that would be responding to their query. As for scheduling time, maybe either have it read the persons calendar and suggest a few times as one of the email responses.
I was thinking it could help with capital raising efforts such as finding potential lead targets for investing in fund, email outreach and automated responses for capital raising. The Replies to incoming emails would have a goal to convert emails to calls to intro the fund. Replies would be based on context from the email thread and email history related to that domain, any information available about the investor profile from crm or online, our fund thesis and logistics (derived from deck, ppm, etc), and context of the person/role that would be responding to their query. As for scheduling time, maybe either have it read the persons calendar and suggest a few times as one of the email responses.
Wow, amazing to read this just as we discovered the same capabilities, Andre. We quickly went from ChatGPT to signing up for access to DaVinci. The next step for our platform for researching 3,232 cybersecurity vendors always included ingesting all their products by name and function. But it took 4,000 hours of my time over years to find and categorize those vendors. Categorizing 10,000 products presented an insurmountable task unless I could afford to hire five experienced industry analysts who were willing to take on a mind-numbing task.
We are ingesting 6,500 products right now, derived from careful queries to DaVinci 3.5, fed with json summaries of the current websites of each vendor. (cost=$450) We get all the products and a feature list for each one. This is game changing. We already have a source of new products, also from an AI trained by Feedly, so keeping current is going to be straightforward.
Dear Andre, thank you for the insightful post! I have a question: How do you go about the margin of error that CHAT GPT still has? I noticed that when researching for the founding year of companies, the answers were sometimes incorrect so we needed to double check all answers which created an equally large amount of work. Are there any fixes to this? Thanks and all the best from Vallendar!
Andre, you wrote that you connect ChatGPT to your internal database to lever the outcome and get up to date results. However don’t you have concerns open internal data base to uncontrolled bid data corp? How is data security managed?
Awesome and inspiring! Thank you Andre
Richard, it is amazing. I have tried almost everything.
I have a question. When I ask to summarize a website it give the following answer: I regret to inform you that I cannot give you a summary of a specific website, as I am not able to browse the internet, however, I can give you an idea of what a summary of a Venture Capital Firm website might typically include in a tabular format. What did I do wrong?
Great suggestions and applications. Thank you Andre.
Andre, this is great.
I was thinking it could help with capital raising efforts such as finding potential lead targets for investing in fund, email outreach and automated responses for capital raising. The Replies to incoming emails would have a goal to convert emails to calls to intro the fund. Replies would be based on context from the email thread and email history related to that domain, any information available about the investor profile from crm or online, our fund thesis and logistics (derived from deck, ppm, etc), and context of the person/role that would be responding to their query. As for scheduling time, maybe either have it read the persons calendar and suggest a few times as one of the email responses.
Andre, this is great.
I was thinking it could help with capital raising efforts such as finding potential lead targets for investing in fund, email outreach and automated responses for capital raising. The Replies to incoming emails would have a goal to convert emails to calls to intro the fund. Replies would be based on context from the email thread and email history related to that domain, any information available about the investor profile from crm or online, our fund thesis and logistics (derived from deck, ppm, etc), and context of the person/role that would be responding to their query. As for scheduling time, maybe either have it read the persons calendar and suggest a few times as one of the email responses.
I tried the similar companies prompt but chatGPT did not give me a the list as you got. Even if I did the search for N26.
Do I miss something?