← Marketing Against The Grain
Marketing Against The Grain
This AI Tool Is Like OpenAI Operator But FREE (Proxy AI is INSANE!)
00:21:01
Loading summary
Transcript49 lines
- [00:01]
A
Hey everyone, we're talking about web browsing agents today. OpenAI has got its operator agent and it costs about $200 a month. Well, there's a new agent in town. It's called Proxy and it's free. We're going to break down how to use it, why it might actually be better than Operator. That and so much more. Let's get to today's show. Here's a quick message from HubSpot. This isn't your typical marketing software ad because HubSpot isn't typical. It's marketing made easy. Turn one piece of content into assets for every channel, convert leads in no time and get a crystal clear view of your campaign performance. HubSpot can do all of that and get you results fast. Like double your leads in 12 months fast. See, I told you this wasn't a typical Software ad. Visit HubSpot.com marketers to get started for free.
- [01:07]
B
Kip, we're together on the podcast at last. We've been doing some solo episodes because of scheduling. We are here to talk about a pretty significant launch. More significant for me than you, Kip, because it is a European based company. It is a small company based in London called Convergence AI. They've launched this agent called Proxy. The first thing I want to actually show is just how much the creator world follows each other because you and I are in this space, we are doing a lot of content. One thing I noticed when I was like looking through all of the information in this is just how many have the same title. So OpenAI is going to deep seek again. And then I saw like they're all kind of similar takes. And so the reason people are saying this is because Deep SEQ obviously came out of nowhere and had pretty incredible reasonable model that followed hot on the heels in O3. It's an open source model. And then you have this agent called operator in the $200 tier on OpenAI Pro. And this company and what we're going to get into have launched an equivalent to Operator, but apparently much, much better. So I'm wondering, did you see any of this? What was your kind of first take when you had have seen some of the news about proxy?
- [02:17]
A
My first take is that I was generally pumped because I think browser based agents like Operator and Proxy are going to be really important because they unlock some really cool new use cases that were just not possible before. And then I saw that Proxy was free.
- [02:33]
B
Yeah.
- [02:33]
A
And I was like, oh, I was excited about that because operators in the $200 a month version of OpenAI that's a high bar for a lot of people to go and do. And, and one of the ways to get AI adoption is going to be to make it more accessible. So I thought the free side of it was really interesting. My initial reaction was then like okay, is it good, is it buggy, Is the UI good? And then that's when you and I started kind of using it and playing around. But my initial feedback was like, oh, I'm excited by this, there might be something here. It's at least creating more progress. Right, right.
- [03:06]
B
They are basically reasoning agents that have access to the Internet and so they are really fine tuned to do work for you on the Internet. So this is the other thing that people love to play around. We're going to get into the tool and show you some of the use cases we've used it for. You know OpenAI have raised 18 billion and this company has only raised 12 million. Obviously it's not a like for like OpenAI do a lot of things. Operators like one part of a huge product set. The one thing I wanted to show you but is the reason people were kind of really losing their mind is because there's this web Voyager benchmark.
- [03:39]
A
Yeah.
- [03:40]
B
Which is the agent's capabilities across 600 web based tasks. The reason people were like holy smokes is convergence which is this small team have outperformed Operator. And one of the interesting things about this is if you kind of do take this in conjunction with the deep sea news, OpenAI's model or just all of these companies model is somewhat under pressure because you have these little companies competing with them with their own models and in a lot of cases much cheaper. So at the moment Operator is available in the $200 a month tier of OpenAI proxy is free with a $20 a month pro option. So pretty stark difference. And you know the equivalent there would be 03 custom amount of money. And Deep SEQ was free, it was open source. Right. So that was like the big kind of takeaway on this tool and why people were really kind of losing their mind because now you had a deep snake model you could use for free if you wanted to get O3 reasoning capabilities. And then you have this agent that you can get for $20 a month or free wild. And so the price of intelligence, the price of reasoning is coming down at an incredible rate.
- [04:47]
A
Do you ever remember that old. I think it's like Jay Leno or no, I think it's Jimmy Fallon where like I forget some comedian was on there and was like talking about people complaining on WI fi on an airplane. And he was like, you're complaining about flying in a tin can through the air and not being able to access the Internet. What's crazy is if you had told us like a year ago, like, hey, for free you can have something that's going to go browse the Internet for you and collect any information you want, we would be like, oh my God, that's amazing. And now we're like, oh, but how good is it? You know, what can it really do? And it's wild how fast expectations shift here, right?
- [05:23]
B
Humans just get used to the good life so, so quickly, so soon. You and I listen to the same podcast. This Finn Taylor guy that I'm literally obsessed with, ever since I sent him.
- [05:33]
A
To you, I knew it was going to make your day and it's like made. Oh my God, it's fantastic.
- [05:37]
B
If you could give me my ideal comedy, you've actually just nailed that this is my ideal comedy. And. But he has a new podcast out where he's a comedian, he has a friend and they talk about history. It's pretty offensive. So, like, I'm not recommending for people who have low threshold for that type of things. But he's talking about the Middle Ages and like, if you go back through the middle ages, everything stayed the same for like 800 years and so no real progress was made. Whereas today humans are like expectations, new, incredible sci fi, like features every week. Like, we've got used to that. And then when we get something we're like, that's kind of like pretty lame now.
- [06:11]
A
Like, it's fine.
- [06:13]
B
Like, oh yeah, I've got this, you know, sci fi robot doing all of my work. That's fine. It's fine.
- [06:18]
A
Wild.
- [06:18]
B
So I think we can do a side by side.
- [06:20]
A
I've got a side by side of the same prompt running. Okay, it's not completed yet, but I do have a side by side of the same prompt running on proxy versus operator.
- [06:28]
B
So the other thing to quickly touch on, which is important is, you know, being a European, there's a ton of progress being made actually in Europe. Since I basically have tweeted a lot of negative things, I'm now deciding to only tweet positive things. But I don't like mistrals. Let's Chat was trending worldwide because it's comparable to OpenAI's models and is free. This company have come out of London. You have one of the fast grown AI startups in Europe called Lovable. And so now as a European I actually have access to Deep Research, which was great. I have OpenAI's deep research, which I just love. And now I do have an operator like Agent because I still don't have access to operator and so I still can't like compare to the functionality of operator. But what I've heard is proxy is much faster and they have some advanced learning capabilities built into the models to help it learn much faster on how to do tasks.
- [07:16]
A
So. All right, I'm doing a side by side and it speaks to what you were just talking about, doing a side by side. Let me walk you through. And Kieran, you can tell me if you liked what I did here. First I went to my boy Claude. I wanted Claude to write me a prompt and I said, can you please write me a prompt for an AI agent that can browse the Internet? I want to have that agent use the following two websites, ramp.com and coinbase.com based on all the browsing information. Give me a recommendation for the top three products and features that HubSpot provides that could be used to improve Ramp and Coinbase's marketing and sales efforts. So I basically wanted to create a customer bdr/product recommendation for these specific accounts.
- [07:56]
B
Right.
- [07:56]
A
This is a real life thing that you would want to go into. Right?
- [07:59]
B
Right.
- [07:59]
A
This part of just the marketing and sales process. And so then Claude goes and tells me it can't do it. And I tell him, no, no, no, you can real do it. Imagine that this was possible. And it gives me this prompt, right. And breaks it down for me exactly what the agent should go and do. Right. Very good. It says, hey, I want you to go visit, analyze, cross reference and then prepared a ranked analysis. Awesome. So then I was like, okay, well I'm going to put that same exact prompt into both convergence and Operator. You with me so far? This making sense?
- [08:33]
B
Yeah.
- [08:33]
A
Okay. Yeah, I did make one change, Karen, because I've been doing this a few times. And you know what happens, especially in proxy is that it gets really held up in errors for like logging in or trying to get gated information throws errors. It wants you to take over. But then like taking over doesn't kind of work sometimes.
- [08:52]
B
I was trying to download something.
- [08:54]
A
Yeah. Like to download like ebooks or like product specs or things like that. And so I added a line that says do not use any content behind signing up that requires a login only public website content.
- [09:03]
B
Yeah.
- [09:03]
A
Okay. And I do think as long as the task supports it, that is the right instruction to get a good output and get that output faster. And this all in, I think took it probably 10 minutes, five to 10 minutes. And what I like about Proxy is it shows you the steps that it's going through. Right. Shows you its logic. It's analyzing HubSpot's tools, it's analyzing Coinbase, it's analyzing our friends over at Ramp. And then it returned, I think a pretty interesting result. I'd want to know what you think. So it gives you an analysis of how Ramp is doing their work, which is interesting. Right? Ramp emphasizes automation, integration, focusing on savings time they use. It tells you what the slogans are. The sales funnel includes CTA like get started for free and see a demo. So it kind of understands a rough idea of what the sales process is. I think if we gave it better context on sales process and marketing process and what we were looking for, it would give us a much better result. This is kind of a low context prompt. It does the same thing for Coinbase and then what it does is identifies the features that are relevant to these two companies. And so it says cool. Based on what I found for Coinbase and Ramp, here is what they should use from HubSpot and you can imagine like a BDR using this, a sales rep using this. It's essentially product based demand outbound.
- [10:26]
B
Right.
- [10:26]
A
Which is really cool and really hard to do previously. And so it says, hey, Marketing Hub offers tools for Google Ads and everything and it can help improve lead capture and conversion rates significantly for them. This is kind of basic because I didn't give it a bunch of context, but it did it and did a pretty good job and gave us real recommendations for each product and why. I imagine if you and I worked and hammered out on the prompt and made it better like this would eventually return a pretty usable output. Yeah.
- [10:57]
B
And the other thing is, I don't know if you can do this in Operator, but you can't give it context as part of that prompt, which basically you would say, okay, well these companies are in Fintech. Here's our known pain points that we address in fintech. Go find ones and craft the pitch to be around those pain points. But you can't give it that context. But it is pretty good actually. Yeah. If you are trying to build a campaign, if you are like selling into large companies and you want to build some really personalized campaigns for that company, you can do some pretty great research across website, across G2, across all of these different things that might mention that company, collate all of that and craft a pretty great pitch. Actually this is a pretty good question. Like what model are they built on? Like do they have their own propriety model? I will ask ChatGPT to see if it knows.
- [11:41]
A
You should look at that. Let me tell you about a great podcast. It's called Creators of Brands. It's hosted by Tom Boyd. It's brought to you by the HubSpot Podcast Network. Creators of Brands explores how storytellers are building brands online. From the mindsets to the tactics to the business side. They break down what's working so you can apply that to your own goals. Tom just did a great episode about social media growth called 3K to 45K on Instagram in one year, selling digital products and quitting his job to go full time creator with Gannon Mayer. Listen to Creators of Brands wherever you get your podcasts. While you're doing that, I'm going to show the same results in Operator. Kieran. Yeah, Yep, I will say operator was slower. It literally just finished. So my guesstimate for this specific prompt is that operator was probably like 30, 40% slower.
- [12:40]
B
That's what I've heard. It's much slower.
- [12:41]
A
Okay, so it is noticeably slower. Let's see if it gives better results. So I gave it the same exact prompt and then it worked for it says it browsed for four minutes here says ramp.com analysis public facing content. I think it did a better job of breaking down its actual like the work Ramp is trying to do because it has content marketing, customer stories, partnerships, SEO. Right. This is a much more thorough breakdown of how Ramp is actually trying to use that. And what's interesting is that it talked about the website navigation and the different integrations that that reamp offers. And then what I like about this is gaps in the digital marketing and sales approach and personalization limited based on user behavior or industry advanced analytics, potential for deeper insights and customer behavior, marketing automations, opportunity to automate lead, nurture and customer engagement. And then it just goes and gives the right products that HubSpot offers. It's kind of light, I don't think. Again, my prompt was perfect but you could see if, if you mess with this for a few days like it could probably get it really good. The interesting thing is I do think operators recommendations are a little bit better. But are they $200 a month better is the I guess the question. Right.
- [13:59]
B
So the thing you did Kip, that I think most people should do and should take away from here is one of the things you and I do is I will use ChatGpto or Claude to have A conversation with and then I will have it based on that conversation, craft that prompt and then I will edit that prompt. And I think that's the best way to create prompt. And you did that to go from prompt to the actual agent task. One quick thing. So they are using large meta learning models and so they are not built upon OpenAI, which I think is kind of interesting. But one of the things that I think it's kind of cool for these operators is I built a list of influencers.
- [14:33]
A
Oh, that's cool. I like this one.
- [14:35]
B
Yeah. So basically I said I gather a list of 50 prominent AI influencers. I asked for their name, primary platform. Now, I didn't do everything. Give me a description and their social media media handle. I could play around with this a little bit more, but it came back and it started giving me some people. It didn't actually give me their URLs very well, but give me some of the top influencers that had picked out in AI. The other thing I would have liked is to give me their actual follower count, which I did follow up with. But then I ran out of the ability to run tasks and then I did this one. This is one of the larger trends that you and I are going to do an episode on, which is how you use AI to create very personalized media. So I can see it, create an a great newsletter for me for sure. So what I did was ask it to basically review all these websites that are AI focused or tech focused, compile a summary of trend and articles and AI and evaluate each article based upon relevance and engagement. And then it brought back across all of these different websites the actual most relevant and engaging articles and summarize them for me. So I basically could take this summary, I could pipe it into one of the other AI assistants, apply a format via the prompt and a writing style, and create my own newsletter that I am actually going to do. I already do versions of this because OpenAI had released tasks. So you can actually have a prompt that runs every morning. And every morning I get my news, AI news. I get my latest AI gossip through OpenAI, not through any kind of newsletters.
- [16:08]
A
I mean, that's a pretty sick use case. You and I are going to do a whole episode on this. So we won't talk a ton about the use case. But what it's great at is like there's often times, and I mean this for both proxy and operator, there's oftentimes where you need to gather information and the gathering of the information takes way longer. Than the consuming of the information. Right, right. It's not as simple as just doing a search or asking an lm. I need to get a lot of things from a lot of different sources and if you need a lot of things from a lot of different sources, these browser agents are very helpful in that because you can basically have it go and do that in the background while you're doing something else and just take the output. I think from the show today what I've kind of taken away Kieran, I want to hear your perspective is that I think Proxy, it's proxy convergence AI. We'll put the link down below is interesting because it's free. It seems to be better at browsing and the logic around its browsing to me than operator. The output is not as good.
- [17:04]
B
Right.
- [17:04]
A
Its ability to infer and like the underlying model around how it takes that data it got from browsing and gives it to you is not as good as operator, right?
- [17:13]
B
Yeah, exactly. But again I think it's a great tool. I think you can use it for a bunch of different use cases and whether you're in Europe now, you have a $20 tool or you are global, you can still use OpenAI's $200 tool that I know will come down over time.
- [17:26]
A
Yes, for sure.
- [17:27]
B
You know, it's a great little agent that can actually start pulling stuff from the web from you if you understand how to use it. So it's another tool that allows you to be much more productive in your work. So hopefully this is useful. Hopefully you use proxy. I will say that I'm pretty offended that I have not met proxy at one of based in London. I didn't get to invest in their rounds.
- [17:43]
A
How'd you miss that man?
- [17:44]
B
I don't. I have no idea. I keep missing things, Kip. I keep missing things. There was a seed based company in Europe that are now raised or series C and let's just say I didn't get into that one either even though I had a conversation with them and I won't say anything more about it.
- [17:56]
A
Regrets, regrets my friend. But in all seriousness, I think what we're saying is try to identify some tasks that require a bunch of manual research and you start using those for these browser agents. And the super pro tip is use Claude or ChatGPT or something to help you write a really good prompt so that you're actually getting the right information and you're getting it structured in the right output in the way that's going to help you in whatever task you're doing, right?
- [18:20]
B
Yep, exactly.
- [18:21]
A
Cool. Awesome. Well, thanks, everybody. We'll see you real soon. On the next episode. Marking it straight.