I built 5 AI Agents in 36 Minutes to save me 20+ hours of work a week

00:36:11
https://www.youtube.com/watch?v=_qr7ogLpTJs

概要

TLDRIn this discussion, Flo, the CEO of Lindy.AI, highlights the power of AI agents, particularly through the concept of agent swarms, which enable multiple AI agents to work collaboratively on tasks. He provides a step-by-step demonstration of creating AI agents for various business functions, such as meeting management and recruitment, showcasing the rapid development and implementation of agents. The conversation emphasizes the low barrier to entry for automating business processes with AI, encouraging listeners to explore and adopt these technologies.

収穫

  • 🤖 AI agents can automate substantial business tasks.
  • ⚡ You can build an effective AI agent in just 10 minutes.
  • 📝 Meeting recorders can summarize discussions and store notes.
  • 📅 AI can handle scheduling and calendar management seamlessly.
  • 📈 Competitive analysis can be automated using AI tools.
  • 🔄 Agent swarms perform tasks in parallel for efficiency.
  • 👥 AI agents can assist in recruiting by sourcing candidates.
  • 🤝 Personalized outreach through AI saves time and effort.
  • 🛠️ No-code platforms like Lindy help non-tech users build agents.
  • 🔍 Start with simple tasks to understand AI capabilities.

タイムライン

  • 00:00:00 - 00:05:00

    In this episode, the host introduces Flo, CEO of Lindy.AI, discussing the capabilities of AI agents and agent swarms, highlighting how multiple AI agents can address business challenges effectively. They emphasize the ease of creating AI agents and how they can automate a significant part of business operations quickly, enabling the audience to explore these tools further.

  • 00:05:00 - 00:10:00

    Flo, the guest, talks about Lindy.AI as a no-code platform for creating AI agents, similar to Zapier, which has released thousands of web scraping agents, including one that extracts YouTube comments. He presents a simple use case for a meeting recording and note-taking AI agent, which can summarize meetings and manage notes, thus increasing productivity and making it indispensable for users.

  • 00:10:00 - 00:15:00

    The discussion continues with a practical demonstration of how to configure the meeting recorder agent using prompts in natural language, showcasing Lindy's flexibility and seamless integration with existing tools like Google Drive. Flo explains how the agent can learn and recover from mistakes, providing a robust solution for meeting documentation and management.

  • 00:15:00 - 00:20:00

    Flo elaborates on the comprehensive capabilities of Lindy, including features for making phone reservations and managing personal assistance tasks. He shares a humorous story of interacting with AI agents, underlining the collaboration between AI in different contexts, specifically in customer service, and how they can improve efficiency in personal and business tasks.

  • 00:20:00 - 00:25:00

    The podcast highlights the concept of agent swarms, where a set of tasks can be distributed among multiple AI agents in parallel. This approach prevents reliability issues that may arise from a single agent handling extensive or repetitive tasks, making the process faster and more effective for tasks such as outreach and lead generation.

  • 00:25:00 - 00:30:00

    Flo provides a live demo of creating a recruitment agent, emphasizing the simplicity of defining criteria and executing tasks with Lindy, which can automate reaching out to potential candidates based on specific parameters, showcasing the effectiveness of AI in streamlining recruitment processes.

  • 00:30:00 - 00:36:11

    The discussion concludes with insights on utilizing Lindy for various business functions, particularly repetitive and recurring tasks. Flo encourages listeners to experiment with these AI tools for improving productivity, highlighting the difference between current capabilities in AI versus traditional methods and the potential of adopting these innovations for competitive advantage.

もっと見る

マインドマップ

ビデオQ&A

  • What are AI agent swarms?

    AI agent swarms are multiple AI agents working together in parallel to accomplish tasks efficiently and reliably.

  • How quickly can I create an AI agent?

    You can create your first AI agent in about 10 minutes using the Lindy.AI platform.

  • Can AI agents replace executive assistants?

    AI agents can automate around 70% of the tasks typically performed by executive assistants.

  • What are some use cases for AI agents?

    Use cases include meeting scheduling, note-taking, customer support, and personalized outreach.

  • How does Lindy.AI differ from other platforms?

    Lindy.AI offers a no-code platform allowing users to build their own AI agents easily, akin to how Zapier operates for general workflow automation.

  • What is the significance of the competitive analysis Lindy?

    It helps businesses track competitors by analyzing metrics like employee count and recent funding rounds.

  • How can AI agents help with recruiting?

    AI agents can automate the recruitment process by sourcing candidates, personalized outreach, and managing applications.

  • What should I consider when implementing AI agents?

    Start with recurring tasks and simple personal assistance use cases to familiarize yourself with the platform.

  • Is Lindy.AI suitable for small businesses?

    Yes, it is designed to enhance efficiency even for small teams by automating numerous tasks.

  • What kind of integrations does Lindy.AI offer?

    Lindy.AI supports thousands of integrations, enhancing capabilities for various workflows.

ビデオをもっと見る

AIを活用したYouTubeの無料動画要約に即アクセス！
字幕
en
オートスクロール:
  • 00:00:00
    what if AI agents could replace some of your  team well they can i brought on Flo who's the
  • 00:00:08
    CEO of Lindy.AI probably the number one AI agent  platform and he shows us how to do agent swarms
  • 00:00:17
    the big new thing with uh AI agents where you  have multiple agents going after these problems
  • 00:00:24
    now we go through a bunch of different job  responsibilities and how to actually set
  • 00:00:29
    up these agents forms and AI agents so  that they become AI employees for your
  • 00:00:37
    business enjoy the episode and I can't  wait to see what you end up building
  • 00:00:55
    flo is back on the pod the AI agent god that's  what I call him um Flo if people stick around
  • 00:01:03
    to the end of this episode what are they going to  learn what are they going to get out of this they
  • 00:01:09
    are going to learn that you can create agents  a lot faster than you think you can and you
  • 00:01:14
    can automate half your business in like half  a day and you can create your first agent in
  • 00:01:19
    10 minutes and you're gonna show us how to  do that yeah that's the goal okay so let's
  • 00:01:26
    let's get to it cool um let me share my screen  real quick okay uh well for quick introduction
  • 00:01:35
    um Flo I'm the founder of Lindy you can think of  us as like the the Zapier of AI we're building a
  • 00:01:40
    no code platform for you to build your your own  AI agents um this is I've already been here on
  • 00:01:45
    the podcast thanks Craig for having me again uh  this is the the last time we we chatted and I'm
  • 00:01:51
    going to use this later as an example for to  show Lindy's web scraping abilities because
  • 00:01:56
    we we released that last week thousands of web  scrapers 4,000 of them in fact and so one of
  • 00:02:01
    the web scrapers is Lindy now has the ability to  scrape uh YouTube comments um so I'll just start
  • 00:02:09
    with like just a super quick introduction and a  super super simple use case for Lindy which is
  • 00:02:15
    uh meeting recording and note takingaking so I  mean this is probably like the most universal use
  • 00:02:20
    case like everyone's in meetings all day and this  is the simplest meeting recorder you can build on
  • 00:02:25
    Lindy it's like hey when a calendar event begins  you record the meeting and then you summarize the
  • 00:02:30
    meeting that's it obviously little by little you  add up and add up and add them more to it and I'll
  • 00:02:34
    show you my meeting recorder this is my actual  meeting recorded or that I that I live with all
  • 00:02:38
    day and this is actually like a a small part of it  like it just keeps going and going and going um so
  • 00:02:43
    in a way that's the beauty of it is like you keep  adding to it and then it becomes irreplaceable
  • 00:02:48
    so I mean one example that this meeting recorder  does here is it uh adds the meeting notes to a
  • 00:02:54
    Google doc and if I have already met with this  person before it looks on my Google drive for
  • 00:03:00
    these notes and it adds the notes to the existing  Google doc that I have for this person uh it was
  • 00:03:07
    actually super useful just yesterday we just on  boarded our first head of marketing and he asked
  • 00:03:12
    me for context like my relationship context with  some marketing agencies that we're working with
  • 00:03:17
    and I just had to like dig up the Google Docs and  I could send him a Google doc and I'm like this
  • 00:03:20
    is everything we've ever talked about with this  person and it worked it just works just works
  • 00:03:25
    um and then the beauty of it is since it's an  agent so when you look at it like this like this
  • 00:03:30
    is where it sort of looks like Zapier it sort of  looks like a workflow under the hood though it's
  • 00:03:35
    an agent and so what it means is that I'll show  you for example this update document step here um
  • 00:03:42
    I can literally just speak to this step in English  so each field here for this step is just a prompt
  • 00:03:50
    so here for example I'm like hey which document  should you update well the document you found
  • 00:03:54
    previously that contains my note for this person  what content should I put in the document and here
  • 00:03:59
    I can just be like summarize the meeting you just  had in bullet points so I don't need to have like
  • 00:04:04
    a separate step for AI like the thing is AI you're  basically telling an AI to go through a sequence
  • 00:04:10
    of steps but these these steps are not islands  like they would be for like a workflow automation
  • 00:04:15
    platform like Zapier and I think what's cool about  this is I mean if you if you dial this and and you
  • 00:04:22
    you do this correctly there's no mistakes that's  right if anything it's it if you made a mistake
  • 00:04:29
    it recovers from it like very often I'm actually  surprised you can create your agentworkflow and
  • 00:04:36
    set up the steps and never configure them you  literally don't even tell it what to do i'll
  • 00:04:40
    actually give you an example right now um I'm  going to create a Lindy start from scratch and
  • 00:04:46
    I'm going to tell her so the trigger here is just  me chatting with it it's just like an agent that
  • 00:04:50
    I can chat with and I'm going to use the the  YouTube video example so YouTube here so this
  • 00:04:55
    is an example of all the scrapers we just we just  added thousands and thousands of integrations in
  • 00:05:01
    scrapers we're like by far the top AI agents right  now in terms of number of integrations um so I'm
  • 00:05:06
    going to do YouTube comments by URL and after  the results are available I'm going to just let
  • 00:05:13
    it have a conversation with me so I'm I'm going to  leave it like this and I'm literally going to do
  • 00:05:18
    nothing i'm I'm not telling it what to do i'm not  telling it I just this is it this is the you know
  • 00:05:23
    the different steps that you that you follow and  I'm going to grab this uh link from the last time
  • 00:05:28
    we chatted now I think there you go and I'm going  to just send it to the video so I got roasted in
  • 00:05:36
    the comment because partly because my accent  think it's it's racist and it is a sick accent
  • 00:05:44
    um and look I did not tell it what to do it's just  like all right it's getting the YouTube comments
  • 00:05:49
    i think this creeping takes about a minute dude  by the way I get roasted all the time for calling
  • 00:05:56
    Claude Clo yeah how How should you call it is  it I agree i agree is it a Canadian thing well
  • 00:06:11
    in French you call it clo right yeah you know so  but people make fun of me all right well back back
  • 00:06:18
    to uh Lindy all right uh I mean right here I you  can see I didn't tell it what to do it just like
  • 00:06:24
    got the com comments and hey one viewer noted a  potential business opportunity startup ID set up
  • 00:06:29
    Lindy's flow as a service we actually do have  uh if you go to I think it's lindy.ai/service
  • 00:06:35
    partners we have like dozens of of companies that  make a living through just building lindies for
  • 00:06:40
    customers like fact that's a lot i didn't even  know there was so many of them i think it's like
  • 00:06:43
    50 or something more than that um yeah you can see  I didn't have to tell it what to do to go back to
  • 00:06:50
    the meeting recording example and again that's a  difference between um a a a workflow and an agent
  • 00:06:57
    is like agents really like to chat so you can just  chat with it at any time so I'm going to go here
  • 00:07:02
    what's an example of a of a of a meeting I can  show you um I had a reference check with someone
  • 00:07:15
    um yeah so I can just chat and be like "What did  the candidate say about moving to SF?" And I can't
  • 00:07:22
    tell you i mean I use this all day i think I have  really bad memory because I'm in meetings all
  • 00:07:26
    day and so I just use this as like I call it my  exocortex it's like my my brain outside my brain
  • 00:07:31
    and it just like replies to questions for me yeah  i also I I find my memory has been getting worse
  • 00:07:38
    too as I'm relying more and more on technology  to basically fulfill things so uh this is helpful
  • 00:07:46
    yeah yeah so all day I just asked you these  questions and let's wait for it to reply right
  • 00:07:52
    here he's currently based again we're going to  have to change his name and and blur it out uh but
  • 00:07:59
    he is interested in our new office and and so on  and so forth um so I I think the meeting recording
  • 00:08:06
    is probably one of the most universal use cases  uh meeting scheduling is a close second basically
  • 00:08:12
    the entire executive assistant stack like I just  I haven't replaced my executive assistant but I
  • 00:08:18
    think I replaced like 70% of of what she does with  Lindy i mean executive assistants they take notes
  • 00:08:24
    during your meetings they schedule your meetings  they prepare you for your meetings uh they make
  • 00:08:28
    restaurant reservations i have this Lindy chief  of staff here so Lindy can make phone calls oh
  • 00:08:32
    the most hilarious thing happened just yesterday  actually I asked her to make a phone call for
  • 00:08:37
    uh to make a reservation for like a date night  with my girlfriend and I was like "Hey make a
  • 00:08:42
    reservation at Flower and Water it's like a super  good restaurant in San Francisco tonight for two
  • 00:08:46
    people at 8:00 p.m can go as early as 7:30 or 9:00  p.m." And I didn't give her the number of flour
  • 00:08:52
    and water so she went to Perplexity to look for  the number she found a number and then she made
  • 00:08:57
    a phone call and then the really thing the really  funny things that happened is I didn't realize but
  • 00:09:02
    this restaurant actually also uses an AI agent to  pick up the phone so after I listened to the call
  • 00:09:08
    and I was like wait a minute this was also an AI  agent hi it's Arena at Flower and Water just so
  • 00:09:15
    you know I'm taking notes on this call to share  with the team how can I help you hi Arena i'm
  • 00:09:21
    calling to make a dinner reservation tonight for  two people we're looking for 8:00 p.m but we're
  • 00:09:26
    flexible and the agents just and in the end I had  a reservation so it's it's crazy like it's already
  • 00:09:33
    happening where AI agents are currently working  together yeah and by the way Flower and Water I
  • 00:09:39
    think uh Johnny Ies from Apple and I think maybe  even Steve Jobs one of their favorite restaurants
  • 00:09:45
    so this is like a hard restaurant to get into  and the fact that this happened is is amazing
  • 00:09:51
    yeah yeah uh it's funny the first time I demoed  this feature I used it to because I literally
  • 00:09:57
    the the team had just coded it in like half a  week and I was like "All right demo time let
  • 00:10:02
    me just ask you to like cancel my flight to Paris  that have scheduled next week and it worked first
  • 00:10:06
    shot and she canceled my flight." I was like "No  I didn't expect it to work." Um yeah so you know
  • 00:10:13
    like phone call like reservations meeting prep is  a pretty big one i have this Lindy here and this
  • 00:10:20
    is actually using the the feature that we just  released last week which we call agent swarms
  • 00:10:25
    and while you bring that up what is an agent  swarm that's a good question an agent swarm is
  • 00:10:31
    the ability to send a list of things to do to to  an AI agent and for this AI agent to do all these
  • 00:10:38
    things reliably quickly and in parallel because AI  agents are awesome and they're and they're super
  • 00:10:44
    powerful but over long-term like longtime horizons  they fail they lose coherence and so for example
  • 00:10:51
    if you give an AI agent a list of things like  hey take these 500 people and send personalized
  • 00:10:56
    outreach to them like personalized lead outreach  is a very big use case for AI agents it's first
  • 00:11:02
    of all it's going to take forever it's going to be  pretty expensive and the by the 200th lead it may
  • 00:11:09
    fail it may just become unreliable if you use  an agent swarm instead it's going to basically
  • 00:11:15
    you know like in the matrix you have like a agent  Smith that duplicates himself it's like the agent
  • 00:11:20
    smith thing like the agent is going to duplicate  himself and send one copy of itself to each lead
  • 00:11:25
    yeah so this meeting prep here uses it's actually  it's funny if it's a swarm of swarms so what I do
  • 00:11:31
    is every morning you wake up you check my meetings  for the day and then you deploy an agent swarm
  • 00:11:37
    for each meeting that I have and then inside this  swarm you deploy another swarm for every attendee
  • 00:11:43
    of every meeting that I have and then this is  really cool because this Lindy actually uses
  • 00:11:48
    the meeting notes that the other Lindy brings  together that I just mentioned so she looks in
  • 00:11:54
    the Google Drive folder that contains all of my  meeting notes that Lindy creates and then she gets
  • 00:12:00
    my notes for this meeting and then she search for  my emails with this person she looks up for their
  • 00:12:06
    LinkedIn on Google and then she sends me a digest  by email so you can see here every morning let's
  • 00:12:15
    see right here again we may have to like uh  blur out some of these but I just receive these
  • 00:12:24
    digest every morning of everything and and it's  pretty detailed like so for example I have this
  • 00:12:29
    uh this dinner tonight it's like a founder dinner  where like people talk about their struggles and
  • 00:12:33
    there's like a bunch of of really senior executive  coaches and they've sent us an email beforehand
  • 00:12:38
    and they're like "Hey you have to come prepared  with a challenge that you want to discuss." And
  • 00:12:44
    so this Lindy here found it and so now you know  it's like "Ah right like I need before this dinner
  • 00:12:47
    tonight I need to come prepared with a challenge  to discuss." I was I was really impressed because
  • 00:12:54
    right before we hopped onto this podcast you said  "Hey by the way I picked up that Sure MV7 mic."
  • 00:13:03
    And I was like I was like "There's no way this  guy is going to remember to buy this mic." Cuz I
  • 00:13:08
    remember when I had you on the first time the mic  wasn't really great and people were complaining
  • 00:13:14
    and it was the first thing you told me and then  when you when I when you you know I just see right
  • 00:13:18
    now in the meeting prep it says use good audio  equipment sure MV7 you got me that's my dirty
  • 00:13:26
    secret that's how you know yeah no 100% it's it's  I mean half my life runs on this right now it's
  • 00:13:31
    just like same for the meeting scheduling i'll  show you my my meeting scheduleuler here um so
  • 00:13:36
    and it works exactly the same as an AI as a human  assistant does which is people reach out to me by
  • 00:13:42
    email they're like flow I'd love to chat or you  know maybe it's like a job interview or anything
  • 00:13:45
    like that that like a candidate I'm interviewing  and all I do is I have given this Flindy her own
  • 00:13:51
    email address and all I do is I CC her I'm like  sounds good I'd love to chat will help us find
  • 00:13:57
    time and so you can see here this happened just  this morning um I was introduced by a recruiter
  • 00:14:04
    to a candidate and I'm like thank you KG great  to meet you Brian I would love to chat plus Lindy
  • 00:14:09
    will help us find some time and you can see here  I literally also added would you like to meet in
  • 00:14:13
    person at the office and here Lindy looked at my  calendar she found available times she sent the
  • 00:14:19
    times by email then he responded "Yep in person  on Monday works." So she sent the calendar invite
  • 00:14:25
    and you can see in the calendar invite right here  she puts the address of the office right here and
  • 00:14:31
    then she sent this uh confirmation she's like "All  right we'll meet at 1:30 at 1841 Market Street."
  • 00:14:37
    This is like you're setting off like a million  light bulbs in my head right now because what I'm
  • 00:14:41
    doing is I'm thinking what are all the tasks  in my business that are recurring like this
  • 00:14:48
    like what what you're showing me right now my EA  does this um my EA does this so like what do you
  • 00:14:55
    recommend to people should they should they take  stock of all the recurring tasks and then see if
  • 00:15:02
    that you know Lindy's can do it i think so so what  I do recommend to people is actually to start with
  • 00:15:07
    these like personal assistance use cases because  it's just so easy and everybody can use a meeting
  • 00:15:12
    scheduleuler everybody can use a meeting prep  everybody can use a meeting recorder and so just
  • 00:15:17
    like you know dip your toes in the water like that  like just like get the reps put a W on the board
  • 00:15:22
    and you can on board to this in like five minutes  it's like super easy we've got templates here
  • 00:15:26
    we've got like hundreds of templates if you go to  the the home tab here there's a bunch of lindies
  • 00:15:31
    that are pre-created and these ones we literally  advertise them at the top because like we call it
  • 00:15:36
    like the personal assistant starter pack it's  just like everybody can use these things and
  • 00:15:40
    then little by little once you understand how the  platform works which it's really pretty easy then
  • 00:15:44
    you're going to very rapidly like to your exactly  what you said like a light bulb is going to go off
  • 00:15:49
    and you're like and you're going to be like oh my  god like this can be used for everything so I'll
  • 00:15:53
    give a more complex example and what do you think  like should we just like build a Lindy live right
  • 00:15:58
    now yeah why not let's do it uh let me build I  spend a ton of time recruiting right now so I'm
  • 00:16:04
    going to create a Lindy recruiter so I'm going  to make her chat with Lindy i'm going to make it
  • 00:16:11
    um when I chat with it I'm going to just give it  a list just criteria of what I'm looking for and
  • 00:16:17
    then I'm going to use the search for people action  so we have like a ton of prospecting integrations
  • 00:16:22
    because like prospecting is one of our top use  cases and then uh I'm going to make it enter an AI
  • 00:16:27
    agent and I'm going to tell it um show me the list  of people you found and ask me which ones to reach
  • 00:16:34
    out to and again that's where it's an AI agent i  don't need to like you know divide up the array
  • 00:16:40
    or the list of people it found or to format it i  just I'm speaking to my agent and the agent saw
  • 00:16:45
    the people it's like the same agent that's moving  from step to step to step and here I'm going to
  • 00:16:50
    give this step and exit conditions like once I've  told you which ones to reach out to then you enter
  • 00:16:59
    uh a swarm and I'm not even going to tell it what  items to swarm through i I think it's just going
  • 00:17:05
    to be smart enough to figure it out and I'm going  to make it uh research this person on perplexity
  • 00:17:12
    so search proplexity so uh research this person on  perplexity and then I'm going to make it send an
  • 00:17:23
    email to this person so and from my email uh send  email and I'm just going to make it I'm going to
  • 00:17:32
    prompt it here i could just also write like a  literal value we have this setting here that's
  • 00:17:36
    like set manually so I could just here type my  email uh but here I'm just going to be prompt
  • 00:17:41
    AI and it's like reach out to join lindy.ai um  that's it i'm just gonna do this for now and in
  • 00:17:49
    one click you can insert a human in the loop so  I can be like ask for confirmation and that's it
  • 00:17:55
    right here it's going to ask me for confirmation  when should people have a human in the loop and
  • 00:18:02
    when shouldn't they have a human in the loop great  question if a if an AI agent could embarrass you
  • 00:18:09
    you should probably insert a human in the loop at  least in the beginning for the first few cycles
  • 00:18:14
    and you're going to work on it it's the same thing  as training a human it's like you just think of it
  • 00:18:18
    as like you just on boarded an intern and like  you don't at first you're kind of on their back
  • 00:18:22
    you kind of watch what they're doing that's how  you think of it and soon we're we're building a
  • 00:18:27
    feature right now that's making it so that uh  the agent can learn from your feedback so as
  • 00:18:33
    you insert a human in the loop if you correct it  little by little it's going to learn um that is it
  • 00:18:38
    right here I have like an MVP recruiter i'm going  to rename her and just call her the recruiter
  • 00:18:44
    that's it i've got I've got a small recruiter  and again that's the beauty of it is like you
  • 00:18:48
    start small like this took me two minutes and then  you add to it and add to it and add to it so for
  • 00:18:53
    example here I could make it send reminders like  if the person doesn't reply I could make it send
  • 00:18:58
    two four five reminders right uh and actually  I'm going to add a last step here so it's like
  • 00:19:03
    hey I've reached that to everyone um I'm going to  start here and I'm going to be like I want to hire
  • 00:19:12
    like find me five account executives uh working  at what's a good what's a good place to hire from
  • 00:19:19
    account executives hubspot yeah um actually I'm  realizing I think this was set yeah okay this is
  • 00:19:26
    beautiful all right we don't recommend poaching  from HubSpot but we don't we don't condone it
  • 00:19:34
    either are you are you a HubSpot partner um no  okay good um okay reach out to every to everyone
  • 00:19:44
    who doesn't have enterprise or corporate in their  title i think that's literally two people and here
  • 00:19:53
    it's going to start swarming over basically the  two people that I gave it right here so you see
  • 00:20:00
    I didn't configure the swarm it's just like smart  enough to figure it out here and now if I expand
  • 00:20:05
    this task here I can see the subtasks that are  part of the swarm and so what it's doing here is
  • 00:20:10
    it's searching complexity for this person and it's  it's going to be AI slap you know like by default
  • 00:20:15
    AI AI just writes AI slap so like I would need to  prompt it more i would need to give it examples
  • 00:20:19
    but boom i hope this email finds you well i'm  reaching at because I came across your profile and
  • 00:20:24
    I mean right here I just gave it to two profiles  but I could have said like 200 and that's that's
  • 00:20:29
    basically how we recruit like we're pretty good  at recruiting and it's very cost effective and
  • 00:20:33
    we just use this all day and this could be used  for well you know recruiting if you think about
  • 00:20:38
    what recruiting is it's about making it's about  closing it's really closing deals at the end of
  • 00:20:44
    the day right so this could be applied to I mean  you mentioned sales prospecting this is in a way
  • 00:20:50
    is like sales process 100% 100% you can also like  upload CSVs here so if you have a bunch of leads
  • 00:20:57
    from another platform so Lindy can generate  her own leads but there's also a lot of other
  • 00:21:01
    platforms that you may want to use to do that and  so I have we also use it for sales prospecting so
  • 00:21:06
    if you look at we have this sales outreacher Lindy  here and I have a CSV right here i'll open it can
  • 00:21:16
    Google Chrome open CSVs i cannot i also have it  in a Google sheet so Unicorn Founders it's like a
  • 00:21:23
    list so this one Google Sheets here is 20 unicorn  founders but um let me see if this is the right
  • 00:21:29
    sales outreacher yeah um I'm just going to delete  to begin what one of the things I noticed by the
  • 00:21:36
    way is that uh 3.5 is default selected should  people keep that default or should they change
  • 00:21:43
    it i think you should keep it i think that's like  a great default um basically start with cloud and
  • 00:21:51
    then if you find your agent is too dumb graduate  to we've got Gemini we've got 01 o1 is is really
  • 00:21:58
    good it's really expensive but it's really good um  I use 01 for research tasks um and if your agent
  • 00:22:06
    is too expensive use Gemini Flash and most of the  time Cloud does a good job and Gemini Flash does a
  • 00:22:13
    good job yeah so right here I just I mean you can  see it took me in the time I spent to answer this
  • 00:22:19
    question i just reached out to 20 unicorn founders  about about what we do and it's actually uh
  • 00:22:26
    personalized right so here it's it's reaching out  to the founder of Epic like team Swinny and it's
  • 00:22:31
    like hey like this is how we Lindy can help you uh  streamline developer support manage and organize
  • 00:22:37
    data from your free games program an epic first  run initiative so it's it's really super super
  • 00:22:42
    customizable and super personalized that's why I  wanted this is why I wanted to have you on the pod
  • 00:22:48
    again i saw that you were well it was right after  the the announcement of the swarms and just I I
  • 00:22:56
    think that you know what it's important for people  to realize is that this can take a small team of
  • 00:23:02
    1 2 3 5 people and make them feel like 20 30 40  50 people and there's an arbitrage moment that
  • 00:23:09
    is happening not everyone i mean maybe in our  world we're all like "Yeah AI agents AI swarms
  • 00:23:14
    everyone knows what this is right?" Making jokes  about Claude and Clude no we're we're so we're so
  • 00:23:20
    early in this and if you're if you're listening to  this um it's all just about like getting your feet
  • 00:23:26
    Yeah and your hands dirty and starting to create  some of these things and just seeing it work in
  • 00:23:32
    action there is a huge gap right now between what  is possible and what people are actually doing
  • 00:23:38
    there's there's a huge arbitrage and you can  see it because the companies that are actually
  • 00:23:42
    exploiting this arbitrage are blowing up i mean uh  there's this startup called Arcades they're like
  • 00:23:49
    this is like an AI ad generator and reportedly  they reached like $5 million in AR in like a
  • 00:23:55
    couple of months with I think like eight people  like seven or eight people or something like that
  • 00:23:59
    you may you may know this yeah I know it because  dude it's hilarious i had the founder on the pod
  • 00:24:06
    a while ago awesome guy and awesome technology and  then like two weeks and I I speak to him on X all
  • 00:24:14
    the time and then two weeks later I get an email  from his team being like "Hey like it was like a
  • 00:24:20
    creator outreach email." And he was like "Hey like  we'd love to partner with you and do like a paid
  • 00:24:26
    promotion or do like something with you or give  you free access to the product." And I messaged
  • 00:24:33
    the founder and I was like "Dude oh and it said  it was him right it said it was him and I was
  • 00:24:38
    like why are you texting me this and he's like he  started laughing and he was like oh no no no that
  • 00:24:42
    you know he was probably using Lindy you know I  you know I can't I can't speak for who's using
  • 00:24:48
    us but I will say this example I just gave of the  restaurant reservations it's also happening for
  • 00:24:54
    outreach like that where we are increasingly we  have cut multiple times Lindy's talk to Lindy's
  • 00:25:00
    from like different customers so this influencer  outreach use case is actually a pretty big one
  • 00:25:04
    and we have I can't say who but we I wish I could  say who because it's pretty cool it's a very big
  • 00:25:09
    YouTuber who uh is using us um and um he uh so he  it's actually not him it's his agent he's using us
  • 00:25:18
    because this guy receives so many emails all day  from like random brands who are offering him to
  • 00:25:23
    partner and it's just it's a deluge right and like  less than 1% of them he wants to work with so his
  • 00:25:29
    agent has deployed a Lindy to help him like filter  and like negotiate deals and all of that stuff
  • 00:25:34
    we have another customer who's like a famous  jewelry brand who uses a lot of influencer
  • 00:25:39
    marketing and they have also deployed a Lindy  to find influencers on Tik Tok and Instagram
  • 00:25:43
    and YouTube and find their contact information and  reach out to them and offer them partnerships and
  • 00:25:50
    when we signed that customer I was like we need  to create a reminder to check a month from now
  • 00:25:54
    if that if if his Lindy ducked to his Lindy and  sure enough we checked a month later and they had
  • 00:25:58
    they had crossed paths i love it um would you be  able to go back to the template section and the
  • 00:26:04
    reason why is I want to scan through some of these  just to get people's minds primed for the types of
  • 00:26:12
    stuff that you can use yeah let me open the full  list of templates here uh you know lead enrichment
  • 00:26:20
    lead qualification customer support like and and  customer support over everything because we just
  • 00:26:25
    released last week like 1,600 integrations like  again we're by far right now the top AI agent
  • 00:26:31
    platform in terms of number of integrations and  so wherever your customer support exists if it's
  • 00:26:37
    like Telegram or Slack or WhatsApp or Zenesk  or Intercom like you name it like we can we
  • 00:26:42
    can automate your customer support over over these  platforms um the focus group here is is a really
  • 00:26:48
    interesting use case because LLMs are not super  good at reasoning but they are really good at
  • 00:26:54
    pretending to be human because that's that's what  they are right they've been trained on on so much
  • 00:26:59
    text that's human written and there's actually  a lot of papers that find that the answers that
  • 00:27:05
    LLM give you are actually very correlated to what  to the answers that a human would have given you
  • 00:27:10
    so if you ask like do you like this or that like  LLM are actually doing a very reasonable job at
  • 00:27:16
    at emulating a human and so that means that you  can like marketing companies and like big firms
  • 00:27:22
    they spend fortunes on focus groups and we use it  ourselves as well like we've created a lindy that
  • 00:27:28
    simulates our user so we've prompted it to be like  hey these are the different personas of users we
  • 00:27:33
    have and we talk to it all day like what do you  think of this what do you think of that like how
  • 00:27:38
    do how is this lending on you and it's it's I  would say it's 80% as good as like an actual
  • 00:27:42
    focus group in an actual user research session but  it cost you like 10 cents instead of $1,000 dude
  • 00:27:49
    that's so interesting i uh I talk a lot about  on the channel just this idea of like building
  • 00:27:55
    community- based businesses and community based  products where it's like you're building a product
  • 00:27:59
    for a community and I never thought of it like  this but a virtual community right like so coming
  • 00:28:07
    up with an idea for like vibe coding something  coming up with a product for something starting a
  • 00:28:11
    social account and then getting feedback on your  business idea and what you're trying to do from
  • 00:28:18
    your virtual community yeah you know I actually  think that's the next step for right now like Bolt
  • 00:28:23
    and Lovable and all of these companies are really  blowing up these like prompt to app platforms are
  • 00:28:28
    really blowing up i think that's going to be the  next step for them where it's like you build the
  • 00:28:32
    MVP of your app and then it sends it to a thousand  virtual users and and they use it and like 5
  • 00:28:39
    minutes later you've got feedback from a thousand  people and then you just rinse and repeat and you
  • 00:28:44
    let this running for a day and by the end of the  day you've got an an app that's been iterated on
  • 00:28:50
    for like the equivalent of a year right uh this  one I I love it's it's my Elon Lindy so what it
  • 00:28:56
    does is uh it actually uses both the phone call  capability we have and the swarm capability we
  • 00:29:01
    have so you give it a list of your team and every  week it makes a phone call to each teammate for
  • 00:29:07
    a sort of virtual standup and it asks them like  what did you get done this week uh it's actually
  • 00:29:12
    funny because I forgot I had this running and I  I received a phone call like a couple of weeks
  • 00:29:16
    ago from my Lindy and I was like oh like it's my  Lindy phone number is in my contacts and I'm like
  • 00:29:21
    oh my Lindy's calling me what's going on so I pick  up the phone i'm like "Hey." And and she's like
  • 00:29:24
    "Hey Floyd it's Lindy." I'm like "Okay what do you  want?" And she's like "What did you get done this
  • 00:29:28
    week?" [ __ ] you um yeah so the Elani is really  cool and then it sends you a report with a summary
  • 00:29:36
    of what your entire team has told you so this is  actually right now being deployed by one of our
  • 00:29:40
    customers like a thousand plus employees and every  week it's just like a thousand people receive a
  • 00:29:45
    phone call and then the CEO receives a report with  like what everybody in the company is doing it's
  • 00:29:50
    basically replacing the middle management layer  of the company very cool dude this is crazy you've
  • 00:29:58
    come I think you were on the pod like 6 months  ago almost and the integrations and just seeing
  • 00:30:04
    all these templates like it's crazy how much has  changed it is moving fast for sure the team has
  • 00:30:10
    been cranking um I'll give one last example I  guess of of a Lindy that I really like which
  • 00:30:16
    is the the competitive analysis Lindy um I think  this is another thing that can be very useful to
  • 00:30:21
    pretty much any company um I have it right here  uh competitive tracker um so you can see it's
  • 00:30:29
    funny it's got the the poop emoji here as an icon  um what it does is uh it wakes up every month it
  • 00:30:37
    gets the list of competitors from this spreadsheet  like you can just like keep a spreadsheet with the
  • 00:30:42
    competitors that you're keeping tabs on and then  it deploys a swarm for each competitor and for
  • 00:30:47
    each competitor it looks up whatever information  you want the employee count the traffic estimates
  • 00:30:52
    the recent news whether they've raised the money  whether they're hiring any anything you want and
  • 00:30:57
    then it does a couple of interesting things which  is one it sends you a report with like hey like
  • 00:31:01
    these are the competitors who are putting ahead  and it logs all of that in a spreadsheet and so
  • 00:31:08
    you can see here this is just an example  spreadsheet where I've I've entered three
  • 00:31:12
    competitors like Brex Mercury and RAM they're like  financial companies and here it's logging all of
  • 00:31:17
    this data here in this in this other tab and then  I've set up this other sheet on the spreadsheet
  • 00:31:22
    that's like telling me it's like a table it shows  me for each competitor for every month how have
  • 00:31:28
    their employees count trending how have their  monthly website visits trended their valuation
  • 00:31:34
    and so on and so forth and again I mean you can  see it's it's pretty simple it's like nine steps
  • 00:31:41
    or something like that and we have a template for  it that's really cool yeah it's also um you know
  • 00:31:49
    when it comes to building a startup and looking  at competition like you you really don't want
  • 00:31:53
    to be like going to their websites every day and  letting them get in your head so having something
  • 00:31:58
    like this feels a bit more sober yes one one  thing I have liked actually doing uh this is
  • 00:32:06
    actually from before we had swarms um if you're on  Twitter or on Product Hunt or whatever you get the
  • 00:32:11
    feeling that everyone is their mother is working  on AI agents so you get a new announcement maybe
  • 00:32:16
    every day at this point like twice a week you get  like a new major announcement and so at first as a
  • 00:32:21
    founder you know I was like I wouldn't say I was  getting demoralized by it but it was like [ __ ]
  • 00:32:26
    like this is this is heavy competition like this  is going to be a hot space right and so what I
  • 00:32:31
    did is I set up a Lindy that's like I could just  send her these announcements and then I would be
  • 00:32:35
    like in six months tell me where these guys are  and in 12 months tell me where these guys are and
  • 00:32:40
    one thing that it's really taught me is 90% of  the time they're nowhere so it's really trained
  • 00:32:47
    me like that now when I see a computer I'm like  yeah look it doesn't it's like the folks that I
  • 00:32:51
    would worry about 12 months ago don't exist today  so 90% of the time it doesn't matter i love it all
  • 00:32:58
    right is there anything else you wanted to cover  um let me think i Okay I'll show one last example
  • 00:33:04
    that the contra is showing is my my CRM manager  so I have this Lindy that helps me um manage my
  • 00:33:11
    my my network and so I every so often I talk to  her and I'm like "Hey I just met this guy he's
  • 00:33:17
    awesome i really wanted to stay stay in touch with  with him." So um I'll show you an example here um
  • 00:33:24
    well we're going to have to we're going to have to  blur it out but uh I edit this guy like hey like
  • 00:33:30
    this guy is is awesome you know apparently he's  the best that other guy has ever worked with addit
  • 00:33:36
    him to a spreadsheet another really cool thing is  that I can talk to this Lindy and I can be like
  • 00:33:39
    hey who should I hit up when I'm in New York or  who are like really good salespeople that I know
  • 00:33:47
    and then it finds me a list and then this Lindy I  actually also made her observe my inbox and notice
  • 00:33:53
    when I have booked a flight which by the way soon  is going to be a Lindy booking flights for me and
  • 00:33:59
    so she she sees when I booked a flight because  I receive an email confirmation and she's like
  • 00:34:04
    and I can I can actually show you because right  now I'm going to to New York so she's like "Hey
  • 00:34:08
    like you're going to New York." This is just  like a test email I sent to myself and she's
  • 00:34:13
    looking in my CRM and she's like "Hey these are  the contacts that you should meet up when you're
  • 00:34:18
    going to New York." That's so smart you know what  I usually do which is like dumb but whenever I'm
  • 00:34:25
    doing something like this I'll go onto my Twitter  account and just see who I'm following and be like
  • 00:34:29
    "Oh yeah Flo's in San Francisco." and reach out  but it's like obviously not the best way to do
  • 00:34:34
    that the problem is too few people are on Twitter  which I don't understand i feel like everybody
  • 00:34:38
    should be on Twitter it's like such a boon but  too few people are on Twitter that's right and
  • 00:34:44
    LinkedIn is gar is kind of garbage let's be real  no 100% yeah it's not your real network this has
  • 00:34:51
    been great uh Flo I'm going to put together a  a document that people can download that can
  • 00:35:00
    help them set up their first agents maybe some  best practices just some notes on how to do it
  • 00:35:08
    um people can go and grab that that'll be in the  comment section and in the show notes and is there
  • 00:35:16
    is there one thing you want to leave people with  i will create a custom signup link for you if you
  • 00:35:23
    go to lindy.ai/greg i'll create a signup link so  that people get a a 50% discount and they get like
  • 00:35:29
    a longer free trial great so I'll include that in  the show notes in the pin comment um appreciate
  • 00:35:37
    that Flo and um why I think it's important that  people start doing this is like don't listen to
  • 00:35:44
    us anymore you know what are you doing listening  to us at this point right like go and get your
  • 00:35:48
    hands dirty yeah the frontier has really rushed  forward so much right now it's it's it's like we
  • 00:35:54
    had computers and everybody was still using the  fax machine and just like computers arrived all
  • 00:35:58
    of a sudden because innovation is accelerating  and people are still using fax machines and
  • 00:36:01
    I'm like this is people don't understand right  now what's what's happening it's cool dude it's
  • 00:36:06
    really cool thanks for sharing it with us yeah  thanks a lot Greg i'll see you around see you
タグ
  • AI Agents
  • Agent Swarms
  • Automation
  • Lindy.AI
  • Meeting Management
  • Recruitment
  • No-Code Platform
  • Business Efficiency
  • Customer Support
  • Integrations