CHEAT CODE: AI Automation in 2025

Поділитися
Вставка
  • Опубліковано 8 січ 2025

КОМЕНТАРІ • 48

  • @valeravoronin7956
    @valeravoronin7956 17 днів тому +1

    watching you do it makes me want to build AI automation, even though I have ZERO coding knowledge. The future is about optimizing your life's processes--especially at work. This is so cool!

  • @msistem2025
    @msistem2025 17 днів тому +4

    I've been looking for this kind of information for a month now, and I spend at least an hour a day. And the universe heard me. Many thanks for this video.

    • @StephenGPope
      @StephenGPope  17 днів тому

      💪💪

    • @FrenchDavidUTOPIAN
      @FrenchDavidUTOPIAN 16 днів тому

      @@StephenGPope WHEN YOU WILL PUBLISH THIS AS A TEAMPLATE FOR A KNOWLEDGE BASE?

  • @RashidAzarang
    @RashidAzarang 16 днів тому +4

    I’ve been working with RAG and using Airtable for a while, and although your system is impecable for a small number of queries, if you ramp up the number of records, the cost will not be efficient.
    A better way would be building simple node.js script and hosting it on Heroku or AWS, then write an Airtable automation that is triggered when the record goes into the view you mentioned, which would run a simple script that triggers the script in node.js to push, get and have both of your db in sync, while respecting your criteria.

    • @jagadeeshch7870
      @jagadeeshch7870 15 днів тому +1

      The channel is about low code or no code automation.
      For personal usecase maybe we can deal with a small script but when it's complex and changes based on requirement then this is best.

    • @AndresRodriguez-ul7hr
      @AndresRodriguez-ul7hr 14 днів тому +1

      What a great answer, if you can help us with a video tutorial, I would be very grateful. Thanks.

    • @StephenGPope
      @StephenGPope  10 днів тому +1

      there are some valid points here but its all comes down to the details, this video is more for concept that production as well. thanks for your thoughts.

  • @MostlyPeacefulNinja
    @MostlyPeacefulNinja 17 днів тому +3

    I literally just draw up a diagram to build a “knowledge base” like this last week. I need to work faster and start releasing my own videos haha.
    Good stuff

    • @StephenGPope
      @StephenGPope  17 днів тому

      Speed is the key to some of this stuff 👌

  • @karlonadaraya
    @karlonadaraya День тому

    amazing ideas!
    Thank you Stephen!

  • @jpmaroney
    @jpmaroney 2 дні тому

    Another fantastic model! Thx 🙏

  • @NVX_Ink
    @NVX_Ink 17 днів тому +1

    This is exciting. Analyzing everything now! Thank you. Watching for the classroom!

    • @StephenGPope
      @StephenGPope  17 днів тому +1

      Awesome! Traveling today so a little later!

  • @lenydiallo
    @lenydiallo 17 днів тому +1

    Awesome demonstration 😍, I use Flowise and Make for those use cases, but it was very interesting to see your process!

  • @mysound777
    @mysound777 15 днів тому +1

    This is awesome. THANK YOU

  • @hayatotakeru568
    @hayatotakeru568 17 днів тому +1

    amazing video!
    Thanks Stephen

  • @TlecocoJakapong
    @TlecocoJakapong 3 дні тому

    What app are you using to make your mouse arrow pointer? Thank you for your response!

  • @svenimmelmann9777
    @svenimmelmann9777 16 днів тому

    So much value in this video!!

  • @MartinTrebbin
    @MartinTrebbin 10 годин тому

    Stephen, love the content. What's the live screen recording annotation tool you're using? Thanks.

  • @alpineai
    @alpineai 6 днів тому

    @Stephen - actually a video walk through of a user asking your NCA Toolkit CustomGPT would help some folks. This is where a person can figure out the many specific use cases for your super useful tools!

  • @hhmtp
    @hhmtp 8 днів тому

    Hello, great videos. What app are you using to make this kind of video? Camtasia?

  • @anhphuongvu227
    @anhphuongvu227 17 днів тому +2

    I understand that the limitatations of the data input is the issue of LLM models here. But Claude just came out with Claude Projects recently with custom prompts and pdf file, image or even videos as inputs. How does your system offer more benefits than Claude projects? Thanks for replying.

    • @MostlyPeacefulNinja
      @MostlyPeacefulNinja 17 днів тому +3

      But you can’t make an API call to Claude projects.

    • @1lostplatoon
      @1lostplatoon 17 днів тому +1

      Automation.

    • @StephenGPope
      @StephenGPope  17 днів тому +1

      A few others have mentioned, projects are cool but dont work with automation or apis

  • @softwaregent7443
    @softwaregent7443 16 днів тому +1

    Great automation! Really looking forward to creating this one. Is there any way to get in contact with you directly?

    • @StephenGPope
      @StephenGPope  16 днів тому

      Yea right here or skool.com/no-code-architects

  • @ajaykumarporeddiwar9226
    @ajaykumarporeddiwar9226 17 днів тому

    Thanks, Stephen. Just random questions popped up. how do make sure the search terms are exactly matching against the vector database? how many embeddings are perfectly matched? how much accuracy is maintained based on matched and unmatched percentage of user query to vector database?

  • @RocknRollCEO
    @RocknRollCEO 14 днів тому +1

    Holy shit!! 🤯🤯🤯
    One question Stephen. Why the content overlap in the "chunks"? Is it so the "embeddings" encryptions contain "linked" content with the previous / next number, so the LLM understands the content is connected somehow?
    And if "yes", how did you figure that out?

    • @StephenGPope
      @StephenGPope  13 днів тому +1

      Yes, i figured it out because i tried to add a larger file and it was too big. So i wondered what to do and wondered if there a strategy for breaking them up.

    • @RocknRollCEO
      @RocknRollCEO 13 днів тому

      Incredible.

  • @handfacts
    @handfacts 17 днів тому

    Great video. Not enough on this topic

  • @Trizzer89
    @Trizzer89 17 днів тому +11

    I dont understand the value added here

    • @StephenGPope
      @StephenGPope  17 днів тому +1

      Its a system for creating customized knowledge basis for companies.

    • @isaiah_dupree
      @isaiah_dupree 17 днів тому +1

      The value added is that the ai systems that you have implemented into your business will now have respond with more concise responses and another benifical part is that it will be self learning.

  • @The_Outkeeper
    @The_Outkeeper 17 днів тому +1

    Feels like a lot of the automations I have build following your tutorials were just the prepwork.

  • @MartinMessier
    @MartinMessier 16 днів тому +1

    Do you teach how to put this together in the community?

    • @StephenGPope
      @StephenGPope  10 днів тому +1

      I provide the templates you see in the video, and of course we provide support as well. I don't have what I'd call formal training on this specific subject yet. But that will develop.

  • @BudLoveall
    @BudLoveall 16 днів тому +1

    He uses the term "rational database". Does he really mean "relational database?" or is there some other kind of database that is rational?

  • @belou2361
    @belou2361 16 днів тому

    This is great content and shows how versatile Make is. But to be honest, this is not the best tool for building a rag with a vector store and embeddings. I would consider n8n or better yet Flowise. Best tool for each job. 😊

  • @conjon4883
    @conjon4883 17 днів тому +1

    Is Slack the best interface for this sort of thing I would love to build out a similar system for a client, but I’m not sure I wanna onboard them to Slack.
    Would be cool if there was an extension in Airtable…

    • @StephenGPope
      @StephenGPope  17 днів тому +1

      I think it works well but i could see other things work well too, like sms, voice, email event interactive avatars, telegram and whatapps could even work too

  • @verasalem5071
    @verasalem5071 8 днів тому

    You said "Explain the API" when talking about the "hidden API". You should clarify that process might be illegal in countries like America. Even if you can see the API calls, you would have to reverse engineer them to get the data you want and this definitely is not a beginner process especially if you don't know anything about coding.