Afrikaans
Akan
Albanian
Amharic
Arabic
Armenian
Azerbaijani
Basque
Belarusian
Bemba
Bengali
Bihari
Bosnian
Breton
Bulgarian
Cambodian
Catalan
Cebuano
Cherokee
Chichewa
Chinese (Simplified)
Chinese (Traditional)
Corsican
Croatian
Czech
Danish
Dutch
English
Esperanto
Estonian
Ewe
Faroese
Filipino
Finnish
French
Frisian
Ga
Galician
Georgian
German
Greek
Guarani
Gujarati
Haitian Creole
Hausa
Hawaiian
Hebrew
Hindi
Hmong
Hungarian
Icelandic
Igbo
Indonesian
Interlingua
Irish
Italian
Japanese
Javanese
Kannada
Kazakh
Kinyarwanda
Kirundi
Kongo
Korean
Krio (Sierra Leone)
Kurdish
Kurdish (Soranรฎ)
Kyrgyz
Laothian
Latin
Latvian
Lingala
Lithuanian
Lozi
Luganda
Luo
Luxembourgish
Macedonian
Malagasy
Malay
Malayalam
Maltese
Maori
Marathi
Mauritian Creole
Moldavian
Mongolian
Myanmar (Burmese)
Montenegrin
Nepali
Nigerian Pidgin
Northern Sotho
Norwegian
Norwegian (Nynorsk)
Occitan
Oriya
Oromo
Pashto
Persian
Polish
Portuguese (Portugal)
Punjabi
Quechua
Romanian
Romansh
Runyakitara
Russian
Samoan
Scots Gaelic
Serbian
Serbo-Croatian
Sesotho
Setswana
Seychellois Creole
Shona
Sindhi
Sinhalese
Slovak
Slovenian
Somali
Spanish
Spanish (Latin American)
Sundanese
Swahili
Swedish
Tajik
Tamil
Tatar
Telugu
Thai
Tigrinya
Tonga
Tshiluba
Tumbuka
Turkish
Turkmen
Twi
Uighur
Ukrainian
Urdu
Uzbek
Vietnamese
Welsh
Wolof
Xhosa
Yiddish
Yoruba
Zulu
- [Sudha] I'm going to show you
how to build an autonomous agent AI
using a no-code agent AI platform.
There are several tools you can find
in the Ecosystem handout that I've shared.
I have chosen one called Promptly.
You can sign up for a free account on trypromptly.com.
Promptly provides a platform to build chatbots and agents
using multiple LLMs that are available in the market today.
Do you remember what is the difference
between an intelligent chatbot and an agent?
Well, a chatbot is an app that is built
on top of an LLM model, and its learning is static
and tied to the model that you choose.
An agent can perform a complex task
by breaking down our ask into simpler tasks
and can learn from external data sources,
and can run tools and reflect on its own results.
Let's get started to build an agent.
The first component to build an agent is a LLM.
So, here you can see multiple options of LLM,
so you need API access and connection to these LLMs
if you start building the agent AI from scratch.
I'm just going to choose OpenAI.
And let's see whether we can make it
do some image generation.
Okay, so I'm going to say draw a marketing funnel.
It is going to use DALL-E 2 as its model.
I don't want such a huge image,
so I'm just going to use a small one.
So, we got it to generate an image.
So, let me show text to speech,
and we can say hello customers.
- [Agent] Hello customers.
- [Sudha] Okay, so here basically
we have selected an LLM, so that's the first step.
Next I'm going to show you in an agent-building process
we can select outside data sources.
So, I'm going to add a data source.
You can have a single data store,
it can be a text file or a PDF.
I'm going to choose a URL.
And for the purpose of this demo I'm going to make it go
and scrape my own site called sudhajamthe.com.
Oh, I need a name for it.
I'm just going to call it SJ.
Here we go.
While it runs and loads I can add another data source.
I'm going to give another one.
This is my student community called businessschoolofai.com.
Again, I'm trying to show you sites
from where it's going to scrape and get information.
And the idea is we are going to make the agent, again,
I've not given it a name.
And I'm going to call it Business School of AI.
So, the idea with this data store is
that we add external data sources, so it's ready.
Here this is still loading,
and it's going to get it ready in a minute.
So, the agent has an LLM that it'll access.
It could access more than one LLM.
And it can access external data sources,
so this could be a site, like I'm showing,
it could be a file that is proprietary to your company
that you could add that you want the agent
to make referrals to.
This is a RAG system that we would build
that would be the agent that's built on top of that, okay?
So, let that happen.
So, now let me go to the actual building of the agent.
If you know to build from scratch you can build from here,
and you can say here is an agent I want to build.
And the agent is called ASR,
I'm just giving it some random name.
And you can drag and drop the file here.
Remember we added some data store,
we can add files here also.
I've not given API access, it's going to throw an error.
But if you know to code and you are comfortable
with the API access, I would recommend going this route
and choosing the LLM here
and adding what the LLM is going to do,
all kinds of things, right?
But there's an easier option
because I want to show you a no-code option,
that is what we are going to see a demo here
because Promptly has provided a lot of templates
that we can use readily to build this using no code.
So, I'm going to choose Marketing,
and let's create a hypothetical company, a dentist office,
a new dentist office,
and they want to build a marketing funnel.
So, I'm going to ask this agent saying craft, not craft,
build me a marketing funnel for a new dentist office.
And what does the agent do?
It takes my request, breaks it down to multiple steps,
and then it starts coming up with a answer
on how to build that.
So, now it is telling me what are the components
of the marketing funnel, and what does each section contain?
So, we'll wait for a moment, it should be done.
Yes, it's ready.
Now, what I would like to do is
I would like to see this as an image,
show this marketing funnel as an image.
This is generating an image,
but from what it actually listed as the activities for us.
So, it's not like the marketing funnel that we asked
the LLM to generate, which was a random marketing funnel.
This is the real thing.
So, it takes my input message,
create a marketing funnel for a new dentist office,
if you see, it has updated the input message.
The prompt I started from is create a marketing funnel,
now it has now expanded that to create
a marketing funnel image for a new dentist office.
Since this is a continuation from the previous request
where it listed all the options
of what needs to get into the funnel, the six stages,
so it's generated its own prompt.
Can you see the agent has generated its own prompt saying,
"Create a marketing funnel image for a new dentist office.
The funnel should have six stages," and it's list that.
"Each stage should include
relevant channels and strategies."
All this is what it came up with from its different
step-by-step steps that it came up with.
Now, it's putting all that generated its own prompt,
and it's created a beautiful marketing funnel for us.
I love it, awesome.
Can't find what you're looking for?
Get subtitles in any language from opensubtitles.com, and translate them here.