← All episodes

How to Build & Sell AI Agents in 2026: Ultimate Beginner’s Guide

| 26 products mentioned
Watch on YouTube ai agents automation no-code development business monetization api integration lead generation voice ai

Host Liam Ottley provides a comprehensive beginner's guide to building and monetizing AI agents in 2026, covering foundational concepts, practical tutorials, and business strategies. The episode emphasizes that AI agent skills are becoming critical for job security, with workers possessing AI expertise earning 56% more than those without, and demonstrates how to build production-ready agents using no-code platforms and AI-assisted development workflows.

Key takeaways
  • AI agents differ fundamentally from chatbots by taking actual actions (booking appointments, updating databases, sending emails) rather than just providing information.
  • The three core ingredients to focus on when building AI agents are prompting (how you instruct the agent), knowledge (external data you provide), and tools (the actions it can perform).
  • APIs are the mechanism that enables agents to interact with real-world systems through GET requests (retrieving data) and POST requests (sending/modifying data), making any online action potentially automatable.
  • Clear tool descriptions that specify what a tool does, what inputs it needs, and what it returns are essential for agents to understand when and how to use them correctly.
  • Conversational agents require human interaction (chatbots, voice calls), while automated agents run independently on schedules or triggers, unlocking 24/7 business process automation without manual input.
  • Building production AI agent systems requires self-hosting on platforms like Hostinger rather than relying on cloud-only services, enabling unlimited scaling, predictable costs, and freedom to install custom tools.
  • Real-world AI agent applications with proven ROI include lead generation and appointment setting, research and qualification agents, and voice agents for customer service, with some handling millions of calls monthly.

Recommendations (18)

N8N
N8N uses

"This is a pretty good general purpose assistant that can be created quite easily on n8n, as I'm going to show you."

Liam Ottley · ▶ 30:13

ChatGPT
ChatGPT uses

"So, ChatGPT taking its sweet time. I don't know what's up with this thing lately, but it takes freaking forever these days."

Liam Ottley · ▶ 2:07:02

Google Sheets

"It should be connected to a Google Sheet. Should be able to take in pictures as an input of receipts and then be able to log that info in a spreadsheet for company expenses."

Liam Ottley · ▶ 32:52

Gemini 1.5 Flash

"We're using the Gemini 2.5 Flash model, which is what I actually put specifically in this section here around the model preference because we needed a multimodal model out of the box"

Liam Ottley · ▶ 37:24

Google Solar API

"based off the Google Solar API which is really the powerhouse of this build. We're going to convert their address into a latitude and longitude coordinate. We're going to pass that into the Google ..."

Liam Ottley · ▶ 1:01:37

Google Geocoding API

"Being able to call custom APIs, in this case, we're calling the Google Solar API and the Google geocoding API as well"

Liam Ottley · ▶ 1:03:01

Airtable
Airtable uses

"Love Airtable. I honestly think it's one of the best apps ever. And I use it a lot for various things"

Liam Ottley · ▶ 1:25:52

n8n Chat UI

"this is the platform we're going to be using to take our n8n agent and put it on a website"

Liam Ottley · ▶ 1:03:54

Gemini
Gemini uses

"We have the Google Gemini 2.5 flash. Again, it's got the wrong model here, so we'll just change it over to the one we want"

Liam Ottley · ▶ 1:08:19

Retell
Retell uses

"We're going to want to go up to create a new agent. We're going to do a voice agent. We're going to click on a single prompt agent."

Liam Ottley · ▶ 2:01:21

Wispr Flow
Wispr Flow uses

"Man, if you guys aren't using Whisper Flow, I don't know what you're doing. I'm yapping to my computer all damn day at this point"

Liam Ottley · ▶ 1:47:37

Gemini 1.5 Flash

"We've got our buddy Gemini 2.5 flash. Have they set it up this time? Nope. Still going to get it right. Pop that in there."

Liam Ottley · ▶ 1:59:14

SerpAPI
SerpAPI uses

"We're going to be using this SER API, which is a good one for you guys to learn how to use, which basically allows us to search Google and pull the search results."

Liam Ottley · ▶ 2:22:36

Apify
Apify uses

"We're going to be using Apify's LinkedIn scraper to pull their actual profile data off of LinkedIn."

Liam Ottley · ▶ 2:22:42

Firecrawl
Firecrawl uses

"So, we're going to be using a tool called Firecrawl here, which again is a great one for you guys to learn how to use and get set up."

Liam Ottley · ▶ 2:22:52

Lovable
Lovable uses

"We're going to be creating it on Lovable. So, we're going to be connecting an N8N workflow here to a custom front end on a vibe coded platform of your choice. We're going to be using Lovable here."

Liam Ottley · ▶ 2:21:05

Stripe
Stripe uses

"So come over to your billing can manage our billing info and through Stripe here you can set up a payment method."

Liam Ottley · ▶ 2:12:27

Upwork
Upwork recommends

"You can also go on platforms like Upwork and start building a reputation there, which is a bit of a grind at first, but it does work very well."

Liam Ottley · ▶ 3:00:29

Mentioned (8)

McKinsey
McKinsey "McKinsey released a report in November of 2025 with a pretty shocking finding. 57% of all the wor..." ▶ 1:49
World Economic Forum
World Economic Forum "And the World Economic Forum is projecting 92 million jobs displaced just by 2030 alone." ▶ 2:04
All-In Podcast
All-In Podcast "Here is Naval Ravikant, one of the world's most respected investors and technologists on the All-..." ▶ 2:58
GPT-4
GPT-4 "You've probably heard of these already. We got GPT-4 from OpenAI, Claude from Anthropic, and Gemi..." ▶ 8:06
Claude
Claude "We got GPT-4 from OpenAI, Claude from Anthropic, and Gemini from Google. These are all LLMs." ▶ 8:08
Gemini
Gemini "We got GPT-4 from OpenAI, Claude from Anthropic, and Gemini from Google. These are all LLMs." ▶ 8:10
11 Labs
11 Labs "I think 11 docs. These guys had a pretty good prompting guide. I'll put this link in the resource..." ▶ 2:06:31
Deloitte
Deloitte "they definitely don't have $200,000 to hire McKinsey or Deloitte to come in and figure it out for..." ▶ 2:58:30