00:00AI agents are everywhere right now, but I think we have made them sound way more complicated than they actually are

00:04When someone says build an AI agent, you probably imagine coding APIs, automation tools, and one of those giant workflows with 20 different boxes connected together

00:17But your first AI agent doesn't need any of [music] that

00:19In this video, I'm going to show you one of the easiest way to build a genuinely useful AI agent using Claude

00:24We're basically going to describe what we want in normal English, give the AI a job, test the result, improve it, and then make it run automatically and no coding at all

00:41Before we build anything, let me quickly explain what an AI agent actually is

00:45Normally, when you use AI chatbot, you ask it a question

00:48It gives you an answer, and that interaction is basically finished

00:52An AI agent is slightly different because instead of giving the AI one question, we give it a job or an outcome that we want it to achieve

01:01The AI can then work through the steps required to complete that job

01:05Depending on the task, it might search the internet, read multiple sources, compare information, work with files, use connected apps, organize everything, and then give you the final result

01:20For our first agent, I want to keep things really simple, but still build something that I would actually use

01:26We're going to create a daily AI research agent

01:28So, every morning, I want this agent to search the web and find the five most important AI stories from the previous 24 hours

01:36I don't want every tiny funding announcements or random AI update

01:41I want it to figure out which stories are actually important, give me a short summary of each one, explain why each story matters, and include links to the original sources

01:53Then, once we know that our agent is doing a good job, we'll make it run automatically every morning and then save the finished report straight into Google Drive

02:00And obviously, you can replace this example with almost anything you want

02:05You could create a stock research agent, a competitor research agent, a job search agent, a travel search agent, a content idea agent, or even an agent that checks information from your connected apps and tells you what needs your attention

02:18But for your first one, I would highly recommend choosing one very clear job instead of trying to build an agent that does [music] everything

02:31So now I'm going to build this using Claude co-work

02:33If you have used Claude before, you're probably familiar with normal chat where you have a back and forth conversation with Claude

02:39Co-work is designed more around giving Claude larger tasks and letting it actually work through them for you

02:45So open Claude, preferably on your desktop, switch from chat to co-work near the message box, and now we essentially have our workspace for building this agent

02:57The first thing we need to do is explain the job clearly, and this is where people sometimes make agents unnecessarily complicated

03:03You don't need to write some massive technical prompt, just describe what you want the finished result to look like

03:09For example, I could say, "Research the five most important artificial intelligence stories from the last 24 hours

03:17Prioritize major AI product launches, new AI models, important research, and significant announcements from companies like OpenAI, Anthropic, Google, Apple, Meta, and Microsoft

03:29For each story, give me a short summary, explain why it matters, and include links to reliable original sources

03:37Avoid duplicate stories and minor announcements

03:39That's already enough to give Claude a very clear job

03:44Did you notice that I mainly described the outcome? I'm not telling Claude, "First search the website, then open this website, compare these three articles, then create a document

03:52Claude can figure out many of these intermediate steps itself

03:57Now, we let Claude run the research

03:59It has the goal, it understands the output I want, and it can work through the intermediate steps necessary to get there

04:10>> [snorts] >> Before we move on, I want to quickly thank HubSpot for sponsoring this part of the video

04:15If you enjoyed building this agent and you want to experiment with more advanced ones, HubSpot partnered with Futurepedia to create a completely free build your first AI agent course

04:26And this is actually a really useful next step after what we just built

04:31There are 18 hands-on videos where they walk you through building different AI agents using tools like N8N

04:38And it's not just explaining what an AI agent is, you're actually building things

04:43For example, you will learn how to connect an agent to Gmail, Google Calendar, and Google Sheets, build a personal assistant, create an agent that turns YouTube scripts into LinkedIn posts, and short-form scripts, and even build a customer support agent trained on a website

04:59They also give you the actual system prompts and explain the really simple brain, memory, and tools frameworks that you can reuse when building your own agents

05:08My favorite part is that it's very hands-on

05:10You're not just learning the theory behind AI agents, you're actually building useful agents step-by-step and connecting them to tools that you already use like Gmail, Google Calendar, and Google Sheets

05:24The whole course is free, so I'll leave the HubSpot link below if you want to check it out

05:28Now, let's get back to the video

05:35Once Claude finishes, look at the results

05:37Your first version probably won't be perfect, and that's completely normal

05:41You can improve the agent

05:41I can say, "Keep each story under 100 words

05:48I can revise further and customize it with all my requirements

05:50Now, the agent becomes much more useful because it understands the actual workflow that I'm trying to accomplish

05:58The next thing to understand is tools

06:00Agents become much more powerful when they have access to tools, but again, this sounds more technical than it really is

06:06A tool is simply something the AI is allowed to use

06:12Web search is a tool

06:12Google Drive can be a tool

06:15Gmail can be a tool

06:15Your calendar can be a tool

06:17Different services and connectors can give an agent access to different information or actions

06:24For example, if you connect Google Drive, you could create agent that works with information stored inside your drive, rather than requiring you to manually copy and paste everything into Claude

06:34If you connect an email service, you could build workflows around finding messages that need your attention, summarizing certain emails, or helping you prepare responses

06:44For our AI news agent, though, we honestly don't need many tools

06:49Web research is enough, and I would actually recommend keeping your first agent this simple

06:52Don't connect 10 different apps just because you can

06:56The more access you give an agent, the more complicated the workflow becomes

07:01Start by asking, what does this agent actually need to complete its job, and only give it those tools

07:10At this point, our AI research agent already works, but there is one problem

07:15I have to remember to come into Claude and ask it to do the research every morning

07:19So, the final step is to automate that part

07:21Inside Claude co-work, go to the schedule section, and create a new schedule task

07:28I'm going to call mine daily AI news brief

07:31Then, I can use essentially the same instructions we just tested, but I'm going to add one more thing

07:36I've connected Google Drive, so I'll tell Claude, "Every morning, create this AI news brief and save the finished report to my daily AI news briefs folder in Google Drive with the date in the file name

07:51Now, to run this task every day automatically, I can again simply say run this workflow every day morning at 8:00 a.m

07:58automatically as a scheduled task

08:00So, every day Claude can do the research automatically, create the report, and save a new dated copy directly into my Google Drive

08:07I don't even have to remember to come back and run it myself

08:16You might think couldn't I just paste this exact prompt into normal Claude every morning? Absolutely, you could

08:23The difference is that then you're still responsible for starting and managing that process every single morning

08:27Here, we have given Claude the goal

08:29We have given it instructions about what a good result looks like

08:33It can use tools like web research to gather the information

08:38It can work through multiple steps to complete the task

08:40And then, we have told it to repeat that task on a schedule

08:43That's really the easiest mental model for an AI agent

08:45It has a goal

08:47It has instructions

08:47It has tools

08:50And it can work through multiple steps to complete the job

08:52And if the task happens repeatedly, automation makes it even more useful

09:01One thing to keep in mind before connecting everything, be careful on how much control you give an agent

09:05There is a big difference between letting it research or summarize information and letting it edit files, send messages, delete data, or take actions inside your accounts

09:17Start with low-risk tasks like research, planning, organization, and drafting

09:22For anything that can make important changes or communicate on your behalf, keep a review step in place until you're confident the workflow is reliable

09:31And that's really all you need to build your first AI agent

09:33Let us know in the comments some of the interesting agents that you have built or going to build

09:38I'll catch you in the next one

09:40This is Sanjana

09:40Bye-bye.