Imagine you can turn call from an AIchat bot into super powerful AI agents that actually does things for you.

 This is exactly what is happeningnow with MCP model context protocol.

 So in this video I'll explain whatis MCP, why this is such a big deal.

 Share my framework that you can applyimmediately to turn Claude into an AI agent together with five exciting AIagents ideas you can start using today.

 Let's go.

 so don't let the term MCP scare you.

 In simple terms, it's just a technologytreat it like a universal plug that offers a standard way for any AImodels, including Claude, to connect to the outside data and tools.

 Without MCP, the only wayClaude can access data was you uploading the file in the chat.

 Now with MCP Claude can directlyaccess to any external data source and system by connecting to an MCP server.

 And this is exactly what makesClaude and MCP such a powerful combo because Claude can now retrieve somuch more context and access to tools to perform the actual task for you.

 Now, I won't go through the detailson how to connect to an MCP server.

 There already so many tutorials out there.

 I'll put all the resources below, it's not difficult to follow.

 What I actually want to highlightis generally there are four ways you can use MCP with Claude.

 First, the official nativeintegration offer on Claude, like Google Drive calendar, Gmail.

 Just click connected appsand start the connection.

 Official MCP servers that offer theofficial integrations in case the native integrations is not available, which Ialways recommend because these are well maintained like Perplexity MCP, NotionMCP, they have their official MCP server.

 And then community built.

 MCP Servers.

 You may want to use this if the previoustwo options are not available like Figma MCP is a community built MCP server.

 And finally, self-built MCP server.

 If there is nothing you can findand you can build one yourself using no-code platforms like n8n, like Google Analytics, GoogleDoc, which is powered by my own self-built MCP server on n8n.

 Note for now, I recommend you to useClaude Desktop to have the best MCP support experience other than thenative integrations, but I believe Anthropic will soon adding moreMCP options to the web app as well.

 Before I move on, if after watchingthis video you find yourself wanting to get started with creating AI agents, Ialso recommend you check out these free playbook master AI agents from HubSpot.

 I've put the down link in the description.

 This is a practical guide to helpyou get started with AI agents.

 It covers everything from whatare AI agents, how they work, the latest AI agent landscape.

 High impact use cases to astep-by-step implementation roadmap and common mistake you should avoid.

 You'll even get a practical checklistof how to use AI agents, whether you're just getting started or looking to scaleup what you have already implemented.

 What I like is how it breaks downthe implementation process in the different stages with clear criteriaand examples that makes this feel much more doable, especially ifyou have no idea where to start.

 I think it makes it easy to follow along.

 Check it out in the descriptionbelow is free to download.

 And thank you HubSpot forsponsoring this video.

 Alright, here is the frameworkto turn Claude into an AI agent.

 First, identify yourproblem and needs first.

 Is it research, managingemails or anything else? Do not start with the tools.

 Then determine what necessary tools tosolve this problem and connect Claude with the right tools through the use ofMCP or the build-in native integrations.

 For example, a perplexity MCP thatenable Claude to do web search.

 And finally, using Claude projectfeatures, define the role and responsibilities, available tools,workflow details for this agent through the project instruction.

 So every Claude project is just likea specific AI agents that does certain tasks, and here are five amazing AIagents ideas that I built using this framework and you will know how toapply the same concept to build whatever AI agents that you need on Claude.

 Our first agent is a research agents.

 Research is what every professionals,marketers would need, and this is what AI can really help you to speed up.

 So we have already had different toolsturned on, including perplexity, but to let you see the difference, I will makesure the native web search is turned off.

 So Claude can only useperplexity for search.

 And here is our research agents, andliterally it's just a Claude project.

 Now, the most important partis the project instruction.

 So we will define the workscope, the tools that are available, the workflow details.

 So every time Claude will developa research plan with three question similar to the experience on Chatgptdeep research, and then do the actual searching and then create a visual summaryand also generate a report to Google Doc and return you with the link and alsothe command to trigger this workflow and any important guardrails for this agent.

 So let's try a simpleresearch topic first.

 Let's ask the latesttrend about minimalism.

 And if you want, youcan just type the topic.

 Claude will be smartenough to pick this up.

 So through the process Claude will promptyou as it needs access to perplexity.

 You can click, allow always or allow once.

 Now you can see it will follow theinstructions and generate two sets of beautiful interactive visual summary,recapping the key insights gathered from the research, which is somethingthat I really like Claude about.

 Again, if you want, you can publishthis artifact and share with your team.

 Now what amazing is that Claude willalso return a Google documentation link, which I can access, and it is the reportabout the research topic with simple formatting and the list of source URLs.

 So this time let's try amore complicated example.

 This time I will also uploada company information.

 So in this case it is about Shopify.

 Upload to Claude and ask it to researcha more controversial research topic, the impact of AI on leadership.

 So this time also turn on extendedthinking because I also wanted to propose recommendations from the research.

 Again, you can see it will generatethe visual summary, it’s a priority matrix, highlighting the areasShopify should focus first, which is really useful, and this is reallyClaude strength for generating this kind of strategic insights.

 And also the report and this time ismuch more detailed and completed than the last one, although it is in amarkdown format, but it's not a big deal.

 We can always enhanceit through the prompts, And I really like how Claude breaks downthe recommendations and also with an implementation roadmap using its thinkingability with a list of citations of the full URLs so this is absolutely amazing.

 Of course, this is simplifieddemo, but you can further refine instructions to this agent.

 Perhaps also prepare an infographic,do a more in-depth research plan, send you an email so there areso much more possibilities and potential for this research agent.

 The next agent is what I calla business intelligence agent.

 Basically, this is an agent that interpretall sorts of data around your business and marketing and to interpret insights.

 This is one of my favorite AI agentsideas because we always need to analyze so much data and extract insights.

 These agents will makeyour work so much easier.

 So I have set up a new project forthis business intelligence agent.

 Again, for the project instructions.

 We define the role for this agent, thetools, which is Google Analytics and Gmail in this case, as most marketers, I know wecan't live without web analytics, but if you have connected to other data sources,also specify here for Claude to use.

 Then the workflow details.

 Note for this agent.

 It can also send email for the GA report.

 Now let's ask it to analyze thesession performance for the past 90 days, break down by channels,and then send an email to me.

 Then again, you can see itwill trigger the connections.

 Click allow, and it will nowpull the Google Analytics data and generate the visualization.

 Then it will also trigger the emailsending and everything is automated.

 And you can see the dashboard with thecallout boxes, is also following my instructions to use a purple color schemeand try to have multiple visualization.

 And this is the power ofClaude for visual storytelling.

 And Claude has also sent a report to my mailbox automatically, withthe rich formatting, callout boxes, key insights and recommendations.

 So this is absolutely amazing,Imagine how much time it can save you.

 You can just ask whatever metrics thatyou want to check from a data source and then Claude will summarize theinsights for you and generate reports and even send you the email quick summary.

 So definitely try thisagent ideas yourself And you can even build an automationby using a command for this agent.

 So every time it will know exactly whatto do and auto generate a report for you.

 So think about what data you mightneed to interact all the time.

 Search trend data, keyword data,third party data, and ask Claude to do the storytelling for youand this is a game changer.

 The next is a personal workflow assistant.

 So this agents will connect to yourGmail, Google Calendar, or other productivity apps to streamline yourdaily work process, retrieve context from your files, just like your personalassistant, but note I will be using my own-built MCP server on n8n for the Gmailintegrations, so Claude can also able to send emails and not just read emails.

 ***Again, I already have this agent set up.

 So here are the instructions for thisagent, and it's very important to define what tools this agent should use,like Gmail and Calendar in this case, and what the workflow process lookslike, when they should generate visual summary or to draft you communications.

 So let's say I want to retrieve everythingabout a mentorship program I have done last year with my mentee, Jessica.

 And I wanted it to generate a simpleproject dashboard to recap the key project milestone and status.

 So you will see it will triggerthe connections and calling the MCP server I set up on n8n.

 So click allow.

 Okay, now it is searching the emails andalso the calendar related to this project and retrieving all the context for you.

 So immediately you will have theproject summaries right in the chat with a beautiful dashboard.

 The program overviews, the projecttimelines, key milestone about the project, key actions made.

 So this is super useful wheneveryou just want to retrieve context about certain project.

 Especially it has started long timeago that you want to immediately get a summary of what is going on.

 and this is the key differencecompared with Gemini.

 Although Gemini has the bestintegrations right within Gmail, but it can't generate any visualization.

 Same case using Gemini Advanced.

 I can even ask it to send this as a quick email summary for me, everything is automated that’s really powerful use of this Claude personal assistant.

 You can also ask Claude to check anything for you.

 For example, I can ask it to helpme to check any leads I haven't follow up in the past seven days.

 And it would immediatelysummarize the status for me.

 Who are they? And even with little context forme to make a quick decision, and this is something I found evenGemini can't do well for now.

 And it can also summarize likenewsletter content for me if I'm just too busy to read them all.

 And this is really Claude strength,very detail oriented, and you can just use Claude as your personal assistant.

 And these are just some of the use cases.

 You can also ask it to audit yourcalendar, mailbox, visualize how you spend your time, provide yousuggestions, and not just simply booking meetings because this issomething Gemini can already do for you.

 But what makes Claude differentis how it can always visualize the meaningful insights for you.

 ******The next UX design agent, I must say thatUX design is an increasingly important part of every growth marketing strategy.

 So turn Claude into a simple UXdesign agent will make this very useful, so you can streamlinelot of design analysis process, prototyping by connecting it to Figma.

 So here is our UX design agent.

 So in the project instructions, wespecify tools like Figma MCP, to access the design file on Figma.

 Google Drive to access the userfeedback, and then the workflow process details for each type of tasks, likecode generation, prototype creation, design analysis and other importantguardrails for this agent, like a Figma link should always be included.

 So let's say I have this eStore productpage mockup design, and I want Claude to give me improvement suggestions.

 So first, copy this Figma designfile link and paste to the chat.

 We are not done yet.

 Let's say here is the real userfeedback from our research process for this Sunshine eStore project.

 And we also want Claude toconsider these user feedback when generating the recommendations.

 So now use this prompt to ask it toanalyze all the materials, including the Google Doc on our Google Driveand suggest prioritize action.

 I also suggest, turn on thinking mode forthis task so you can get more thoughtful recommendations with its thinking ability.

 So you can see it will based onthe mockup and feedback to come up with high priority improvement.

 And it even visualize a roughmockups for its suggestions.

 And this is why I always love Claudeabout, and you can see it is addressing the feedback from users in this mockup.

 Now let's say this is our officiale-store style guide on Figma.

 Then we can just ask Claude to createa new product page prototype and following the brand style guideline.

 So this is absolutely amazing.

 It's on brand tone.

 With the improvement made, youcan just download the SVG file and we import to Figma and thenyou can share with your team to immediately visualize theside by side improvement.

 So this will save you so much time.

 *The next project intelligence agents,or you can call it knowledge agent.

 I know most marketers love usingNotion or Airtable as their team shared knowledge repository or keeptrack of different project datas.

 So by connecting with Notion, we can turnClaude into a powerful project agent that help you to analyze the project data andto actively update these notion projects.

 So this is our project intelligence agent.

 For this agent.

 We will connect it withNotion and perplexity.

 So we can also enable thisagent to do some research tasks.

 Again, include the workflow details,like how it should follow the notion template when generating a new page.

 Now let's say we have this SWOTanalysis project on Notion It is used it to store all kinds of SWOTanalysis we do for our competitors.

 And this is the template.

 So first, use this prompt to askClaude to perform a simple SWOT analysis about the brand Canva.

 So you can see it will trigger theconnections with perplexity for the web search and notion to automaticallygenerate the new SWOT analysis on this notion project I just show you .

 Andyou can see it will also follow instructions to generate the artifactfor this task, which you can later publish or export for your teammate.

 And the best thing is Claude willautomatically insert a new SWOT analysis to this Notion Projectwhere you can click on it and it is following the same template.

 So imagine how much easierit will make your work.

 So you no longer need to copyand paste or export and import.

 So this agent willhandle all that for you.

 And now another example.

 Let's say we have thisproject planner on notion.

 It's just a demo.

 It has all the projectand task status details.

 So we can use this prompt to askClaude to analyze this project planner and visualize the project status.

 As well as completion ratesand resource allocation.

 So unlike retrieving your unstructureddata on your personal mailbox, these are structured data and the visualizationis to be shared across your team.

 So how the project status is going,resource workload, task priority, and most importantly, the potentialbottlenecks and the dependency.

 So it will give you immediateinsights about a ny active projects that you're collaborating withyour internal and external team.

 If you don't want visuals, youcan just ask Claude any question about any projects and it willimmediately pull insights for you.

 And same time, you can alsoask it to update the project.

 For example, I can ask it to add anew task on this project planner.

 And note, I didn't use any structuredformat, is completely conversational and Claude is smart enough to pick upfor you and understand that and populate the task details on this planner.

 So this is a huge time saver.

 But keep in mind, the more theautonomy of these AI agents, the higher are the potential risks.

 So for high stake actions, alwayshave an approval mechanism or have humans in the loop before theseAI agents take the actual actions.

 Claude and MCP is a real gamechanger that you shouldn't miss.

 And the thing is setting up MCP on Claudecan be very approachable even if you have little or no technical background.

 The effort is worth the spend if youwant to streamline your workflow further.

 If you want more inspiration,you can join my community.

 You'll get access to my otherfeature content and all my tested prompt I share on my channel.

 You can find the link in the descriptionto join, and before you go, I highly recommend you to watch this videoabout AI agents so you have a better concept when you should use AI agents.

 I will see you next time.