Your site is slow. People leave. Google shrugs. You tweak your theme, compress your images, scream into the void. Still slow… The problem might be your cache plugin, or rather the cache plugin you’re not using yet.
If you want to get good at link building, you need to practice. And one of the best reachable goals you can set for yourself is to build your first 100 quality backlinks. Why 100? To be honest, it’s a bit of an arbitrary number. But for a lot of low and mid competition niches, it’s enough to get a meaningful amount of organic traffic.
For example, this golf site gets around 4,500 monthly search visits with around 150 linking domains across their site. This low authority travel site has around 175 referring domains and gets over 4,000 monthly search visits. And this parenting blog with around 70 referring domains gets over 5,000 monthly search visits. Most importantly, building 100 quality backlinks will give you the practical experience you need as a link builder because you’ll have to communicate with a lot of different people.
So, in this tutorial, I’m going to show you how to get your first 100 backlinks using tried and tested tactics.
Stay tuned. [music] Backlinks are undeniably the lifeblood of higher Google rankings. And once you start getting them, organic traffic often climbs in tandem. But not all backlinks are created equal. I often see new sites that start by building low quality backlinks with comment spam, forum links, PBNs, and links from coupon sites.
And sometimes, these backlinks are enough to move the needle initially. But building low-quality links can be a dangerous game to play because they can literally wipe your site off of Google. Now, while link building can vary from niche to niche and even from page to page, there are a few tried and tested tactics that can work for anyone with minimal experience.
So, let’s start with the easiest method and that’s to start with organizations, communities or clubs that you’re already part of. Whether it be personal or pleasure, in everyday life, we integrate ourselves in communities.
That can be anything from a law association to a non-profit organization to a school’s parent advisory board. If you’re a part of one of these organizations and it’s relevant to your site, ask for a link.
Oftentimes, they’ll have team or advisory board pages where it actually makes sense to link to your site. Start here because it’s about as easy as it gets. But that’s only one link.
So let’s get into our second tactic. And that’s to use HARO to build authoritative links to your homepage. HARO stands for Help a reporter out. It’s a service that connects journalists with sources and sources with journalists. After you’ve signed up as a “source,” you’ll get emails with a list of queries from journalists at various publications.
And these include Business Insider, The New York Times, and USA Today to name a few. Now, there are tons of requests that come in on a daily basis and the majority won’t be relevant to you. So, you can set up a simple Gmail filter to sort through the noise.
Just go to your Inbox and click on the caret to bring down Gmail’s search options. Next, set the “From” field to haro@helpareporter.
com. Then, you’ll want to set the subject to HARO within square brackets since all of their emails include that in the subject line. Finally, set the “Has the words” field to any keywords you want to monitor. And you can also use the OR search operator to include multiple keywords or phrases. Click Search to see the results your search filters would include and check out some of the emails to ensure you’re getting relevant results.
If everything looks good, click on the caret again and then click Create filter. Now, even though we’ve filtered down the results to relevant ones, it doesn’t mean journalists are going to cite you just because you responded. And while you should go the extra mile to provide unique and insightful information, half the battle is in responding to the right questions.
So, to increase your chances of getting mentioned, look for queries where they’re likely looking for multiple experts on the topic. For example, in this query, Bustle is looking for relationship therapists as in the plural of therapist.
And they want to know more about boredom in relationships. Now, the description is even more clear that they want multiple experts. She says: “I’m working on an article called “13 common mistakes that lead to boredom in a relationship.” So more likely than not, she’s looking for multiple experts that can fill in the blanks in her outline. So, if you happen to be a relationship expert, provide your best answer and then move on to the next query or carry on with the rest of your day.
Bottomline, HARO is a super-easy way to get high quality backlinks because the journalists are the ones that are soliciting sources and not the other way around. I’d recommend using HARO without an end date in mind. The quality of links are just that good for the amount of effort it takes to respond. Alright, the next tactic is to do some guest posting. Guest posting is when you create content to be posted on another website.
And generally speaking, that post comes with attribution and a link back to your site.
Now, while some sites won’t allow you to link to yourself within the content, most will, as long as it makes sense and adds value to your guest article. So the first thing you need to do is find websites that are likely to accept guest posts. To get started, you can use Ahrefs Content Explorer, which lets you search through billions of pages and get SEO metrics for all of them. Just search for a topic related to your niche and run the search.
Next, let’s set a Domain Rating filter to weed out both very low and very high authority websites. So I’ll choose a range like 30 to 60.
I’ll also check the “One page per domain” box since we don’t need to pitch the same website multiple times. Finally, I’ll set the “Published” filter to the past 90 days, which will help us narrow in on websites that have published or republished content in the last 3 months. Now, we still have around 90,000 websites to pitch, which is just way too many.
So let’s head on over to the Websites tab, which will show you the top 100 websites from your results. And to get a better idea of which sites would more likely accept guest posts, let’s sort the table by Authors, because if there are multiple authors on that site, then there’s a higher chance that they have guest contributors.
Now, it’s just a matter of looking at the domain names, visiting ones that look relevant, and pitching your guest posts. Now, it’s important to note that while guest posting can be a great way to build links, what often gets overlooked is that when you write for reputable sites, you have the opportunity to demonstrate your expertise to an audience that someone else has built. That means you can get exposure backed by trust.
And since time is finite, it’s worth prioritizing websites that will likely provide the best overall value for your time and expertise. Alright, the next tactic works great for experts in their field and that’s to do podcast interviews. Much like guest posting, being interviewed on a podcast puts you in the spotlight as an expert in front of someone else’s audience. Now, the thing I love about podcasts as a link building strategy is that it only takes around an hour of your time and links are almost a given if you choose your podcasts appropriately. A lot of podcasts have “Episodes” pages on their websites.
And these pages almost always include a link back to the guest’s website. So to find podcast prospects, you can simply reverse engineer a podcast interviewee’s homepage backlinks.
So, assuming you were in the SEO niche, you might look at Arefs’ backlinks because a few of us have been on some podcasts. So just go to Arefs’ Site Explorer and search for ahrefs.com and set the search mode to URL since again, podcast links usually point to the guest’s homepage.
Next, go to the backlinks report. Now, since Arefs is a pretty established brand, you’ll see links from various sources. So, too narrow in on just links from podcasts, just search for “podcast” in the Include box, and set the filter mode to search in the URLs and titles of referring pages.
From here, you can sift through the results, visit relevant pages, and pitch yourself as a guest when appropriate. Another great thing about podcast interviews is that oftentimes, hosts will also link to other resources that are mentioned in the interview.
So it’s actually possible to get links to other pages across your site if it comes up naturally in your conversation. The benefits to being on podcasts goes way beyond links. You get the chance to meet like-minded people in your industry and building your network can go a long way even from an SEO perspective. Alright, the final thing I recommend you do is email outreach for your best content. Now, don’t get me wrong, getting links to all pages on your site is a great thing.
But chances are, you won’t have time to do outreach for every single page on your site. Plus, it’s a lot easier to promote something that’s unique or insightful versus something that’s informative, but generic. For example, let’s say you have a personal finance site, and you have some unique data on how the pandemic affected credit scores across the nation.
That’s interesting and it’s probably something that people in your niche will actually want to be contacted about. And if they’re impressed by your content, they’d probably link to you in existing or future content.
Whereas a post on let’s say, “What are credit cards,” could be well-written and informative, but you probably won’t have anything to say that’s much better than what’s already out there. At least enough to motivate someone to link to you. Now, there are so many ways to do outreach for links and your approach will vary depending on the topic and angle you’ll be taking. So instead of going through a hypothetical example, I strongly suggest watching our link building module in our SEO for beginners course or if you’ve already had some exposure to email outreach for links, then check out some of our more advanced tutorials in our link building playlist. I’ll link up both in the description.
Now, you might be wondering, how long will it take to get my first 100 backlinks? There really isn’t a definitive answer, and I don’t think speed should be your goal especially when you’re just starting out.
Think of link building like eating steamed broccoli every day. It may not be the most exciting or delicious, but just as broccoli delivers essential nutrients to your body, links deliver trust and authority to your website, which results in higher Google rankings. So what’s important is that you stay the course, implement these tactics and iterate on them as you get hands-on experience.
Getting high quality backlinks isn’t easy. And that’s probably why it’s still a ranking factor. So go and try these tactics out for your site, and if you enjoyed this tutorial, make sure to like, share and subscribe for more actionable SEO and marketing tutorials. I’ll see you in the next one.
A sweep account is an account set up at a bank or other financial institution where the funds are automatically managed between a primary cash account and secondary investment accounts. Function A sweep account combines two or more accounts at a bank or a financial institution, moving funds between them in a predetermined manner. Sweep accounts are useful in managing a steady cash flow between a cash account used to make scheduled payments, and an investment account where the cash is able to accrue a higher return. Many banks and financial institutions offer a sweep account service for personal customers and small business owners.
It has also become part of the arsenal of services offered by credit card companies.
Mechanics In banking, sweep accounts are primarily used as a legal workaround to the prohibition on paying interest on business checking accounts. In this system, the funds are described as being “swept overnight” into an investment vehicle of some kind. The choices for sweep investments are often the following: money funds, and what are known as “Eurodollar Sweeps” or “Repo Sweeps”. Eurodollar sweeps are legal transfers of funds to the bank’s offshore entities, although essentially they are just an accounting technique to allow the banks to have full lending of the funds without the reserve requirements normally required and without having to pay for FDIC insurance. Essentially, the funds are just unsecured obligations of the bank and therefore are paid the highest interest rate offered by the bank to overnight deposit borrowings.
“Repo Sweeps” are for companies that are concerned about the safety of the bank. In this arrangement, the swept funds on deposit with the bank are secured by some of the bond holdings of the bank.
If the bank were to fail, the depositor would just be given the bond holdings and then could sell the bonds to get their money back. Larger corporate bank accounts are charged numerous fees for each of the services the bank offers, however the bank rebates these fees based on the companies account balances in a process known as account analysis. = How it actually works = In a sweep account A cash account is set up first and a lump sum of money is deposited into that account.
A financial advisor and the client will discuss and determine an average balance that should be kept in this account. Depending on the institution’s service, this amount may be pre-determined.
Most of the extra cash above the average balance will be invested into a money market, CD, or some other form of investment that can be easily liquidated. When the balance in the cash account falls below the pre-determined average balance, some of the investment is liquidated and the proceeds get deposited into the cash account, thus maintaining the average balance. If the initial calculations are done correctly, the interest on the cash and returns on the investments should yield a large enough return that will increase the total value of the sweep account.
During a bad economic cycle, the funds in the investment accounts may fall low enough that substantial gains will not be possible to maintain the average balance in the cash account. In these cases, the financial institutions would ask either for more funds to be put into the investment account, or recommend other forms of investments and liquidation. The financial innovation of sweep accounts is particularly interesting because it was stimulated not only by the desire to avoid costly regulation, but also by a change in supply conditions — in this case technology.
Company policy issues Some companies choose to have all of their funds swept into a sweep account if they believe that the increased earnings will more than offset the fees they would have been rebated, should they have left the funds in the account. Other companies calculate the approximate amount needed to rebate the fees and then only sweep funds in excess of that amount.
Companies pay extra for more complex investment strategies, and for more detailed communication from their bank. For example, knowing when the checks they issue will probably clear, enables them to more precisely determine how to invest and for how long.
By now, you’ve probably started using ChatGPT, right? It’s not rocket science. Anyone can ask questions, and it’s going to give you answers. In school, we learned that there are no bad questions. In ChatGPT world, there are.
It’s not going to tell you that, but it’s going to give you poor quality answers, and you’re just going to waste a lot of time going back and forth. I’ve been there—super annoyed—so I decided to spend some time to find the best prompts to get the most out of ChatGPT. My first tip for you is to take advantage of custom instructions, which you’re going to find by clicking on your profile icon. So, when you go to custom instructions, you have the ability to hand over a note to ChatGPT that explains who you are, what you want, and how you want ChatGPT to respond. This way, you won’t have to repeat your preferences in every single conversation.
So, the first question is: what would you like ChatGPT to know about you to provide better responses? It helps if you can provide some context about yourself.
So, for example, if you’re a teacher, let it know. If you’re a student, an accountant, a lawyer, let it know. This way, you can get responses that are more relevant to your line of work.
If you want responses that are relevant to your region, tell it where you live. Not the exact address, but just the area where you are. So, for example, you could say, “I’m a software developer based in Chicago working with Python.” Or you could say, “I’m a marketing professional in New York writing advertising copy.” Right, you get the idea.
The next question is: how would you like ChatGPT to respond? We get some thought starters, like how formal or casual should ChatGPT be? For example, you could put in, “Language and tone should be friendly and casual.” You can decide if ChatGPT can have opinions on topics or remain neutral, and if responses should be long or short.
And this can really make a difference because you can get rid of a lot of frustrating back and forth.
So, for example, let’s say you’re good in Excel and use ChatGPT to help you out when you get stuck, but you don’t like seeing all those explanations about the solutions. So, what you could write is, “When I ask for Excel formulas, just provide the most efficient formula without any explanation.” If you were a programmer and you didn’t want to see all those programming explanations, you could type in, “When I ask you for code, just give me the most efficient code with code snippets without additional explanation.” Right, so that’s really helpful. In this case, I’m picky about Excel formulas.
I’m going to leave this in and click on Save.
Now, let’s go and start a new chat, and I’m going to ask it for a formula just to make sure this works. Let’s say I’m in Excel, and I’m struggling with updating this formula. Currently, it’s returning everything that’s greater than 12,000, but I want to change this to be between 12,000 and 15,000. And I have no idea how to tell it to do it between these values.
I’m going to go back to ChatGPT and type in my formula, tell it to update this Excel formula so it returns values in the B column that are between these two. And when I send this, it just provides the solution without any explanation. Now, without that custom setting, this is what I would get. And sometimes you would just end up with a lot longer explanations like this one. These are great if you don’t know your way around, but if you do, they can be pretty annoying.
Another thing that could be quite helpful is to tell ChatGPT to always inform us about the confidence level of its answer. This could be quite helpful for factual topics. Now, we can also expand on this and say, “When your answer includes facts, always provide a valid URL with the source for your answer. And if you speculate or predict something, inform me.” Okay, so let’s test this out.
I’m going to save this, go ahead and start a new chat, and let’s ask it over the FIFA World Cup winners of the ’90s. When I run this, I get: 1990: West Germany, Brazil, France.
Confidence level is high, and I get a list of valid URLs directly from FIFA.com. Right, so these settings can be really helpful.
I’m sure you’re going to find them handy. Now let’s move on to prompts. The first one is to write like you. So, if you ask ChatGPT to write some text for you, the results will probably sound a bit generic, right? Even if you’re emphasizing the custom instructions and the tone and the style that you want, it might not properly reflect your style of writing.
Now, the good news is that you can teach it to write in your own style by giving it some examples. So, first, we’re going to explain to ChatGPT what we’re going to do with this prompt. “I’d like you to help me write articles from my productivity blog.” Just replace this with whatever type of blog or article you need. “First, I want you to understand my writing style based on examples that I give you.
You’ll save my writing style under ‘LG_STYLE.'” Now, this makes it easier to refer to later. “After that, you’ll ask me what the topic of my specific content is. You’ll then write the article using LG_STYLE.” Okay, so let’s give it a try.
Okay, so it understands what we’re trying to do and it’s ready for some examples. I’m just going to go and grab some copy from my website. Let’s copy this paragraph from the About page and paste it in as example one of LG_STYLE. Now I’ll give it a second example of LG_STYLE. I’ll just go and grab the other copy from here, and paste it in.
So, it summarized my style as informative, personable, and aims to establish a connection. And now it’s ready to write our content. So, I want to write an article about the importance of daily coffee for productivity. Cool, start writing it in my personal writing style, the one that it previously saved. Now, you can, of course, continue working on this and make it better.
You can also come back to this chat and ask it to write other related articles. And by the way, if you love your daily coffee, subscribe to this channel because we all love coffee around here. Next up is self-critic. So, another great option is to ask ChatGPT to review its own text and provide feedback. Now, it sounds funny, but it really works well.
So, let’s say I asked ChatGPT to provide me with a summary of why Python and Excel can work well together and it comes up with this reply which I’m not really happy with.
So, I’m going to ask it to act as a critic. Be ruthless, analyze the text, and tell me where it can be better. It will go over the reply and provide step-by-step feedback on potential issues. For example, with clarity and how adding specific examples could make the summary better, how we could highlight specific capabilities.
It also went ahead and revised this original reply, giving examples of Python’s strengths and Excel’s strengths. From there, you can further improve on this reply by asking it to specifically emphasize and include some of the previous pointers that it gave us. It’s pretty cool, right? Next up is self-prompting.
So, how about using ChatGPT to self-prompt to optimize its own prompt?
Here’s how you can do that. So, let’s say I want to send an email to my team encouraging them to participate in our team-building event. To get the perfect prompt, I could ask ChatGPT, “Write five perfect ChatGPT prompts that will really show off the power of ChatGPT. Focus the prompts around writing an email to my team encouraging them to participate in our team-building event. Before you write anything, ask me questions until you’re sure you can create the optimal prompts.
” It will usually come back with some questions about the topic, in this case, about the purpose, dates, and locations and other useful information. Now, after I provide my answers, so, for example, for any particular incentives or benefits, I’ve put “nice dinner, nice breakfast, no work,” then I send this off, and it creates five possible prompts for me. Now, these are prompts that will help me get the best reply.
So, one is, “Draft an email to your creative team encouraging them to join a special team-building event. Mention the importance of taking a break from work.
” Another one is, “Compose an email inviting your team to a casual and fun team-building event. Stress the importance of building strong relationships within the group and the opportunity for a nice dinner.” Okay, so I like number three better. I’m just going to tell it to use it.
Now it just provides me with a prompt, but I actually want it to run it.
So can I do it? It starts writing the email. Now, we can see it has a nice subject, the tone is soft and casual, and it’s highlighting the bonding and relationships. Right, so we can see it sprinkled in different places, like we can share stories, laughter, and delicious food. We’ll have a great breakfast.
There’s no work, no deadlines. So, it’s a very customized email. Now, compare this to a case where I don’t optimize the prompt. So, I tell it to write an email to my team to participate in our team-building event. It’s no surprise that I get a very generic email about team-building and what generally team-building events are designed to do.
So, as you can see, self-prompting can give you a much better output. But you can also take this self-prompting a step further. So, if you go back to the step where we got the different prompts, we could ask it why a prompt would work well. It gives me detailed information about the reasons it thinks this prompt is effective, but I’m not so sure. So, I’m going to ask it, “which prompt do you find the best?
” It tells me that prompt three effectively combines the key elements I provided, so it could work well in my case, which it actually did. Often when you ask ChatGPT to write something, the reply can be rather long.
So, one way to avoid this is to tell it from the beginning to stick to a specific word count. Now, if this is something that you want in every single reply, you can add it to your custom settings. If not, you can add it to your prompt.
So, for example, we want to know the advantages of using XLOOKUP over VLOOKUP in Excel. I’m going to add that the maximum length of the text should be 500 words. A few moments later. Okay, so let’s double-check. I’ll copy this, go to a new page, type in “word.
new” to open a blank Word document in the browser and paste in the text. We can see down here that we have 469 words. Now, another alternative is to tell it to reduce the length of a text that it already gave you. So, a good prompt for that is, “Now, say the same thing more concise and prefer using only 60% as many words or whatever percentage you need.
You could try cutting it down even more, step by step, until you get the crispiness that you like.
Your audience is going to be thankful for it.” Specify the output format. ChatGPT has many different output formats, not just plain text. So, for example, you can tell it to give you the response in a table format. Let’s say, “Create a table with the winners of the FIFA World Cups between 1990 and 2018.
The headings should be year, winner, and runners-up.” So, we get a table. We can just highlight the content, use the shortcut Ctrl+C to copy it, move over to an Excel sheet, and paste the table with Ctrl+V. Now, alternatively, you can tell it to output the table as CSV. Then all you need to do is to copy the code from here and paste it into a text editor and then save it as a CSV file extension.
Now, if you need this, let’s say for your website, you could output as HTML. Moments later… I’m just going to test this out.
So, I’m going to grab this code and paste it on our site in an HTML editor.
Then, when I go to preview, I can see the table, but it doesn’t look really nice. I’d rather have borders and spacing. So, let’s improve the prompt and ask it to add the borders and spacing. Later that night.
Now, when I replace the code, I have a table that’s a lot easier to read. Right? So, you can also ouput in different format like JSON or XML. Or if you need it as a Pandas data frame, you can do that as well. Just give it a try.
SO, these are some tips to get the most out of ChatGPT or any large language model AI, actually. It really comes down to the old principle: garbage in, garbage out. Keep this in mind, and you’ll definitely make better use of these new tools. I hope you found this helpful. Do subscribe if you aren’t subscribed yet, and I’m going to catch you in the next video. https://www.offerlab.com/jv-optin?olaff=RhSAaCtYwQxGEy7bXbETRgta&utm_source=clipboard
Hi everyone, and welcome back to the channel, today’s goal is super simple. I’m just going to help you build your first AI agent. If you haven’t done something like this before, this video is perfect for you. So let’s get started. Now.
I’m going to use a tool called NA 10. It’s an amazing AI workflow tool, which can do literally anything in the world, and we are going to use that to build.
You can simply go ahead and click on get started and sign up. once you come here, you get to something like this and you have to click on create a workflow. I’ve already done that, and I have this particular workflow with just a simple note.
And I’ll also tell you how can you add a note in a second? This is the blank space that you’re going to get started with, so let’s build together. When you are thinking about building an agent, start with an idea. My idea is pretty simple. I want to do two things.
Ask for a topic from the user, and create content about that topic using an AI agent and send an email. I’m just going to click add first step and select my trigger. Now what is a trigger? A trigger is literally, as the name suggests, to trigger your workflow and trigger your AI agent. when does it get started?
I’m going to search for chat trigger and click here. Once this is done, I’m just going to like, you know, I can put settings, I can add parameters, I can do something.
I’m just going to keep chart, trigger here, and that’s it. And then a couple of things that you can do here to make your UI look better is you can write user input, I am just renaming this so you can understand that, and that’s pretty simple. We have our building block with us, and now what I’m going to do is click on this plus button and select.
As you can see, there are multiple options. We are just going to click on advanced AI right now.
That’s all you want to do. Now, you have a ton of template options and another a hundred different options you can select from there. We are just going to pick the first option, which is the AI agent.
Now, as you can see, it automatically comes up with some settings created. just to show you this is how it looks connected to a chart, trigger note. there is an error because we still have to do a lot of things, but just getting started, the first thing that you would like to do is click on this chart model option. And once you click on chart model, which model do you want to use Now you can select any model that is there. The only thing is all of these models are external So that means you will have to go ahead and sign up on any of these platforms, open AI API, or you have to sign up for Cloud API and anything like that, right?
So you have to pay separately for all of those things.
You can go and sign up here and get a API key and you can do the same with Claude from an API perspective and purchase their keys. doing that is super simple, given that you are doing this for the first time, I’m going to show you how does this work, right? So first of all, you’ll come to something like this and you can log in and sign up. Once you do that, you’ll end up on this platform where you can see multiple options exist.
So if. I just show you there’s dashboard logs, traces, and everything. This is for open AI right now, for cloud, the system looks a bit different, but the logic stays the same. I have different API keys available here. these are all saved and obviously I’ve hidden them so they are not revealed.
you’ll come to something like this. Now, what you have to do here is create a new secret, a VI key, I’m just going to write.
This is YouTube test, And you can select different projects or something like that right now, just like, don’t even worry about it. And click that. And here is where you get the whole key.
Don’t worry, this key is not going to be usable. I’m going to delete it after this. Click on copy. And now you are technically done. You come back here and the first thing that you can do is now you can come to this language model and select open AI Now.
As you can see, I already have a credential created for open air.
Now, what is a credential? It’s nothing but just an authentication process that says, okay, you know what? This is my key. I own this, and here is the proof that I own this.
So you are going to click on create new credential. I’m going to enter my API key here, right? And I can enter an organization ID or a base URL. Something like that. But again, very simply here we are just going to write API key paste that and I’ll just read him this to YouTube test so that I remember that what is this key usage for?
I’ll click on save and. This is ready it online tested. The key is valid, and I can then select YouTube test. You will probably just have a single credential, Now another thing that I should not miss to mention is that you need to pay some money to run this.
So for example, this API is not free.
Now, to use any of these APIs, you have to pay some amount of money, click on settings, and once you click on settings, you’ll get to billing. Once you get to billing, you can add a credit balance. As you can see, I have three point $14 now, so I don’t need to do that, but once you click on add to credit balances, you can then add some amount here, and select your payment method. Let’s come back here. I have the YouTube test credential.
I have this, I’m just going to keep this here. Now again, this is what I need to connect as a chart model. As you can see, I can only connect a single chat model, right? I can’t have multiple chat models available here. Next thing that I want to do is, now obviously I have the user input.
I have this agent, but this agent knows nothing on what it has to do. So I want to come back here and select, as you can see, an option system message.
Every LLM model works on two things. It has. A system message and then a user input.
the response that we get back from the AI is called assistant message or AI message, whatever you want to call it. Perfect. So when I write, hi WhatsApp, this is the response that I get, right? Hey, I shall not match X, Y, Z, whatever. This is a user message and this is a.
AI message, but now in behind this open AI has written something called a system message, which is the definition on how the LLM should respond. So they might have written B fund B. Serious or something like that. And that’s what we call as a system message. So in the system message, what we will use it for is to define how should the agent perform.
So we are going to keep it super simple. I’m not going to make it an extremely complex prompt here. I’m just going to keep it super simple so that you can get started by building a first agent.
I’m just going to use basic personal prompting techniques and say you are. A newsletter expert who has been writing newsletters for the last 20 days.
Based on the user input, create a small newsletter to send to the user. Is this the right agent prompt? No, but we are just going to get started and reply and use this. That’s it. I can now technically start testing my model.
So if I come back, I just have a chart. I’m just going to write an example of. India history, right? This is the newsletter that I want based on this. If I’ve given this the topic, it should use AI agent.
As you can see, it started using.
It has started working, and then it will also go ahead and use the open AI chart model and reply back to me with a newsletter about the history of India or hopefully something around that. As you can see, it has responded with a pretty good newsletter, which I believe is Well modified for the prompt that I’ve given it, very simply,. Welcome to the Indian History Digest. It has given some important stuff, upcoming events, which it has automatically thought by itself.
Interesting tidbits and a couple of other things, which I believe is super cool given that we gave it very simple stuff. It also gave itself a name, the Indian History Digest team, Now, this is amazing to get started, right? But the goal is not just to have an AI agent. actually, I can technically do this in charge video also, obviously true, but the idea is an agent is not complete until we add a tool.
Now, what is the difference?
With a tool being added. Let me just show you. Okay? Now the point is when you add a tool to an AI agent, AI agent gets access to do stuff, to do stuff outside its own current parameters. Right?
Now what you did, you could do it in charge PD, because it is just interacting in a chat based format, and an AI agent can do.
Actions by its own understanding based on the instructions So if you remember, we want to create an content about topic and send an email. So I’m going to come back here and connect a Gmail route so you can just, so Gmail and there is like a ton of tools here and select all these options. obviously you’ll have to set up a credential. You can use your Gmail account, log in directly from there, I have custom.
Credentials created, click on create new. You can input all of these details, or if you’re using NA 10 on a public option you will have an option to sign in and completely link the account by just a click of the button.
Given that I’m on my own server, this is a complexity that I have to deal with, you don’t even have to worry about that. Okay, perfect. We are gonna close this.
We are going to close this, and now you can see there are multiple options when you’re setting up a tool. So let’s go one by one, what is the tool description? this is very simply where we are going to define. What is this tool going to do? So if I have set automatically, then this is technically automatically set by an attend and by the LLM concern is something I love to use the manual option, it gives you a bit more understanding on how you use it, It gives you a bit more space to completely expressively tell what it is used for.
So I’m gonna say it. It’s simply to send an email with a newsletter in the body, right? Again, I’m doing a very clear description of what the tool is.
I can also just say, send an email using Gmail. That’s it.
If I come back here, click on resource, you can see there are multiple options. I can reply to a thread, I can create a draft. I can label something, or I can just send a message. I want to just send a message and then I’m going to come back here. I’m going to input my email idea and also input the subject.
Right now, you would be like, I don’t want to write a subject. I want AI to write the subject, and you will be absolutely correct. Again, for this, we are going to use our simplest, easiest format. Just come back here and you will be here. Just click on this particular button.
then you can define what the subject should look like. I will say a simple forward word subject as a headline for the newsletter. So this is an input that the AI model will get when it is going and looking at the tools that it has access to.
When it figures out that this is the tool that has access to, and it has to use this tool, it’ll use this tool by describing the subject itself the same way. I’m also going to describe this particular message, which is the.
Email body. So message here is nothing but the body of the email. That means just zoom it properly so you can see. This is automatically the body of the email. That’s it, right?
we can say description should be here, like this is the newsletter audio or something like that.
But if you see the email type, there are two options. Text and H, TM LI would like to actually use htm l I’ll show you. How does that translate? Now here, I’m just going to input my email id.
It’s the same email id, which the email is going to actually get triggered from, but I don’t want to send anywhere else, so I can just show you all on a single page. Now, again, you can obviously ask the model to define this but given that it’s an email. You would probably want to use your own email to test it out, or the email that you want to send the newsletter to. And given all of this is done, we are pretty much good to go. I’ll just do this and then if you can see this like, you know, ignore this.
This is just, kind of a warning that says because you have changed so much stuff, the responses need to be reconfigured and we have all of this, but there’s one thing still missing, which I’ll show you in a second. Let’s save and let me show you. How does this. Look like. Okay, click on open chart again.
Let’s reset this. And I’m just going to write US history this time rather than Indian history. It’s going to process everything, but if you see the response I’m hoping is just not going to, and as you can see, it has sent an email automatically, even without writing a prompt. Right. And that’s interesting ’cause AI tool would’ve seen that this is the input and I’ve, I have a tool, I’m just going to send the template.
I’m going to send the email myself and that’s crazy, right? I did not define it. I should have technically gone and input there, but that’s pretty cool.
And the reason behind that is very simply because we have a small newsletter to send to the user AI agents are pretty smart because the LM models that we are using are pretty smart. They understand that if I have access to a tool and the user is asking me to send a newsletter, they’re going to use the email to send the newsletter.
Let me quickly show you the email that the agent has sent. Now, as you can see, this is the actual email that I got right now. Obviously, this email looks horrible.
Not formatted well and everything else, it just does not look well. But what is the problem there, right?
And that’s where you have to understand that every tool has a different configuration. the way that we are using. LM agents. you see this is the body of the email, and we have the email type at HTM L, but our agent is actually not responding in html, right? It’s just responding in a language for markdown.
So markdown is a language used to define content like this. So if I come here, and if you see this also uses markdown, if I just remove a hashtag, it becomes this big and heading, and if I had a hashtag, it becomes a smaller one. So markdown is used to format content in the simplest way possible using Simple, options.
Now again, you can learn a lot more about Mark, but the problem here is it’s not responding to htm. So what I’m going, come here and say, and this way you have to make sure that the prompts are better, which respond based on the user input.
Create a small newsletter to send to the user and strictly create the newsletter in an HTMI format, which is beautiful. Right now, this is done, and I’ll say a reply with the HTMR only, or now once I’ve written this, I’m just going to come back here and test it again. Again, you are going to have issues.
Don’t expect your agents to be perfect in one shot. they’re not going to be.
So come back here. We are going to try US history again Press enter and give it a couple of seconds and let it run its course. it should be able to respond in html this is the mistake that I would’ve made. I knew this now because if I have asked this strictly respond in html, it’s going to respond to me, right? I did not define it that, you know, reply with the H TM L only for the email tool.
Even that is done. It won’t work. So what I have to do is again, create a newsletter in H format, which is beautiful. And then use the email tool to send the newsletter in the same format. Right?
And let’s test it again, Literally just test this whole step again. So we’re gonna come back here and let’s see how this runs. It already has an input from us. But if it wants me to give an input, I’ll give it an input again, but keep testing, And the best thing is like you are facing all these errors because our prompt is not great. And once you start seeing the prompt to be better, you’ll actually start exploring and seeing that this can be really, really better.
This is the output that I got, this is so much better. this email newsletter looks a hundred times better than what we were seeing before and that’s the beauty of this, Now, the one thing that has happened here is I got two emails and the reason we had that is probably got triggered twice or something like that.
Obviously we can control that. You can say only run it once or something like that. But again, those are things that you just figure out as you go.
But this is literally your first AI agent that takes a topic, writes a newsletter, and sends the newsletter to anyone that you want across the world. Now, the one thing that I’ll recommend all of you to do is to click on this tool tab and see the number of tools that exist. There is a sheer amount of tools that you can use and can really, really utilize it for literally anything. I am like you have Airtable hair, you have phantom buster hair, you have LinkedIn tool hair. You have literally anything that you can think of, right?
And the best thing is in case you can’t find a tool, you can use the HVP request tool. Now again, but if you’re done and follow the tutorial along, tell Long. I will just say. Give yourself a huge pat on the back. You’ve created your first AI agent and I’m super proud that you followed through the whole tutorial.
If you’re here, I’m going to give you a really big reason to subscribe, I’m going to do more of these tutorials where I teach you step by step how to build agents so that you can go from this to this kind of agents and amazing templates and upskill yourself and also utilize that in your daily basis. Now, if you’re interested to learn more and engage with me directly, we have recently launched a community. I just got my first member two days back. So again, if you’re interested to join, go ahead and sign up. The link will be in the description, but other than that, please, please hit that subscribe and like button.
It really helps me out and check out the description. There are a ton of free resources that you can utilize Until then, I would love to see you in the next one. Bye-bye.
Here’s the year the stars fell. The year of many buffalo. The year of whooping cough. The year of measles. The year of an eclipse. The year the white soldiers attacked. A year of peace. A year of war. This … Continue reading →
Don’t forget students, sign-ups for after school activities start today in the cafeteria! Because nothing is more important for your college application than after school activities! Well, except for grades. And SAT scores. You know what, being Native American doesn’t … Continue reading →
Hello. A few weeks ago, I published a video on affiliate marketing. A number of questions have arisen when I am coaching my students just on affiliate marketing. If you are struggling to make affiliate marketing work, you are not alone. … Continue reading →
Because shoot we are going to Epcot today just saying and so uh you know just going to get some stuff done so that i can do some snuggling and then move into our day right so um anyway what is the … Continue reading →
Hello friends… Are you looking for cheap wholesale jewelry for your new business? India is the perfect location! Jewelry is symbolic in Indian culture. Artificial jewelry is produced at the domestic level in India. A buyer outside India can buy it … Continue reading →
Hey guys H from shout mil out and welcome to another video episode of blogging and today we’ll be talking about AdSense so this video is for the beginners who just started using AdSense or about to use AdSense and … Continue reading →
All right we got the Sima s107 H-E these start right around $50 make it a perfect gift for Christmas that won’t break the bank it has a dual rotor system to keep it stable and a small motor in the back … Continue reading →
Privacy & Cookies: This site uses cookies. By continuing to use this website, you agree to their use.
To find out more, including how to control cookies, see here:
Cookie Policy