Email: 5 core techniques you’ll learn building your AI assistant

Subject:
5 core techniques you’ll learn building your AI assistant
Received:
11/14/2025, 3:54:49 PM
From:
"Matt Pocock (AI Hero)" <matt@aihero.dev>
To:
porch.hat.81@rss.andrealin.it
&lt;!DOCTYPE html&gt;
&lt;html&gt;
&lt;head&gt;
&lt;style&gt;.ck-link { text-decoration: underline; }&lt;/style&gt;
&lt;style&gt;.ck-link { text-decoration: underline; }&lt;/style&gt;
&lt;style&gt;@media only screen { .email * { word-break: break-word; } }
@media screen and (max-width: 384px) { .mail-message-content { width: 414px !important; } }
@media only screen { .email * { word-break: break-word; } }
@media screen and (max-width: 384px) { .mail-message-content { width: 414px !important; } }
@media only screen and (max-width:600px) { .ck-mobile-font-size { font-size:50px !important; }  }
@media only screen and (max-width:600px) { .ck-mobile-font-size { font-size:50px !important; }  }
@media only screen and (max-width:600px) { .ck-mobile-font-size { font-size:50px !important; }  }&lt;/style&gt;
&lt;meta http-equiv="Content-Type" content="text/html; charset=UTF-8"&gt;
&lt;/head&gt;
&lt;body style="margin:0;padding:0;-webkit-font-smoothing:antialiased;-ms-text-size-adjust:100%;-webkit-text-size-adjust:100%"&gt;
&lt;div class="email" style="margin-left:18px;margin-right:18px"&gt;
&lt;!--[if mso]&gt;&lt;style&gt;.button-table { padding: 12px 0 }&lt;/style&gt;&lt;![endif]--&gt;&lt;table cellpadding="0" cellspacing="0" style="border-collapse:separate;mso-table-lspace:0pt;mso-table-rspace:0pt;width:100%;margin:0 auto"&gt;&lt;tbody&gt;&lt;tr&gt;&lt;td style="vertical-align:top"&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;In my last few emails, we've covered what AI assistants can do for you.&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Hopefully, you've seen how a tool like this can turn your daily work into repeatable tasks. &lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;And you can start to see how plugging them into your own data — especially emails, notes and docs — makes them incredibly powerful.&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;So what do &lt;strong&gt;you&lt;/strong&gt; actually &lt;strong&gt;need&lt;/strong&gt; to learn to build one of your own?&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Where should you spend your time? Which techniques are battle-tested? Which approaches will stand the test of time (vs what can you ignore from the weekly discourse over whether "RAG is dead" or "agents vs workflows" on Twitter?&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;&lt;strong&gt;Based on my research and experience, here are the 5 core techniques you NEED to know:&lt;/strong&gt;&lt;/p&gt;
&lt;h3 class="" style="font-weight:bold;font-style:normal;font-size:1em;margin:0;font-size:1.17em;margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#000000;line-height:1.5"&gt;&lt;strong&gt;1. Evals&lt;/strong&gt;&lt;/h3&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Throwing test cases at your system to see what it does is the most powerful way to scale any AI system.&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;It’s especially useful for tool calls and retrieval, which are hard to evaluate but &lt;em&gt;crucial&lt;/em&gt; to get right.&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;It's probably overkill for personal software. But if you're ever putting AI in production (even if it’s just for yourself), you &lt;strong&gt;need&lt;/strong&gt; to know how to run evals. &lt;/p&gt;
&lt;h3 class="" style="font-weight:bold;font-style:normal;font-size:1em;margin:0;font-size:1.17em;margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#000000;line-height:1.5"&gt;&lt;strong&gt;2. Tool calling at scale&lt;/strong&gt;&lt;/h3&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Your assistant needs to do lots of things. &lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;That means lots of tools - MCP servers, programmatic APIs, whatever.&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;But here's the thing: models have limits. They can only handle so many tools, especially when those tools are complex or have polymorphic inputs. Fill up your context window too quickly, or with the wrong (or extra) data, and you’re gonna have a bad time. &lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;You need to know how to work within the constraints of the tools, and how to adjust for different real world scenarios.&lt;/p&gt;
&lt;h3 class="" style="font-weight:bold;font-style:normal;font-size:1em;margin:0;font-size:1.17em;margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#000000;line-height:1.5"&gt;&lt;strong&gt;3. Converting Unstructured data to Structured data&lt;/strong&gt;&lt;/h3&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;This element is &lt;strong&gt;key&lt;/strong&gt; for &lt;a href="https://click.convertkit-mail2.com/xmu6xnrw77s6hp3wg7kc5h2qd6dllcnhdd66q/48hvh7um6exvpmux/aHR0cHM6Ly93d3cuYWloZXJvLmRldi93aGF0LWFyZS1sbG1zLXVzZWQtZm9y" target="_blank" class="ck-link" rel="noopener noreferrer" style="color:#0875c1" url-id="1805477817"&gt;tons of AI use cases&lt;/a&gt;, but especially for ones that rely on memory.&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Because what are memories if not structured information pulled from unstructured conversations?&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;If you want a system that learns, you&lt;strong&gt; need&lt;/strong&gt; to know how to extract data.&lt;/p&gt;
&lt;h3 class="" style="font-weight:bold;font-style:normal;font-size:1em;margin:0;font-size:1.17em;margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#000000;line-height:1.5"&gt;&lt;strong&gt;4. Layered memory types&lt;/strong&gt;&lt;/h3&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;I recently got super-inspired by &lt;a href="https://click.convertkit-mail2.com/xmu6xnrw77s6hp3wg7kc5h2qd6dllcnhdd66q/wnh2h6uqxp0nkxi7/aHR0cHM6Ly93d3cueW91dHViZS5jb20vd2F0Y2g_dj1WS1BuZ3lPMGlLZw==" target="_blank" class="ck-link" rel="noopener noreferrer" style="color:#0875c1" url-id="1805477818"&gt;this video&lt;/a&gt;. It’s based on a paper that tries to recreate human-style memory into LLM systems. Semantic memory. Episodic memory. Working memory.&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;So, I decided to integrate human-like memory into my systems - and it paid off beautifully.&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;But recreating human memory in a system isn't easy. You need to layer different techniques together to build something that actually works.&lt;/p&gt;
&lt;h3 class="" style="font-weight:bold;font-style:normal;font-size:1em;margin:0;font-size:1.17em;margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#000000;line-height:1.5"&gt;&lt;strong&gt;5. AI UX&lt;/strong&gt;&lt;/h3&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Designing a smart user experience — not just for you but &lt;em&gt;for the model&lt;/em&gt; — takes a ton of pressure off the LLM itself. &lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Putting more control in your / the user’s hands means a better-designed context for the LLM: &lt;/p&gt;
&lt;ul class="unordered_list" style="margin:1em 0;margin-left:1em;padding:0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5;list-style-position:outside !important"&gt;
&lt;li class="list_item" style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;&lt;span&gt;You can disallow certain tool calls through the interface. &lt;/span&gt;&lt;/li&gt;
&lt;li class="list_item" style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;&lt;span&gt;Put the LLM in different modes based on user input. &lt;/span&gt;&lt;/li&gt;
&lt;li class="list_item" style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;&lt;span&gt;Tie the user closer to the process with human-in-the-loop patterns.&lt;/span&gt;&lt;/li&gt;
&lt;/ul&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Now, you could absolutely go out and learn all this on your own. Stitch it together from hundreds of blog posts, YouTube videos, and GitHub repos.&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Or you could learn it all in one place. In a single project. With a community of developers building alongside you!&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;We cover all of this, and more in &lt;a href="https://click.convertkit-mail2.com/xmu6xnrw77s6hp3wg7kc5h2qd6dllcnhdd66q/reh8h9umwr643xf2/aHR0cHM6Ly93d3cuYWloZXJvLmRldi9jb2hvcnRzL2J1aWxkLXlvdXItb3duLWFpLXBlcnNvbmFsLWFzc2lzdGFudC1pbi10eXBlc2NyaXB0" target="_blank" class="ck-link" rel="noopener noreferrer" style="color:#0875c1" url-id="1805477819"&gt;&lt;strong&gt;Build Your Own AI Personal Assistant in TypeScript&lt;/strong&gt;&lt;/a&gt;&lt;strong&gt;. &lt;/strong&gt;We’ll be building with the latest and greatest AI SDK, also all in Typescript, so you know it’s going to be awesome. &lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;If you’re thinking about building &lt;em&gt;anything&lt;/em&gt; with an LLM integration in 2026, and haven’t checked out the course page yet, make sure you do before &lt;strong&gt; Monday Nov 24 at 11:59 PM Pacific when the price goes up by 40%!&lt;/strong&gt;&lt;/p&gt;
&lt;!--[if !mso]&gt;--&gt;&lt;table width="100%" style="border-collapse:separate;mso-table-lspace:0pt;mso-table-rspace:0pt"&gt;&lt;tbody&gt;&lt;tr&gt;&lt;td align="center" style="vertical-align:top"&gt;&lt;a class="email-button" href="https://click.convertkit-mail2.com/xmu6xnrw77s6hp3wg7kc5h2qd6dllcnhdd66q/reh8h9umwr643xf2/aHR0cHM6Ly93d3cuYWloZXJvLmRldi9jb2hvcnRzL2J1aWxkLXlvdXItb3duLWFpLXBlcnNvbmFsLWFzc2lzdGFudC1pbi10eXBlc2NyaXB0" target="_blank" rel="noopener noreferrer" style="color:#0875c1;border:0 none;margin-bottom:0.5em;font-size:16px;line-height:1.5;background-color:#0875c1;color:#ffffff;border-radius:4px;border-color:#0875c1;background-color:#0875c1;box-sizing:border-box;border-style:solid;color:#ffffff;display:inline-block;width:auto;text-align:center;text-decoration:none;padding:18px 32px;margin-top:48px;margin-bottom:48px;font-size:24px;border-radius:4px 4px 4px 4px" url-id="1805477819"&gt;&lt;strong&gt;ENROLL NOW&lt;/strong&gt;&lt;/a&gt;&lt;/td&gt;&lt;/tr&gt;&lt;/tbody&gt;&lt;/table&gt;
&lt;!--&lt;![endif]--&gt;&lt;!--[if mso]&gt;&lt;table class="button-table" width="100%" border="0" cellSpacing="0" cellPadding="0" style="margin-top:48px;margin-bottom:48px"&gt;&lt;tr&gt;&lt;td align="center"&gt;&lt;table border="0" cellSpacing="0" cellPadding="0" width="auto"&gt;&lt;tr&gt;&lt;td align="center" bgcolor="#0875c1" style="background-color:#0875c1;overflow:hidden;padding:18px 32px"&gt;&lt;a class="email-button" href="https://www.aihero.dev/cohorts/build-your-own-ai-personal-assistant-in-typescript" target="_blank" rel="noopener noreferrer" style="background-color:inherit;display:inline-block;text-decoration:none;margin:0;color:#ffffff;font-size:24px" data-ck-element="button"&gt;&lt;strong&gt;ENROLL NOW&lt;/strong&gt;&lt;/a&gt;&lt;/td&gt;&lt;/tr&gt;&lt;/table&gt;&lt;/td&gt;&lt;/tr&gt;&lt;/table&gt;&lt;![endif]--&gt;&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Next week, I’ll be back to share more behind the scenes…plus some of the biggest dangers and pitfalls I’ve found while working with LLMs and how I avoided them while building my assistant. &lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;-Matt&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;&lt;/p&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;&lt;br&gt;&lt;/p&gt;
&lt;/td&gt;&lt;/tr&gt;&lt;/tbody&gt;&lt;/table&gt;
&lt;div class="email-footer"&gt;&lt;table cellpadding="0" cellspacing="0" style="border-collapse:separate;mso-table-lspace:0pt;mso-table-rspace:0pt;width:100%;margin:0 auto"&gt;&lt;tbody&gt;&lt;tr&gt;&lt;td style="vertical-align:top"&gt;
&lt;div&gt;&lt;div class="email-footer" style="color:#4b4b4b"&gt;
  &lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5;color:#4b4b4b; margin:1em 0;font-family:Arial,-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;;font-size:12px;line-height:1.5;display:block;margin:13px 0;"&gt;&lt;a href="https://click.convertkit-mail2.com/xmu6xnrw77s6hp3wg7kc5h2qd6dllcnhdd66q/g3h72p2wcwum65qrlxtr/aHR0cHM6Ly93d3cudG90YWx0eXBlc2NyaXB0LmNvbS91bnN1YnNjcmliZWQ_c2VxdWVuY2U9YWlfaGVybw==" trigger-id="5153768" style="color:#0875c1" url-id="1805477820"&gt;Unsubscribe from AI Hero Emails&lt;/a&gt;. You can also &lt;a href="https://unsubscribe.convertkit-mail2.com/xmu6xnrw77s6hp3wg7kc5h2qd6dllcnhdd66q" style="color:#0875c1"&gt;&lt;span style="font-size:12px"&gt;unsubscribe&lt;/span&gt;&lt;/a&gt;&lt;span style="font-size:12px"&gt; from all emails at any time.&lt;/span&gt;&lt;/p&gt;
  &lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5;color:#4b4b4b; margin:1em 0;font-family:Arial,-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;;line-height:1.5;display:block;margin:13px 0;"&gt;&lt;span style="font-size:10px"&gt;12333 Sowden Rd, Ste. B, PMB #97429, Houston, TX 77080&lt;/span&gt;&lt;/p&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;&lt;/p&gt;
&lt;/td&gt;&lt;/tr&gt;&lt;/tbody&gt;&lt;/table&gt;&lt;/div&gt;
&lt;/div&gt;
&lt;!-- --&gt;
&lt;img src="https://open.convertkit-mail2.com/xmu6xnrw77s6hp3wg7kc5h2qd6dllcnhdd66q" alt="" style="border:0 none;display:block;height:auto;line-height:100%;outline:none;-webkit-text-decoration:none;text-decoration:none;max-width:100%"&gt;
&lt;/body&gt;
&lt;/html&gt;
Email Content
