<!DOCTYPE html>
<html>
<head>
<style>.ck-link { text-decoration: underline; }</style>
<style>.ck-link { text-decoration: underline; }</style>
<style>@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; } }</style>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body style="margin:0;padding:0;-webkit-font-smoothing:antialiased;-ms-text-size-adjust:100%;-webkit-text-size-adjust:100%">
<div id="preview-text">
<span style="display: none; max-height: 0; overflow: hidden;">
Cohort enrollment closes TOMORROW Dec 5th
</span>
<span style="display: none; max-height: 0; overflow: hidden;">
͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
</span>
</div>
<div class="email" style="margin-left:18px;margin-right:18px">
<table cellpadding="0" cellspacing="0" style="border-collapse:separate;mso-table-lspace:0pt;mso-table-rspace:0pt;width:100%;margin:0 auto"><tbody><tr><td style="vertical-align:top">
<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">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”?</p>
<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">Based on my research and experience, here are the 5 core techniques you need to know:</p>
<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"><strong>1. Evals</strong> Throwing test cases at your system to see what it does is the most powerful way to scale any AI system. It’s especially useful for tool calls and retrieval, which are hard to evaluate but crucial to get right.</p>
<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"><strong>2. Tool calling at scale</strong> Models have limits. They can only handle so many tools, especially when those tools are complex. You need to know how to work within the constraints.</p>
<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"><strong>3. Converting unstructured data to structured data</strong> What are memories if not structured information pulled from unstructured conversations? If you want a system that learns, you need to know how to extract data.</p>
<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"><strong>4. Layered memory types</strong> Semantic memory. Episodic memory. Working memory. Recreating human-like memory in a system isn’t easy. You need to layer different techniques together to build something that actually works.</p>
<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"><strong>5. AI UX</strong> Designing a smart user experience — not just for you but for the model — takes a ton of pressure off the LLM itself. Disallow certain tool calls through the interface. Put the LLM in different modes. Tie the user closer to the process with human-in-the-loop patterns.</p>
<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">By the end of the cohort, you’ll understand the difference between ‘retrieval’ and ‘agentic retrieval’, ‘fixed’ and ‘structural’ chunking, semantic and episodic and working memory. You’ll have evaluated an agent’s outputs end-to-end, built a HITL (human-in-the-loop) system, and implemented a retrieval algorithm from the ground up.</p>
<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"><strong>Doors close tomorrow.</strong></p>
<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">The course includes the AI SDK v5 Crash Course, included free.</p>
<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"><a href="https://click.convertkit-mail2.com/v8upv7lqddirhv84gvphghv3e98lls9hrrdde/08hwhgu2zqe5deil/aHR0cHM6Ly93d3cuYWloZXJvLmRldi9jb2hvcnRzL2J1aWxkLXlvdXItb3duLWFpLXBlcnNvbmFsLWFzc2lzdGFudC1pbi10eXBlc2NyaXB0" target="_blank" class="ck-link" rel="noopener noreferrer" style="color:#0875c1" url-id="1811714319"><strong>ENROLL NOW</strong></a></p>
<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">-Matt</p>
</td></tr></tbody></table>
<div class="email-footer"><table cellpadding="0" cellspacing="0" style="border-collapse:separate;mso-table-lspace:0pt;mso-table-rspace:0pt;width:100%;margin:0 auto"><tbody><tr><td style="vertical-align:top">
<div><div class="email-footer" style="color:#4b4b4b">
<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;"><a href="https://click.convertkit-mail2.com/v8upv7lqddirhv84gvphghv3e98lls9hrrdde/n2h4prp8fquvreqp39c6/aHR0cHM6Ly93d3cudG90YWx0eXBlc2NyaXB0LmNvbS91bnN1YnNjcmliZWQ_c2VxdWVuY2U9YWlfaGVybw==" trigger-id="5153768" style="color:#0875c1" url-id="1811714322">Unsubscribe from AI Hero Emails</a>. You can also <a href="https://unsubscribe.convertkit-mail2.com/v8upv7lqddirhv84gvphghv3e98lls9hrrdde" style="color:#0875c1"><span style="font-size:12px">unsubscribe</span></a><span style="font-size:12px"> from all emails at any time.</span></p>
<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;"><span style="font-size:10px">12333 Sowden Rd, Ste. B, PMB #97429, Houston, TX 77080</span></p>
</div></div>
<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"></p>
</td></tr></tbody></table></div>
</div>
<!-- -->
<img src="https://open.convertkit-mail2.com/v8upv7lqddirhv84gvphghv3e98lls9hrrdde" alt="" style="border:0 none;display:block;height:auto;line-height:100%;outline:none;-webkit-text-decoration:none;text-decoration:none;max-width:100%">
</body>
</html>