Hey everyone! and just like you, I’ve been fascinated with the recent progress of artificial intelligence. Realizing that I needed to stay abreast with all the developments happening, I decided to embark on a personal journey of learning, thus was born! With this series, I will be learning about LLMs and share ideas, experiments, opinions, trends & learnings through my blog posts. You can follow along the journey on HackerNoon or my personal website . In today’s article, we’ll be looking to build a Semantic Kernel with the help of GPT-4. , I’m Nataraj 100 days of AI here here My goal with this post is to look at how startups at different stages leveraged LLMs and understand how they integrated AI into their products. The goal of this exercise is to come up with best practices that startups can learn from these examples. Example 1: Notion AI In a classic startup fashion the first version of Notion AI was coded in a hotel room during a company retreat in couple of days. Timeline – Private alpha in November 2022. We spent 10 weeks gathering vital user feedback before February 2023, when Notion AI became generally available to tens of millions of users Features launched: Completion of blog ideas to create first draft. Generate ideas to accomplish a task. Check grammar check, translation to different languages & Summarize a document. Help me write, to unblock writers and get them started. Example 2: Stripe Stripe took a drastic step and asked 100 of its employees to stop what they are doing and come up with ideas on how to use GPT4 to make stripe better. The result was a whole new set of features. Launched a way to summarize their customer business information, which was better than what people would write. Launched a chat bot to answer questions about its technical documentation, improves developer & partner productivity. Used GPT4 to find malicious accounts in their discord community. Example 3: Shopify Shopify was quick to adopt gen AI and launched a suite of AI features under the product name Shopify Magic. Shopify Magic is a collection of gen AI features which include: Text Generation – Speed up writing product descriptions, blog posts, email subject lines, email replies & headlines in Shopify stores. Basically anywhere a Shopify store admin has to write text they have added text generation capability. Media Generation – Product images play a big role in ecommerce. Editing image with out using any other apps is now added. Summarize App review – Instead of looking at 100’s of app reviews to find the right app to install you can look at summarized app reviews to find the right app. Example 4: CapCut If you have not heard of CapCut before, it is a video editing tool created by TikTok’s parent company Bytedance to help creators on TikTok. I use it to edit my podcast on a regular basis and I think its the most easiest & advanced editing tool out there for content creators. CapCut is also constantly updating its software and introducing new AI features. Here are some of them. Generate subtitles with one click. Generate videos with a text or image as a prompt and also give an ability to edit them once they are generated. The most latest feature they launched is CapCut will automatically generate shorts for you which you can further edit from a long form video. Although its not perfect it does save hours if you are an editor. Example 5: Yabble Yabble is a tool that delivers insights for business using which they can make important decisions. With lots of customer feedback data, using generative AI was an obvious choice for Yabble. They added the following new updates. Tool that analyses customer comments and categorizes them by sentiment and topics. Used GPT-3, to translate data sets into meaningful themes saving manual work for Yabble team. Startups both small and big are at the forefront of accessing AI and solving real business problems. If you are a product developer at a tech company or a startup here are some takeaways from these examples. Think of Gen AI as adding a new intelligence layer to your product. Current Gen AI models are really good at manipulating text. Text summarizations, text categorization, extracting sentiment from a given text are easy but high ROI use cases. Anywhere there is text in your product you can use gen AI to save time for your users. That’s it for Day 15 of 100 Days of AI. I write a newsletter called Above Average where I talk about the second order insights behind everything that is happening in big tech. If you are in tech and don’t want to be average, . subscribe to it Follow me on , or for latest updates on 100 days of AI. If you are in tech you might be interested in joining my community of tech professionals . Twitter LinkedIn HackerNoon here
