I order lots of things online all the time. I always have packages coming. I also return a decent percentage of the orders. It’s pretty annoying to keep track of everything. What was ordered, what I received, what I’m thinking about returning, and what I decided to return, but haven’t taken care of yet.<p>For a long time, I’ve had this idea to scratch this itch and build something that can solve this. The primary blocker was that it’s not practical to manually add everything to such a system. There is nothing like Plaid for merchants, where I can access order information. Building out native integrations for each merchant is too much work to do for an unproven idea. Even scraping the data from emails is a lot of work. Each merchant has its own email format, and could even have multiple email formats (A/B testing etc.).<p>What changed now are LLMs. Now, it’s easy to extract structured data from unstructured HTML. When an order comes in, I send it to the OpenAI API with an expected data schema, and it’s able to extract the information.<p>I built [Orderl.ing](<a href="https://orderl.ing" rel="nofollow">https://orderl.ing</a>) to solve this problem. You can think of it as a CRM for your orders.<p>What is different about Orderling over other products is that the focus is less about tracking the order coming to your door. It’s about tracking the order after. When you confirm that you actually got the item, you mark it as received. You can then decide if you want to keep it, unsure about returning, or want to return it. You can then easily come back to see orders that you still need to decide about, or that need to be packaged up and shipped. You can also quickly see a list of orders that are close to the return-by date, so you can make the final decision, or actually return it.<p>There are still lots of features on the roadmap. I’d love to get feedback from users to see if anyone else finds it helpful, and to see if there are any other features that would be useful.