Hey all! I want to share something different I’m building. It’s a bit outside what I normally do—more of a practical application—but I had a lot of fun building it, and I think I’m on track to create something consistent and useful (maybe even revenue-generating). What it isI’m building an insider-trading intelligence platform that alerts me to significant insider trades—think CEOs buying large amounts of their own company’s stock, or politicians loading up on positions that suggest they may know something we don’t. As a thank-you to this community, I’ll give anyone who’s interested exclusive free access once it’s ready. Stay tuned. What the app does today 🧠 Advanced AI AnalysisUses GPT-5 to analyze insider trading data and generate high-confidence trading signals (70–95% accuracy scores) with reasoning, entry points, stop losses, and profit targets. 🏛️ Congressional Trading IntelligenceAutomatically detects when politicians trade and analyzes their moves for potential informational edge. Think examples like high-profile NVDA options or senators trading ahead of policy announcements. 📊 Real-Time MonitoringTracks 30+ insider transactions daily from OpenInsider.com, applies an 8-filter validation system, and generates comprehensive reports in seconds. 🎯 Signal UpgradesWhen politicians and corporate insiders trade the same names, the system upgrades signal confidence and flags possible policy-driven opportunities. 📈 Performance TrackingMaintains leaderboards of top-performing political traders, tracks win rates, and compares party-level performance. Why this matters Politicians can legally trade while having access to non-public context via committees, policy work, and regulatory discussions. This platform levels the playing field by tracking their moves in real time and analyzing the intelligence behind them. Real exampleThe system flagged a ~$3M NVDA options buy by a House Financial Services Committee member just before AI-regulation hearings—the kind of edge institutions pay up for.

I don't have any question here but want to share, because it feels like a huge win for me but nobody in my life understands - the other day, I made two huge milestones. 1. After researching and learning about RAG methodologies and strategies for weeks, I finally got a RAG ingestion workflow working that seems like it's going to work for my use-case and yield really good, accurate results. I have a lot to add to it yet to further automate, but determining how to chunk it out and what tools to use, and actually understanding a bit of the "why" behind all of these choices, was a milestone for me. I haven't officially starting my testing yet but already it's accuracy is looking SO much better. (For the curious - I'm manually breaking up the chunks semantically, I'm using an LLM to enrich each chunk with metadata/tags/chunk summaries/example questions, and I switched to openai embeddings which apparently are better with semantic search). I also setup the metadata in a way that will make it easier to translate into a postgresql table if I decide I need hybrid search in the future to further increase accuracy, which learning about postgres in and of itself was a large endeavor. 2. I got one of my agent workflows setup with hybrid text/image RAG! I had to tag my RAG docs to look for the images and make the metadata flag it, then I had to set up a firebase storage, and I'm just so damn pleased that it all actually worked. When my chat test came back with the images along with the answer, I straight up giggled. For some people here, these might seem like pedestrian or super easy, afternoon type projects. For other people here, this might seem almost like another language still. I hope by sharing that I inspire someone else to keep going! I love reading posts like these myself (thanks for always posting @Didac Fernandez !) so I thought I'd try and share too.

I recently found the Lindy.ai agent build platform. The company claims SOCII and HIPAA compliance. Has anyone here explored Lindy? I’m wondering whether or not I should add another tool to my already overflowing toolkit! 😂

The Virtual Company Project: Finance Department The first block of the Virtual Company project will be the Finance Department. I've broken it down into four distinct functions to start, but there will be more—such as Financial Analyst and Payroll Specialist—in the future. Currently, I don't have enough data to simulate these additional roles. The four roles: - Victor (Controller):This workflow will receive bank transactions in the form of bank statements and transfer this information into the accounting books for future reconciliation with Accounts Payable (AP) and Accounts Receivable (AR). - Donna (Accountant #1):This workflow will process invoices dropped into a specific Google Drive folder as PDFs. The flow will be triggered, run OCR to extract all data into a structured JSON format, and then add the information into a simulated ERP using Google Sheets. - Mark (Accountant #2):Similar to the invoice process, but focused on expenses. I also aim to implement a more dynamic method for inputting expenses, such as taking pictures and sending them via email, WhatsApp, or Telegram to the workflow, which will process them and add them to the books. - Andrew (CFO):This AI agent will manage and extract all information related to financial data. It will be capable of pulling data from all books and responding to financial data requests made by the AI Orchestrator agent (CEO). This agent will interact with human users indirectly via the orchestrator. The workflows are currently at version 1. There are many improvements and additions that can be incorporated into the entire Virtual Company project for financial operations, but for now, I'm satisfied with the progress of this first block. This is just a concept, but with a few adjustments tailored to the specific software and frameworks each company uses, it can be easily adapted for real-world application—which is the ultimate goal of this project. Stay tuned for next chapter!

Hi everyone! Long post incoming - thanks for humoring me. I would love to hear what you all think about a project I have sitting on the shelf right now. Happy to go into more details, but the tldr version is that I have a relationship enhancement tool, primarily built for sales people/account managers/etc to have an easy tool to build out relationships with clients/potential clients/partners. Long story short, you login to your instance of FB via the tool dashboard- the dashboard pulls down all of your contacts - you decide which people you want to follow in more depth - you chose from 4 sentiments that you want to follow - the dashboard populates only those posts. If you decide, you can chose a photo, include a digital frame, then send an email. It was built, it works, I get good discussion around it. The issue is the FB login. Just in the course of time that we were building it, they moved the goalposts a lot. We can probably get around that, but I don't want to be the cause of anyone getting their account banned. So, I'm trying to pivot. At its core, it is a photo/text reading and classification tool. The AI is trained on sentiment analysis right now, but that can be changed. Some people think I need to try to keep the customer flow that we have now, because technically that is the unique part. It might be beneficial for a larger company who wants privacy since we have a secure environment on AWS. The landing page is still live and it gets into pretty good detail. Would love to hear your thoughts. https://milestonememos.com/