<p>Hey Product Hunt 👋<br></p><p>I’m <strong>Arunabh</strong>, Co-Founder & CEO of <strong>Leni</strong>.</p><p></p><p><strong>Three years ago, we started with a simple observation:</strong></p><p></p><p>The smartest people in investing were spending an absurd amount of time moving data between systems, fixing spreadsheets, validating reports, and checking the outputs of tools that were supposed to save them time.</p><p></p><p>Everyone was talking about AI.</p><p></p><p>But when real money was involved, most professionals still didn't trust it.</p><p></p><p>And honestly, they were right.</p><p></p><p><strong>In high-stakes work, "mostly correct" isn't good enough.</strong></p><p></p><p>A wrong number, a missed assumption, or a hallucinated fact can cost millions.</p><p></p><p>So instead of building another chatbot, we spent years working alongside sophisticated investors, operators, lenders, and asset managers to understand what trustworthy AI actually looks like.</p><p></p><p>Since then, we've supported <strong>more than $80B in assets</strong>, processed <strong>over 100 million rows of investment data every day</strong>, built proprietary verification systems, and tested relentlessly against real-world workflows.</p><p></p><p><strong>The result is Leni.</strong></p><p></p><p>THE most reliable and accurate AI infrastructure platform for investors and back office work that can analyze hundreds of files simultaneously, reason through complex tasks, validate its outputs, and deliver finished work instead of just generating responses.</p><p></p><p><strong>In independent testing, Leni now ranks among the top AI systems for spreadsheet analysis, reasoning, and resistance to hallucinations.</strong> That work also led to our selection as one of the few companies invited to Google's Gemini Forum, where we've had the opportunity to collaborate with the <strong>DeepMind</strong> team.</p><p></p><p>But what excites me most isn't a benchmark result.</p><p></p><p><strong>It's seeing professionals finally trust AI with the work that actually matters.</strong></p><p></p><p>Huge thank you to our team, customers, advisors, investors, and everyone who helped us get here.</p><p></p><p>We’re excited to finally put Leni and its API portal into the hands of the broader Product Hunt community and see what you build with it.</p><p></p><p>We'll be here all day answering questions, gathering feedback, and learning from the community.</p><p></p><p>My team and I are here all day. Ask us anything 🙌</p><p></p><p>P.S. 🎁 Exclusive for the Product Hunt community: Try <a href="https://Leni.co" target="_blank" rel="nofollow noopener noreferrer">Leni.co</a> directly on the platform or via APIs today with code PHLENI to get 90% off your 1st month's subscription on any plans, valid till the end of the day!</p>
<p>Hello Product Hunt, excited to be live today with Leni. I'm Gaurav, co-founder at Leni. <br><br>Leni is an accuracy-first AI platform for investment finance and real estate teams. It helps you go from messy documents & siloed systems to structured, verifiable answers with analysis you can actually trust.<br><br><br>AI tools optimize for fluent responses. Leni obsesses over accuracy. <br><br>• With verification layers that validate outputs instead of "guessing."<br>• Decision traces so you can see how an answer was formed and what it was grounded in<br>• A context graph + Unified Data Model (UDM) that keeps information consistent across documents, models, and entities<br>• A focus on retrieval + extraction (getting the right facts) before generation (writing the response)<br><br><br>If you work in investments, asset management, credit, capital markets, valuation, or any workflow where a single wrong number can derail a deal, Leni is for you.<br><br><br>Over the years, especially in the last 6 months, it's been rewarding to see skeptics become believers. Teams that started with us as an experiment now rely on Leni for mission-critical work. That trust came from obsessing over accuracy, building robust verification systems, and learning through real implementations.<br><br><strong>We'd love feedback from the Product Hunt community:</strong><br></p><ol><li><p>What workflow are you trying to make "AI-native" today?</p></li><li><p>Where do existing tools break down on trust/accuracy?</p></li></ol><p>Thanks to our customers, team, advisors, investors, and early supporters who believed in us before this became obvious.<br><br>We're here all day so fire away with questions 🙌<br><br>P.S. 🎁 Exclusive for the Product Hunt community: Try <a href="http://Leni.co" target="_blank" rel="nofollow noopener noreferrer">Leni.co</a> directly on the platform or via APIs today with code PHLENI to get 90% off your 1st month's subscription on any plans, valid till the end of the day!</p>
<p><a href="https://www.producthunt.com/@arunabh_dastidar" data-node-type="mention" data-mention-type="user" data-mention-id="arunabh_dastidar" target="_blank" rel="nofollow noopener noreferrer">@arunabh_dastidar</a> Congrats on the launch!! </p><p></p><p>Two things I'm curious about. The model-agnostic routing, how does Leni decide which LLM handles what? Is it task-based, like one model for number-crunching and another for writing memos, or something more dynamic? And does the user get any say in that or is it fully behind the scenes?</p><p></p><p>Also, as a founder myself, I'm curious how you got the first few institutional customers to actually trust AI with real money decisions. That's probably the hardest cold start problem in enterprise AI. Did you have to start with low-stakes work and earn your way up, or did one customer go all in early?</p>
How does your “decision trace” and private context graph work over time—what gets stored, how do you prevent bad assumptions from becoming institutional memory, and how do you handle changing definitions (e.g., NOI, occupancy, same-store) across teams?
