Pebble Finance – Personalize Your Investments Today
Hello HN, We are Pebble Finance! Our newly launched product offers a custom indexing solution, empowering investors to personalize their investment portfolios. # The product What our product is now: We are creating a platform for users to use natural language to search for their interests and personalize their portfolio. Search is a combination of using OpenAI LLM models with Langchain, OpenSearch index, and some traditional NLP techniques. Search is divided into several tools which are selected based on the user’s input query. Based on the complexity of the input query, a single tool or a…
In plain words
Pebble Finance is a platform that lets investors build custom portfolios using natural language search. Users describe their interests and preferences, and the system uses AI language models and search technology to identify relevant companies and construct personalized investment indexes. The platform processes complex queries to match investors with portfolio options aligned to their specific interests and themes.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hello HN, We are Pebble Finance! Our newly launched product offers a custom indexing solution, empowering investors to personalize their investment portfolios. # The product What our product is now: We are creating a platform for users to use natural language to search for their interests and personalize their portfolio. Search is a combination of using OpenAI LLM models with Langchain, OpenSearch index, and some traditional NLP techniques. Search is divided into several tools which are selected based on the user’s input query. Based on the complexity of the input query, a single tool or a combination of tools can be used to return a list of companies for the user’s portfolio. Also based on the complexity of query search times can vary from less than a second to up to 15 seconds. List of tools - Themes - General themes or concepts such as type of company - Index/ETFs - Search for common ETFs such as S&P 500, Russell1000, and Russell3000 Location - Currently we can search for US states and countries (we are going to be adding in US cities soon as well) - Fundamental Metrics - Filter companies based on fundamental metrics such as market cap, revenue, and pe ratio - Supplier Data - Identify companies based on their supplier relationships What we would like to add: We are looking to add more tools to add more functionality for users. Some tools we are looking to add are based around news integration, historic stock price, and expanding our sources of data We are also trying to improve search speed while keeping quality of results consistent so we are looking at new ways to parse queries such as with fine tuning transformer models and looking at more traditional NLP techniques. Challenges we have come across We are seeing issues with trading off between speed and quality of search results. Many of the queries can take up to 15 seconds based on the complexity. Also saw issues where LLMs are producing hallucinations which led to incorrect results. We have mitigated this issue by using OpenAI’s davinci-003 model versus gpt3.5-turbo, but this also increases overall cost. Some Example Queries - I want to invest in eco friendly companies - Faang without the n - Electric cars without elon musk - Californian companies - Aapl - Top marketcap companies - ev companies with marketcap above 10 billion - s&p without apple # Feedback Please try out our search capabilities on pebble.finance/themes and check the results! We would really love honest feedback on search results, suggestions on improving results/speed, future tools, and/or general thoughts! Thanks for reading! The Pebble Finance Team
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, July 2023
the whole month →
- WL
Hey everyone, I here is a small open-source project I've been working on lately. I'd love to hear your thoughts and improvement ideas :) GitHub: [github.com/Vincenius/workout-lol](https://github.com/Vincenius/workout-lol)
Dev tools · 2023 · workout.lol
- HN
I saw this [0] pretty cool thread by user revskill, and wanted a quicker way to search through it, but also to keep them all in one place so I can read them at my leisure whenever I get time. Right now is like 60 lines of Ruby using Nokogiri, but I will certainly look into it further down the line and improve the list. There's a cronjob checking the thread every 12 hours but I will eventually shut that down and it will become static after that. There are some really awesome blogs in there. I really recommend going through the list, it made my day. [0] "Could you share your personal blog…
Life & fun · 2023 · dm.hn
A safe space for your thoughts, private, local, p2p & open
Commerce · 2023 · anytype.io
