Urgent.News

What's breaking now, across thousands of outlets.

AI

How to Integrate SEC Filings into Your AI Agent

Day 24 of 30 Days of Search. TL;DR To integrate SEC filings into your AI agent, give it a search tool that targets Valyu's valyu/valyu-sec-filings dataset, checks the returned filing identity, and passes source URLs alongside the retrieved text. Let the model summarize the evidence, but keep the original passages so someone can check its answer. We will build a small TypeScript agent that…

To integrate SEC filings into an AI agent, you need to follow a specific workflow. First, determine the appropriate SEC filing form based on the question you want to answer. For example, if you want to know about supply-chain risks, you would look for a 10-K annual report. Next, you need to know the details of the filing, such as the form type, company name, reporting period, and filing date.

In this case, Apple's fiscal 2024 10-K filing covers the year ended September 28, 2024 and was filed on November 1, 2024. The accession number for this filing is 0000320193-24-000123.

Once you have the necessary information, you can use the Valyu search tool to retrieve relevant SEC filings. Valyu returns the content along with source URLs, which you can then use to create a short research brief. This brief should include the retrieved passages and their corresponding source links. This way, a person reviewing the output can verify the information and make further investigations if needed.

The agent should not attempt to assess the current risk exposure or provide investment recommendations. It should only summarize the evidence found in the SEC filings.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

OpenAI Moves Frontier AI Model Training Offline for Enhanced Security

Originally published on PkLavc . Confirmed facts OpenAI announced on 2026-10-23 that it is moving frontier model training to offline, contained environments without direct internet access.

  • OpenAI moves frontier AI model training offline for enhanced security.
  • Offline environments isolate models from the internet to reduce attack surface.
  • Transition involves pre-fetching, caching, and strict access controls for data.

SlothBot: The Fully Automated AI Farmer (Powered by Open-Weight LLMs & Web Edition)

What I Built Meet SlothBot, an autonomous, local AI agent designed for the ultimate champion of leisure. Inspired by the spirit of the sloth and built specifically for The Farmer Was Replaced Web…

  • SlothBot automates all farming tasks in The Farmer Was Replaced
  • Powered by open-weight LLMs and Ollama for offline use
  • Saves players 14 hours of coding per week

More from Saturday 24 October →