AI Engineer

Build Your Own Finance Agent Inside ChatGPT - Stefano Fabbri & Oliver Steffmann, OpenAI

Published 2026-11-07 · Duration 1:50:32

Summary

This workshop details building sophisticated financial agents and workflows using OpenAI's applied AI platform, focusing on the financial services sector (wealth and asset management). Speakers demonstrate how to merge financial data (from partners like LSEG and PitchBook), LLM intelligence, and structured workflows using ChatGPT Work and Codex. The core focus for builders is transitioning from bespoke API integrations to scalable, enterprise-grade solutions using Skills, Plugins, and Plugin Extensions, which streamline development and deployment within a controlled ecosystem.

Download summary

Key takeaways

  1. Platform Architecture for Enterprise AI 16:46

    The platform utilizes three main surfaces: ChatGPT (original), ChatGPT Work (for knowledge workers/agents), and Codex (for engineering tasks). The most powerful, scalable approach is using Plugins, which combine Skills (reusable prompts/templates) and MCPs (Model Connection Points) to integrate internal data and tools.

  2. Workflow Automation and Customization 23:45

    A wealth advisor's workflow example demonstrates how the system can automate complex tasks, such as analyzing portfolio changes, generating P&L, and preparing client decks, accelerating the end-user process.

  3. Advanced Model Capabilities and Optimization 20:20

    The platform supports advanced features like Compaction mode (for long-running tasks and large context windows) and 'Goal Mode' in Codex, allowing agents to iteratively optimize performance toward a specified numerical target, which is crucial for quantitative research.

  4. Enterprise Deployment and Control 25:00

    For builders, the key benefit is the ability to deploy customized plugins and extensions within the ChatGPT Work surface, avoiding the need to build entirely standalone applications. Enterprise control features include sandboxing and customizable policies (e.g., limiting which URLs a plugin can access).

More digests on Generative AI

Technical details

  • Core Components 1006s

    The system architecture is layered: **Skills** (reusable prompt templates/knowledge), **Plugins** (a heavier package containing skills, MCPs, and tools for enterprise integration), and **Plugin Extensions** (allowing customization of the UI surface itself).

  • Data Integration and Ontology 751s

    Financial data is integrated via built-in partnerships (LSEG, PitchBook, Crunchbase) and is pre-processed with a specialized data ontology layer. This ensures the model consumes data not just as raw rows, but with context (e.g., explaining what a 10K or 10Q filing contains).

  • Model Performance and Efficiency 1220s

    The platform recommends using models like Astra or 6.1 Soul, and utilizing 'Ultra mode' for speed. For cost optimization, the speaker advises that while powerful models are good for new research, repeatable tasks can leverage cheaper models (like Luna) combined with highly optimized Skills.

  • Security and Deployment 1600s

    Codex provides enterprise controls, including sandboxing and configurable policies (defined via TOML files). This allows administrators to strictly limit a plugin's access (e.g., restricting URLs or preventing access to sensitive project folders), balancing security needs with user convenience.

Mentioned resources

  • ChatGPT Work (Platform Surface)
  • Codex (Development Tool/Surface)
  • LSEG (Data Vendor)
  • PitchBook (Data Vendor)
  • Daloopa (Data Vendor)
  • Astra / 6.1 Soul (LLM Model)

Channel & topics

Watch on YouTube · Back to latest

This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.