tech
March 27, 2026
Build Your Own Bloomberg Terminal With AI
A step-by-step guide to going from ChatGPT earnings previews to a custom investment dashboard—no engineering team required
.png)
TL;DR
- Earnings season is a time-intensive task for financial analysts that is well-suited for AI automation.
- Many investment teams abandon AI after initial disappointing experiences with unsophisticated tools.
- A four-level approach is presented to progressively build more advanced AI capabilities for financial analysis.
- Level one utilizes custom GPTs with detailed prompts to create earnings previews, but has limitations in handling multi-step workflows and output customization.
- Output from custom GPTs can have formatting issues and may require multiple steps to achieve desired results.
- The 8,000-character limit in ChatGPT projects restricts the complexity of combined prompts and workflows.
Continue reading the original article