Recursive prompt engineering: how Gemini 3.0 Pro refined and executed its stock-picking playbook
We made Gemini 3.0 pro re-engineer its own deep research workflow using results from the last run.
Topic
Gemini 3 Pro
A collection of 4 issues
The Alpha-Divergence Protocol: We let Gemini-3 Pro design an autonomous stock research workflow
How we moved beyond basic prompts to build a forensic AI workflow that exploits the gap between headlines and reality, and the single high-conviction trade it uncovered.
We reran our most successful investment methodology using Gemini 3 Pro.
In 2023 we used GPT-4 to design a “most investable” hypothetical stock and found a real-world match that returned 117% vs 15.9% for the S&P 500. Here we rerun that process with Gemini 3 Pro and share the new thesis it surfaces.
OpenAI vs Google: One methodology, two flagship AI models, and their best stock picks
We used GPT-5.1 and Gemini-3 Pro to run an autonomous Deep Value research workflow on U.S. equities.