CEO Kevin Kawchak

ChemicalQDevice

San Diego, CA

March 23, 2025

kevink@chemicalqdevice.com

Every once in a while, a new artificial intelligence technology is released that significantly improves research utility and results. This ’deep research’ tool released by OpenAI in February 2025 is a Large Language Model (LLM) web agent that autonomously queries sites such as PubMed Central (PMC), and generates high quality summaries with verifiable citations. A February 2025 article by Haman M. et al. reported deep research advantages in "analyzing 37 sources-35 of which were found on the PubMed website" using the OpenAI o3 model. Here, ChatGPT 4.5 Deep research summaries regarding five pharmaceutical industry financial categories were found to be 100% in-context with PMC articles, and averaged 1,400 words in 10 minutes with minor issues. Also impressive was the processing of these summaries by the Claude 3.7 Sonnet Extended reasoning model to produce a structured 1,900 word 37 citation report containing detailed economic solutions, which were supported by 6 paragraphs of key insights collaborating multiple author quotations in approx. one minute. In addition, the Claude model produced eleven professional images based on USD or ROI trends, anomalies, and forecasts in three Python scripts. The Claude model possessed an output length that scaled by 3.2x for the report and 6x for code generations vs. the manufacturer’s previous model, was 100% in-context with source data, and included interpretable reasoning summaries. The outputs from ChatGPT 4.5 Deep research served as inputs to 3.7 Sonnet Extended in mitigating model bias amplification that can occur when using results within a single software manufacturer. For transparency, comprehensive generation traceability analyses were conducted for the five summaries, the financial solutions report, and the eleven Python diagrams.