Science, Technology and Innovation policy making is being revolutionized using text data analytics. The existence of repositories of scientific knowledge, together with the advances in text analytics, are increasingly offering the opportunity to research funders to improve their policy making across the policy cycle. The complexity of the innovation system leads to a granularity challenge. Sophisticated policy questions can only be answered using refined disciplinary, stakeholder and territorial breakdowns, which in turn call for advanced mappings, bottom-up machine-guided approaches and multifaceted visualizations. This policy brief shows the first results of the IntelComp platform: the use cases of Energy, as a key element for mitigating climate change, and of science and technology in Artificial Intelligence. They indicate that IntelComp has successfully produced topic models and automatic classifiers to address the granularity challenge.