Within the evolving landscape of artificial intelligence (AI), large language models (LLMs) have the potential to enhance the efficiency, breadth, and validity of the collection, processing, and analysis of text as data in evaluation practice. However, LLMs do not always generate aligned,...

Process tracing (PT) involves a detailed analysis of the processes that link interventions to outcomes. PT is particularly useful for evaluating interventions that are difficult to quantify, such as knowledge work or institution building. It involves creating a detailed causal theory, tracking...