Literature review and evidence synthesis
A use case in Pharmaceuticals and life sciences, seen as a chain of named AI tasks.
What it is. Literature review and evidence synthesis is an AI use case in Pharmaceuticals and life sciences. Its input is text, and underneath it is a short chain of named tasks: it finds the most relevant material, then summarises it. That makes it grounded, or RAG: it looks things up first, then answers from what it found, so it stays tied to real text.
How you tell it is working. Each task is measured, and fails, differently. The weakest step sets the ceiling for the whole chain, so concentrate testing there.
- Retrieve / search (finding & recommending): whether the right item shows up near the top of the results. Watch: if the right item is not retrieved, everything after it is wrong.
- Summarise (language): whether it keeps the key points and a person finds it faithful. Watch: omission and invented facts.
How much it decides. As drawn, it sits at the grounded level: looks things up first, then answers; you check. The same use case can be built with more or less autonomy, and more autonomy means more reach and more to check.
Judging the materiality. This page does not assign a risk tier. How material it is depends on your deployment: who it affects, whether a person genuinely re-decides or only approves, whether the action can be reversed, and your regulatory and fairness exposure. Rate it on impact, complexity and reliance as the AIRG expects, and let the controls follow. See use-case risk and materiality.
Related: the interactive AI use-case explorer, AI use cases by industry, and the AI risks taxonomy.