---
name: "cambridge-llm-screening-training-loop-method"
description: "Use when you need to Screen studies for a systematic review with a chat AI. Train a chat AI to screen abstracts against your review criteria"
---

# Train a chat AI to screen abstracts against your review criteria

Job: [Screen studies for a systematic review with a chat AI](https://aiagents.org/canai/cambridge-llm-screening-training-loop)

## Need

- ai agent

## Steps

1. Upload inclusion/exclusion criteria as a PDF.
2. The agent summarizes the criteria in its own words.
3. The researcher reviews and corrects the summary in a single pass.
4. The agent re-summarizes until accurate.
5. Upload a sample set of abstracts as a training set.
6. The agent classifies each abstract as include or exclude with a justification.
7. The researcher reviews the results, provides corrective feedback, and supplies targeted examples. Steps 6 and 7 repeat until the agent's classifications are consistent with the researcher's judgment.
8. Optional: Title and abstract prompt from the article: "Based on the uploaded criteria, should the following study be included or excluded? Please explain your reasoning."
9. Optional: Full-text prompt from the article: "Assess whether this full-text article meets the inclusion criteria for this systematic review. If you decide to include or exclude, provide direct quotations from the article to justify your decision."
10. Note: Steps and prompts quoted from the open-access tutorial by Qiu, Jiang, Chen and Lin (CC BY 4.0). A person still makes the final include or exclude call.

## Credit

Method author Tongyu Qiu et al., International Journal of Technology Assessment in Health Care (CC BY 4.0)
Source: https://www.cambridge.org/core/journals/international-journal-of-technology-assessment-in-health-care/article/promptbased-tutorial-for-large-language-modelassisted-screening-in-systematic-reviews-and-metaanalyses/A769118FCF9B9A1F0E9911E770044CE1