Artificial intelligence offers many ways to improve access to research evidence. The challenge is not generating ideas, it is deciding which problems are most worth solving.

At Trip, we are considering two quite different developments. One would use AI to help people build better searches and identify the most relevant results. The other would monitor guidelines, reviews and clinical topics for important new evidence.

Both could be useful. We are unlikely to develop both at the same time, so we would like your help deciding where to focus.

Option one: AI-supported search

Traditional search remains central to Trip. It keeps the underlying evidence visible and allows users to explore the results for themselves.

But searching can be difficult. People may not know the best terminology, useful synonyms can be missed, and the most relevant result does not always appear near the top.

AI could help by:

  • suggesting alternative or missing search terms;
  • turning a natural-language question into a stronger search;
  • identifying synonyms and related clinical concepts;
  • reranking results by likely relevance;
  • suggesting ways to broaden or narrow a search.

The aim would not be to replace search with a generated answer. It would be to make finding the evidence quicker and easier.

This may be most useful if you struggle with choosing search terms, refining queries or finding the best evidence among noisy results.

Option two: Evidence Watch

Evidence does not stand still.

A guideline or systematic review may be reliable when published, but new trials appear, safety concerns emerge, and papers may later be corrected or retracted.

Evidence Watch would allow users to monitor an important topic, guideline, review or recommendation for developments such as:

  • new trials or systematic reviews;
  • findings that challenge an existing conclusion;
  • important safety evidence;
  • corrections or retractions.

It would not decide that guidance should change. It would act as a safety net, flagging new evidence that may deserve human review.

This may be most useful if you need to keep searches up to date, monitor existing guidance or avoid repeatedly running the same searches.

Which problem causes you more difficulty?

We are not asking which idea sounds more exciting. We want to know which problem has the greater impact on your work.

Would you benefit more from help finding the right evidence today or from knowing when the evidence changes tomorrow?

Please vote in the poll below:

Please also leave a comment telling us what you would need the chosen service to do well.

Your feedback will help us decide what Trip builds next.