How to use the Evidence Synthesis Tool.
Synthesis should retain disagreement and differences in methods. Sources that answer different questions should not be forced into a single average conclusion.
Make the workflow fit your task.
Create a source matrix covering population, method, measure, date and findings. Compare like-for-like evidence before drawing themes, preserving disagreement and quality limitations. Trace each synthesis statement to its supporting sources instead of averaging incompatible results.
- What you provide
- Supplied source excerpts addressing one question.
- What you get
- Areas of agreement, disagreement and missing evidence.
See the input and the result.
Illustrative input and output · a teaching example, not a live WebAct run
Example input
Two fictional studies: A observes 5 beginners, 3 need help with setup. B surveys 20 experienced users, 18 report easy setup. Compare without pooling the results.
Completed example
Study A: observed assistance needed by 3 of 5 beginners. Study B: self-reported ease among 18 of 20 experienced users. Synthesis: these findings concern different populations and measures, so they do not directly contradict each other. Do not calculate one combined ease rate. Investigate whether experience or measurement method accounts for the difference; this pair does not establish causation.
Load this input into the prompt, then copy it to WebAct to try the task. Your result may differ from the illustration.
Decisions and troubleshooting.
Should findings from different populations be combined into one percentage?
Only with a justified method and compatible measures. Otherwise compare them separately and explain the differences.
Why do two studies appear contradictory despite measuring different outcomes?
Their questions or operational definitions may differ. Align those details before concluding that the evidence conflicts.
Try it with your own source.
Replace the example with your material in the task prompt. Keep the requirements you need, then copy the task into WebAct.
Customize and copy the task ↑