Extract from a whole folder
Run your extraction template across every paper in a folder.
Point Anara at a folder of papers and it runs the same structured extraction across all of them, returning one combined table with a row per paper. Use it once your template is finalized and you just need it applied at scale. This is a Deep Search workflow, so it requires the Max plan.
Prompt
A PhD candidate applies a ten-field schema to sixty studies for a systematic review.
Prompt
I need to run my extraction template across every paper in my "Compassion Fatigue SR - Included" folder. It has 60 papers. Use Deep Search across the folder so this runs in parallel.
For each paper, extract these fields:
- Title
- First author and year
- Country and healthcare setting (ICU, primary care, oncology, etc.)
- Study design (RCT, quasi-experimental, qualitative)
- Sample size and population
- Intervention description (what was done, duration, dose)
- Primary outcome measure and scale used
- Effect size with confidence interval if reported
- Key limitations noted by the authors
- Risk of bias rating (using Cochrane RoB 2 if reported, otherwise leave blank)
Return a single combined table with one row per paper. Where a field is not reported in the paper, leave the cell blank and do not infer. At the end, flag any paper where three or more fields came back blank so I can review whether it belongs in the review at all.What to add to your library
- Required: a folder containing the papers you want to extract from.
- Required: the full extraction template, in the prompt or pasted from a completed example row.
- Optional: one or two completed rows, so Anara matches your phrasing and detail.
What you get
- One combined table, one row per paper, with cells populated from each source or left blank as "not reported."
- A list at the bottom of papers that hit the blank-field threshold, for inclusion triage.
Follow-ups
Dig into a row that looks off.
Prompt
Row 23 (Johnson et al. 2019) has the effect size missing. Open that paper and tell me what it reports about the primary outcome, why you left effect size blank, and whether it should be excluded on methodological grounds.Re-extract one field with a stricter definition.
Prompt
For the "healthcare setting" column, re-extract across all 60 papers using a stricter definition: only use ICU, ED, oncology ward, or primary care as the four allowed values. Anything else, put "other" and note what the paper actually described.Tips
- Name the expected format for each field. "Effect size with confidence interval if reported" gives consistent rows; "effect size" does not.
- Say "leave blank, do not infer" up front, or gaps may get plausible values that are not in the paper.
- For folders over thirty papers, use sub-folders of ten to fifteen. Deep Search does not guarantee full coverage at very large sizes.