How to run a literature review

You will need:

• Your PubMed search queries (the same ones from the previous review packet)
• The date range of the update window
• An idea of the maximum number of articles you want to carry into the evidence table — the workspace defaults to a sensible cap based on your prior packet

Sign in with your Chemular email at the sign-in page. You'll get a 6-digit code in your inbox; type it back into the page. There is no password.

The scientist decides Include or Exclude using the abstract, full text, or other evidence they consider sufficient. That decision stays saved until a scientist changes it. Obtaining more text or preparing a write-up never asks you to repeat it. Unanswered articles remain undecided.

From the home page (the page you land on after sign-in), click New projectif this is a new product or a new review topic, or open an existing project if you're running an update.

Inside a project, click New run. A run is one execution of the review — one update window, one set of search queries. Each run produces its own deliverables and never overwrites a previous run.

Fill in the run setup form: the review title, the update window (start and end dates), and your PubMed query strings. Save. You'll land on the run dashboard.

On the run dashboard, the primary blue button at the top right says Run everything →. Click it. The workspace will redirect you to a progress page.

The pipeline does five things in sequence:

• Runs your PubMed queries
• Normalizes and deduplicates the records
• Has the AI screen every record's title and abstract against the inclusion criteria
• Downloads open-access full text for every record the AI ranks above the cutoff
• Has the AI read each downloaded full text and recommend Include or Exclude

You don't need to do anything during this. The progress page shows live ticks — “48 of 124 records screened” — so you can tell it's working. Most runs complete in five to fifteen minutes depending on volume.

When the pipeline finishes, the page will show a blue button sending you to the next step.

Open Article review. Each card shows its available abstract and full text. Include or Exclude when you have enough information; an exclusion requires a reason. Saved decisions show a collapsed reviewer summary, with changes available under Change decision / details.

When selection is finished, choose Finish selection & prepare write-ups. The AI then prepares drafts only for scientist-included articles. After signoff, Continue to write-up review opens saved drafts without running AI. Use Re-sign & regenerate AI drafts only when you want a fresh AI pass; scientist edits and approved write-ups are preserved. Obtaining more text never resets a decision.

Check the AI drafts against the included articles, edit the findings and write-ups, and approve them. This reviews the report content; it does not ask you to Include or Exclude again. Earlier drafts, edits and approvals remain saved.

If a draft is missing, use Prepare write-up once a copy is available, or enter the findings yourself. Finish write-up review when every included article’s write-up is approved.

If your review is single-scientist, you can skip this section entirely — adjudication only appears when two scientists have recorded conflicting decisions on the same record.

When it does appear, the dashboard will show a Resolve N conflicts → button. The adjudication page lays out both scientists' decisions side-by-side with their rationales. You make a third call that supersedes the first two.

With every appraisal signed off, the dashboard's primary button becomes Build outputs →. Click it.

The build pipeline runs six stages in sequence: it generates the PMTA narrative draft, catalogs article access, builds the screening audit trail, computes the PRISMA flow counts, finalizes the 1.10.3 Evidence Table, and renders the report PDFs. The progress page ticks per section as the narrative synthesis runs — you can tell live whether it's working or stalled.

Builds typically finish in two to four minutes. When they do, the page sends you straight to the downloads.

The downloads page lists every artifact the build produced. Click any filename to save it locally. The packet you hand off to the regulatory team typically includes:

• narrative_draft.md — the 1.10.2 narrative scaffold, scientist edits go here
• evidence_table_template.csv — the 1.10.3 Evidence Table
• prisma_counts.json / .csv / .md — the PRISMA flow counts for the methods section
• title_abstract_screening.csv and full_text_review.csv — the audit-trail workbooks
• referenced_literature_manifest.csv — every cited record with its access provenance

Libraryin the sidebar is your organisation's document library — it replaces the Zotero group, with the same collections and items. Everyone in your organisation sees the same library.

• Find: pick a collection on the left (or All items, Unfiled items, Trash) and search by title, author, year, DOI, PMID or tag.
• Add: click Add items, then paste DOIs or PubMed IDs (details come from PubMed), or drop PDFs. A PDF is matched to its article by the DOI or PMID on its first page; one with neither becomes an item named after the file — open it and fill in its details. Items are added to the collection you're viewing.
• Organise: tick items and use Add to collection, Remove from this collection or Move to trash. Create, rename and delete collections in the left column (deleting a collection never deletes its items).
• Edit: open an item to edit its details, tags and notes, add links, or attach a PDF.
• Use in a review:on a run's abstract review page, Import from library adds a collection (or the whole library) to the run, PDFs included. These are recorded as other sources in the protocol.

Every error in the workspace is recoverable. The general rule is: if you see a red error message, look for a blue retry button next to it. The two most common cases:

• A pipeline stage failed. The progress page will show Retry pipeline. Click it; the run picks up cleanly from the start. Your scientist decisions and appraisals are preserved — they live in a different table from the pipeline state.
• A build stage failed. The progress page will show Retry build. Click it; only the build re-runs. None of your screening work is touched.

If a retry fails twice in a row, that's when to flag it. The error message and the “Show full traceback” link below it carry enough context for the engineering team to diagnose without you needing to reproduce.

The fastest path to confidence is doing a single end-to-end run on a small update window — say, the last quarter — and seeing the deliverables land. Once you've seen the workspace produce one packet, the rest of the protocol cycles will feel familiar.

Sign in to start →