Mark up the record together — without losing where anything came from.
A medical record annotation tool for marking up the file together: highlights, notes, and tags placed directly on record pages and shared across the review team. Every annotation is pinned to its page — filterable, exportable as cited work product, and kept separate from the record itself, so the record stays the record.
By Ahmed Jemaa, Co-Founder & CEO of Medrecords AI · Published 10 Jul 2026 · Updated 30 Aug 2026
Pinned to the page, not to a position.
Highlight a passage, drop a note, or tag a page, and the annotation anchors to that exact location in the source document. Re-sort the file, deduplicate it, rebuild the packet — the markup follows its page. Filter the layer by tag, author, or document and the whole review snaps into view.
1 file, a whole team — with roles that mean something.
Split the review by packet, provider, or tag and assign it. Threads keep the discussion attached to the evidence it's about, and visibility follows case roles: private notes stay private, team notes stay in the team, and an external reviewer sees the record without your thinking layered on it.
Export the review as cited work product.
Filter the annotation layer down to what matters — one tag, one author, 1 document range — and export it as a digest where every note carries its page reference. Exam-prep lists, deposition outlines, and case memos start from markup that already knows where its evidence lives.
The record stays the record. Your thinking stays yours.
Annotations never alter a source page, so producing the file never means producing your strategy. The separation is structural, not procedural: 2 layers, distinct permissions, and an audit trail on both — audit-grade and legally defensible by design.
See Command WorkspaceFrom raw file to reviewed file.
3 steps, and the whole team works one copy instead of 6.
The file is read, sorted, and indexed; sections are assigned to reviewers by packet, provider, or tag.
Highlights, notes, tags, and threads accumulate on the pages themselves — visible by role, pinned for good.
Slice the annotation layer by tag or author and export a cited digest — the review becomes work product.
Watch a page get a highlight and a sticky note
The clip opens on Configure Export for a demo case. Under Content, the sections list sets what the PDF holds: cover page, document index, narrative, summaries and source pages. Your logo and firm name go on the cover and footers. Document Summaries is unticked, and the nav shows 1 hidden. Under Organize, the documents are grouped by provider; category, facility and relevance are the other choices. Date Range is set to Mar 14, 2025 through Jun 30, 2025, with undated records left out. Generate Export, and the job appears in Past Exports, turns Ready and downloads as 1 PDF. Cases above 10,000 pages split into volumes of 20,000 pages. Last, the chronology opens in the viewer: a bookmark jumps to page 163, the impression gets a yellow highlight and the page gets a sticky note. Every name, provider and date in the demo is invented.
Transcript
- Choose the sections. Your logo goes on the cover and footers.
- Group by category, provider, facility or relevance. Set dates.
- Out comes 1 PDF. Over 10,000 pages, it splits into volumes.
- Jump by bookmark, then highlight and note the page.
Who reviews records with it.
Any team where more than one person reads the same thousand pages.
Staff pre-mark the file; the evaluator walks in with the key pages flagged.
For IME orgsParalegal, associate, and partner on one annotation layer — work product kept apart.
For law firmsNurse reviewers and adjusters share findings without emailing marked-up PDFs.
For TPAsClaim teams keep review history on the file itself, with access logged per role.
For carriersRecord annotation, answered.
No. Annotations live in a separate, access-controlled layer on top of the record — the underlying pages are never altered. That separation matters legally: your team's impressions and strategy notes are work product, and keeping them out of the record itself means producing the file never means producing your thinking.
Annotation visibility follows case roles and permissions. A note can be private to its author, shared with the review team, or scoped to a group — and an external reviewer given access to the record doesn't see the internal annotation layer unless you grant it. Access is managed per case, and viewing is logged like any other PHI access.
Yes. Each annotation is pinned to its exact page and location in the source document, not to a position in a list. Re-sort the file, deduplicate it, or rebuild the packet, and every highlight and note stays attached to the same page it was made on.
Yes. Filter the annotation layer — by tag, author, date, or document — and export the result as a cited digest: each note alongside its page reference, ready for exam prep, deposition outlines, or a case memo. The export cites pages the same way the rest of the platform does.
Split the file by document range, provider, or tag and assign sections to reviewers. Threads on an annotation keep the discussion pinned to the evidence it's about, and a filterable review view shows what's been covered and what's still open — so 2 reviewers never silently duplicate the same thousand pages.
Related capabilities.
Annotation is how the team works the file — these are the surfaces it works on.
Source, timeline, and report on one synced screen — annotate without leaving it.
ExploreSource-linked lists of every diagnosis, medication, and provider — tag from the list.
ExploreEvery annotation view and edit logged — the layer is governed, not informal.
ExplorePut the whole team on one annotated file.
Upload a file, invite your reviewers, and see highlights, threads, and cited exports on your own record. Handled under our BAA; never used to train a model.