ZS Associates · 2025–2026 · Team Lead

6,000 PDFs that nobody could safely edit

Turned 6,000+ static SOP PDFs into an editable, auditable system with plain-English edits and region-aware approvals.

6,000+

SOPs supported

5

regions

4

person team led

no — returned to author

yes

send back

approve

version history retained

SharePoint
6,000+ SOP PDFs
system of record

Bulk ingestion
parses documents in parallel

Platform database
stored section by section,
with version metadata

Author requests a change
in plain English

System rewrites only
the affected sections

Redline preview
old text struck through, new text in red

Automated compliance check
basic rules met?

Routes to the approver
for that region

Approver decision

Approved version published
back to SharePoint,
version in the filename

Turning 6,000+ static SOP PDFs into an editable, auditable system — plain-English edits, redlined previews, automated compliance screening, and region-specific approval routing across 5 regions.

Problem

A global pharma client’s standard operating procedures lived as PDFs on SharePoint across five regions. Updating one meant finding the file, editing it offline, and chasing approvals over email — with no reliable record of what changed, who approved it, or which version was current.

Approach

Led the four-person cross-functional team that built the platform, spanning generative AI, API work, data setup, and UI/UX.

We ingest the existing PDFs in parallel, parse them, and store them section by section so edits are surgical rather than whole-document. An author describes a change in plain English; the system rewrites only the affected sections and shows a redline preview — old text struck through, new text in red — before anything is committed.

An automated check screens the draft against basic compliance rules and returns it to the author if they aren’t met, then routes it to the correct approver for that region.

Outcome

Approved versions publish back to SharePoint — which remains the client’s system of record — with the version encoded in the filename, while the platform retains version metadata and full change history. The design worked inside the client’s existing governance rather than asking a regulated organization to abandon it.

Technical detail

Section-level storage

Section-level storage is what makes plain-English editing tractable. The model operates on a bounded section rather than a forty-page document, which keeps rewrites reviewable and diffs meaningful.

Region handling

Region handling was scoped deliberately. Regulatory requirements and document templates were shared across the five regions, and only the approver routing differed — so that became the single region-aware component, rather than five parallel workflows maintained in parallel.

Rejection paths

Rejection paths exist at two points: automated compliance screening and human approval. Both return to the author with the redline intact, so nothing has to be reconstructed from scratch after a rejection.

  • Generative AI
  • Platform & Workflow
  • Team Leadership