Blood Work Pipeline

What It Does

The pipeline takes a client's raw blood test PDF and processes it end-to-end — no manual NP involvement until the final review step.

Before: NP manually reads every report, types up findings, drafts recommendations, pastes into GHL, sends to client. ~45 minutes per client.

After: Pipeline pre-processes everything. NP opens GHL, sees AI summary already in call_notes, edits/approves in ~5 minutes, sends to client.

The 6 Steps

#	Step	Model / Tool	Output
1	Ingest	—	Raw PDF saved, run created
2	Extract text	pdf-parse → Claude vision fallback	Clean text
3	Parse biomarkers	Claude Sonnet 4.6	Structured JSON
4	Clinical analysis	Claude Opus 4.7	Summary + recommendations
5	Generate client PDF	Puppeteer	Branded PDF
6	Write to GHL	GHL REST API	Updated contact

Cost Per Report

Step	Model	Est. Cost
OCR (if scanned)	Sonnet 4.6 vision, ~5 pages	~$0.05
Parse biomarkers	Sonnet 4.6	~$0.02
Clinical analysis	Opus 4.7	~$0.10
Total		~$0.15–0.20

Compared to ~45 min of NP time per report.

GHL Tag Lifecycle

flowchart LR
    A["new lead"] -->|send_to_protocol_health| B["Protocol Health intake"]
    B -->|junction + junction_sent| C["Junction linked"]
    C -->|link_to_schedule_bloodwork| D["Scheduling link sent"]
    D -->|bloodwork_scheduled| E["Blood draw done"]
    E -->|pipeline runs| F["bloodwork_completed"]
    F -->|scheduled_bloodwork_review| G["NP review in GHL"]