clinical_documentation · healthcare · workflow
Heidi Health increases prompt testing speed 3x using PromptHub
Heidi Health's Medical AI Residents stored prompts in Google Sheets and tested them in Jupyter notebooks, quickly outgrowing this setup. A subsequent third-party prompt testing tool proved equally unreliable and clunky, leaving the team without a stable solution that non-technical medical doctors could also use.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Store prompts and datasets
Prompts and reusable data are stored in PromptHub via variables and datasets to ensure they work at scale.
Tools used
PromptHubJupyter notebooksLLMs
Outcome
Heidi Health saw their testing speed increase by 3x, with prompts becoming better and more robust, leading to improved product experiences for users and major efficiency gains.
What failed first
The Google Sheets and Jupyter notebooks workflow was clunky and inaccessible to non-technical team members. A dedicated prompt testing tool tried before PromptHub was also found to be unreliable and clunky.
Results
Volume3x
Grounding & classification
Source type: vendor customer story
22 fields verified against source quotes, 1 dropped as unverifiable.
content generationdocument aiclinical notefailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedhealthcaresoftwareemployee productivitythroughput increasevendor customer storyclinical documentationquality assurance