What challenges did The Clinician face before AI implementation?

Manual authoring of clinical projects required multi-week coordination across clinical leads, solutions teams, informatics specialists, statisticians, and integration engineers. Clinical protocol intent had to be manually mapped into validated variables, cohorts, assessments, schedules, and reporting logic. The legacy process created a bottleneck that limited project launches and made smaller registry or quality-improvement projects hard to justify.

What was the impact of the AI solution?

Median setup time fell from 42 days to 3.1 hours. Monthly project launches increased from 4 to 47 within 30 days. Customers avoided an estimated $2.1M in annualized external consulting costs. The system flagged 14 unauthorized instrument extraction attempts.

Source

GCP

The Clinician no-code clinical project authoring wizard using Gemini Enterprise Agent Platform

Use case typeWorkflow automationUpdated 1 day ago

The Clinician built TC-WIZ, a no-code project-authoring wizard powered by its Responsible AI Clinical Assistant (RAI) on Google Cloud. The system translates clinical protocol intent into validated platform configuration, including variables, cohorts, assessments, schedules, reporting logic, draft updates, scoring formulas, and recommended validated instruments. The architecture uses Gemini Enterprise Agent Platform (formerly Vertex AI), Gemini models, function calling, and Cloud Run functions with hybrid routing between Gemini Pro and Gemini Flash. The wizard includes PHI screening controls and licensing checks against curated instrument libraries.

Organization: The Clinician
Industry: Healthcare
Location: Australia
Published: July 2026

Reported outcomes

47 projects per month

monthly project launchesOther quantified impact

42 daysmedian setup time3.1 hoursmedian setup time4 projects per monthmonthly project launches2.1 USD millionannualized external consulting costs14 attemptsunauthorized instrument extraction attempts

Strategic outcomes

Scale & capacityScaled clinical project launchesCost efficiencyReduced reliance on external consultingRisk & complianceAdded PHI and licensing guardrails

Primary read

Use case focus

Showing 3 of 3

1Workflow automation
2Project management automation
3Healthcare workflow automation

Manual authoring of clinical projects required multi-week coordination across clinical leads, solutions teams, informatics specialists, statisticians, and integration engineers.
Clinical protocol intent had to be manually mapped into validated variables, cohorts, assessments, schedules, and reporting logic.
The legacy process created a bottleneck that limited project launches and made smaller registry or quality-improvement projects hard to justify.

Built TC-WIZ, a no-code project-authoring wizard powered by RAI.
Used Gemini Enterprise Agent Platform and Gemini models with function calling to update drafts, build form sections, generate scoring formulas, and recommend validated instruments.
Deployed the system on Cloud Run functions with nine production endpoints and a hybrid routing pattern that sends complex reasoning and document extraction to Gemini Pro and high-volume tasks to Gemini Flash.
Added PHI detection to block sensitive-data calls and embedded licensing controls to check requested clinical instruments against curated libraries.

Technologies

Gemini Enterprise Agent Platform Gemini Cloud Run functions

Median setup time fell from 42 days to 3.1 hours.
Monthly project launches increased from 4 to 47 within 30 days.
Customers avoided an estimated $2.1M in annualized external consulting costs.
The system flagged 14 unauthorized instrument extraction attempts.

Architecture

TC-WIZ is a no-code project-authoring wizard powered by RAI and built on Gemini Enterprise Agent Platform (formerly Vertex AI). The implementation uses Gemini models with function calling, runs on Cloud Run functions, and routes work across nine production endpoints: Gemini Pro handles complex reasoning and document extraction, while Gemini Flash handles high-volume, latency-sensitive drafting tasks. The design also includes PHI screening and licensing controls tied to curated clinical instrument libraries.

Sources & evidence1

Groundedness: 5/5Type: Customer StoryPublished: Jul 12, 2026Publisher: Google CloudEvidence: PrimaryConfidence: High

Primary source

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Customer evidence