Normalized claim
Documentation_time_reduction: 90% decrease
resulting in a 90 percent reduction in time compared with manual photography
PlanRadar: GenAI-based visual documentation (“SiteView”) on AWS
Use case typeDocument automationUpdated Jun 13, 2026
PlanRadar, a Vienna-based B2B software company for construction and real estate, built SiteView as a visual documentation add-on to its platform. The solution uses 360-degree camera footage uploaded to Amazon S3, extracts metadata, combines camera views, blurs people for GDPR compliance, and uses machine learning and Amazon Nova Foundation Models via Amazon Bedrock to analyze floor plans and generate interactive walkthroughs. SiteView aligns captures from different dates so users can compare progress over time in one place.
- Organization
- PlanRadar
- Industry
- Real Estate
- Location
- Austria
- Published
- June 2026
Reported outcomes
500 square meters
site_area_documentedTime & speed
−90%documentation_time_reduction+97%positioning_accuracy50 requests/monthnew_access_requests_per_month
Strategic outcomes
New product / capabilityLaunched visual site documentation add-onRisk & complianceEnabled GDPR-compliant footage processingCustomer experience & trustCentralized site documentation in one placeNew product / capabilityCreated interactive walkthrough comparisons
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Site_area_documented: 500 square meters increase
Customers can document 500 square meters of a construction site in approximately 5 minutes
Normalized claim
Positioning_accuracy: 97% increase
SiteView delivers positioning accuracy of 97 percent
Normalized claim
New_access_requests_per_month: 50 requests/month increase
Since going live with SiteView, PlanRadar has had approximately 50 new access requests per month
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- PlanRadar
- Provider
- AWS
- Maturity
- Unknown
- Linked source
- AWS Solutions Case Study
No explicit deployment-stage evidence found.
Customer identity supportedSource describes one deploymentMaturity evidence evaluated
Primary read
Use case focus
Showing 3 of 3
- 1Visual inspection
- 2Document processing
- 3Generative AI application
- Manual photo documentation on construction sites was time-consuming and incomplete, especially amid labor shortages.
- PlanRadar needed a GDPR-compliant visual documentation workflow that integrated with its existing platform.
- PlanRadar runs its platform on Amazon EKS and stores SiteView video data in Amazon S3.
- Users capture a site with a 360-degree Insta360 camera; the uploaded footage is processed to extract metadata, combine front and rear views, scale video, and blur people for GDPR compliance.
- SiteView uses machine learning to calculate distances and analyze floor plans.
- PlanRadar uses Amazon Nova Foundation Models via Amazon Bedrock for its AI workloads.
- The system extracts key frames, builds an interactive walkthrough, and aligns recording paths across dates to support time-based comparisons.
- Customers can document 500 square meters of a construction site in approximately 5 minutes.
- That represents a 90% reduction in time compared with manual photography.
- SiteView delivers 97% positioning accuracy.
- PlanRadar reported about 50 new access requests per month after going live.
- The company says customers can manage all site documentation in one place, improving the user experience.
Architecture
SiteView is a visual documentation add-on for PlanRadar's construction, facility management, and real estate platform. It runs on Amazon EKS, stores uploaded 360-degree video in Amazon S3, processes the footage to extract metadata, combine camera views, blur people for GDPR compliance, and uses machine learning plus Amazon Nova Foundation Models via Amazon Bedrock to analyze floor plans and generate interactive site walkthroughs aligned across dates.
Sources & evidence1
Evidence: Medium50/100Evidence strength
- Customer explicitly identified
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: Jun 8, 2026Publisher: AWSEvidence: VendorConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
AI patterns
Browse the catalog
Was this useful?
Community
Comments
Loading comments...