World model
A Blueprint world model is a site-specific digital environment built from real capture of one facility and one workflow lane.
For Robot Teams
Bring the exact deployment site into your robot workflow.
Blueprint turns one real facility into a site-specific world model your team can train on, fine-tune against, and use for exact-site data generation before the expensive fieldwork starts.
What teams are buying: one site-specific digital environment built from real capture of one facility and one workflow lane, with the package path and hosted path tied back to the same source record.
Fine-tune policies against the real geometry, occlusions, and workflow constraints that matter at deployment.
Generate site-specific training data and controlled variations from the same capture record.
Compare checkpoints on one exact environment so regressions show up before travel and deployment week.
Use hosted evaluation when your team wants Blueprint to run the exact site and export results without moving files first.
What Blueprint is
Three things Blueprint sells.
Capture the real site, package it cleanly, then let the buyer run its own stack or use Blueprint-hosted runtime.
Site package
A site package is everything a robot team needs to run, adapt, or build its own world model for that site — walkthrough media, geometry, metadata, and rights — instead of using Blueprint-hosted runtime.
Hosted evaluation
Hosted evaluation is the Blueprint-managed runtime path for one exact site, used for reruns, failure review, checkpoint comparison, and export generation without passing files around first.
Visual proof
See the real site first, then inspect the product around it.
The public demo listing is the first trust check. It shows that the site is real, that the package is grounded to that site, and that the hosted path stays tied to the same facility.
- Every artifact starts from real capture of a real facility.
- The site package gives your team everything it needs to run its own stack on that site.
- Hosted evaluation lets you rerun, review failures, and export results without moving files first.
Sample artifact
This reel shows current capture and product surfaces. Additional views are added as the product develops.
What teams get
Start with the path that matches the work.
Buy the site package if your team wants all the site data in its own stack. Request hosted evaluation if your team wants Blueprint to run the exact site, compare checkpoints, and export results before the real visit.
$2,100 - $3,400
Buy the site package
Everything your team needs to run its own world model on that facility — walkthrough media, geometry, metadata, and rights.
- Walkthrough video, timestamps, and camera poses
- Depth and geometry artifacts when available from source capture
- Rights, freshness, provenance, and package notes
$16 - $29 / session-hour
Run a hosted evaluation
Blueprint runs the site for you. Rerun tasks, review failures, compare checkpoints, and export results — no local setup needed.
- Repeatable runs on one exact site
- Rollout video, metrics, and failure review
- Raw bundles and dataset exports for tuning and adaptation
A session-hour is one hour of self-serve hosted runtime on one exact site. It covers the live session time used to run, rerun, inspect, and export results.
Request hosted evaluation$50,000+
Plan a custom program
Use this for custom capture, exclusive training data, or managed evaluation programs around one facility.
- Custom capture scope
- Private or exclusive access
- Managed support for high-stakes work
Illustrative preview
What goes into the site package
- Walkthrough video, timestamps, and camera poses tied to one real facility
- Intrinsics, depth, and geometry artifacts when the source capture supports them
- Site notes, provenance, privacy, and rights metadata
- Package manifest and reference material for grounding your own world model
Sample artifact
What comes back from hosted evaluation
- Repeatable runs on the same exact site
- Rollout video, failure review, and checkpoint comparison
- Dataset, raw bundle, and export generation tied to the listing
- A browser-accessible runtime session, no local setup needed
A session-hour is one hour of self-serve hosted runtime on one exact site. It covers the live session time used to run, rerun, inspect, and export results.
How teams use it
Use one exact site to answer one expensive question earlier.
Deployment fit
Use one exact site to see whether the robot can localize, fit, see the task, and finish the job before the expensive visit starts.
Site-specific data
Generate exports tied to the real facility instead of trying to recover that context later.
Checkpoint comparison
Run the same lane after each autonomy update so regressions show up on the exact environment that matters.
Trust and governance
Clear enough for a skeptical buyer.
- Blueprint captures real facilities and turns them into products robot teams can buy.
- Blueprint sells site-specific packages and hosted access, not deployment guarantees.
- Rights, privacy, and usage controls are attached to every listing up front.
Company references
Blueprint handles capture, packaging, licensing, and hosted access for site-specific world models. It does not promise deployment success. It makes the real site available earlier.