> ## Documentation Index
> Fetch the complete documentation index at: https://docs.encord.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Physical AI End-to-End Walkthrough

> Follow an end-to-end walkthrough of a Physical AI pipeline, from raw sensor data to validated model improvements.

# Physical AI end-to-end walkthrough

This walkthrough illustrates how teams commonly use Encord to build, improve, and scale Physical AI systems.

***

## Step 1: Ingest multimodal sensor data

Start by bringing raw sensor data into a unified workspace:

* Upload or sync cloud data
* Preserve timelines and sensor relationships
* Attach environment and scenario metadata

**Docs**

* [Register Cloud Data](/platform-documentation/Curate/add-files/index-register-cloud-data)
* [Files](/platform-documentation/Curate/index-files)

***

## Step 2: Curate data intentionally

Before labeling everything:

* Filter for edge cases
* Group rare or failure scenarios
* Create collections for targeted annotation

**Docs**

* [Getting Started with Index](/platform-documentation/Curate/index-getting-started)
* [Collections](/platform-documentation/Curate/curation-basics)

***

## Step 3: Create annotation projects

Design projects that reflect real-world complexity:

* Choose appropriate workflows
* Define clear ontologies
* Assign annotators and reviewers

**Docs**

* [Create a Project](/platform-documentation/GettingStarted/gettingstarted-create-project)
* [Ontologies](/platform-documentation/Annotate/annotate-ontologies/annotate-ontologies)

***

## Step 4: Annotate and review

Annotate data with temporal and multimodal awareness, then validate quality through structured review.

* Automated labeling accelerates throughput
* Review stages ensure correctness
* Consensus resolves ambiguity

**Docs**

* [Annotate & Review](/platform-documentation/Annotate/annotate-label-editor/annotate-label-editor-annotate)
* [Automated Labeling (Interpolation)](/platform-documentation/Annotate/automated-labeling/annotate-interpolation)
* [Consensus Workflows](/platform-documentation/Annotate/annotate-projects/annotate-workflows-consensus)

***

## Step 5: Export and evaluate

Export labeled data for training and evaluation. Compare model predictions against ground truth to identify gaps.

**Docs**

* [Export Labels (JSON)](/platform-documentation/Annotate/annotate-export/annotate-export-json)
* [Model Evaluation](/platform-documentation/Validation/active-how-to/active-model-predictions-eval)
* [Quality Metrics](/platform-documentation/Validation/label-validation-basics#quality-metrics)

***

## Step 6: Close the loop

Feed evaluation insights back into curation:

* Identify new edge cases
* Re-prioritize data
* Refine Ontologies and Workflows

This loop repeats continuously as models improve.

***

## What success looks like

You know your Physical AI pipeline is healthy when:

* New failure modes are surfaced quickly
* Annotation effort is focused where it matters most
* Label quality is measurable and auditable
* Iteration cycles shorten over time

***

## Next steps

* Explore **Applied AI** for production-focused workflows
* Dive deeper into **Platform → Annotate** for workflow configuration
* Automate repetitive steps using **Agents**

Physical AI is a long game — the right data foundation makes all the difference.