Skip to scenario
Back to the business caseParts identification · Implementation

From a photo to an evidenced replacement

Recognition starts the search. The replacement decision requires explicit product relationships and current unit data.

Follow the process
Business goal
Increase efficiency
Business metric
Parts return rate

Verify the part before ordering

Use maintained illustrated lists, supersession records, and installed-unit data. Define when a photo requires manual confirmation.

The task in this example

We need another seal kit like this for the pump at Northfield Water, Plant 2.

  1. Step 1

    Recognize the category

    The vision model suggests a seal kit.

    Model

    A category prediction is a candidate, not a confirmed part number.

  2. Step 2

    Identify the pump

    Confirm Plant 2’s PX-400 and build year.

    Product or customer data

    Installed-base records establish serial 2291 and the 2019 build. Ask if the site has multiple possible units.

  3. Step 3

    Find the assembly part

    Follow the figure callout to the original part.

    Content team

    Maintain callout-to-part and part-to-assembly links in the illustrated list.

  4. Step 4

    Evaluate replacement fit

    Follow SK-12 to SK-15 and check the build-year condition.

    Ontology and knowledge graph

    The query uses the identified unit and returns the replacement, rule, and supporting facts.

  5. Step 5

    Confirm fulfillment

    Check stock and prepare the order.

    System

    The parts system determines availability and executes authorized ordering.

    People

    Confirm unresolved identification and order details before shipment.

This framework provides a practical baseline shaped by experience. Every organization operates under distinct technical and operational realities that require tailored design and governance. While you can adapt these measures independently, we frequently partner with teams to customize governance, integrations, and rollout. Performance outcomes will naturally vary.

Why these content layers matter

Intelligent content

Link each illustrated callout to a part number and assembly, with a maintained installation procedure reference.

Taxonomy

Use shared model, assembly, and part identifiers across content and installed-base records.

Ontology and knowledge graph

Connect the unit to its original part and follow supersession and fit relationships. Preserve the rule and the facts used to derive the recommendation.

Verify the result and handle exceptions

Test the 2019 unit, a pre-2017 unit, a missing build year, and an unclear image. Confirm that unknown or unsupported fit produces a review route.

Do not substitute a visually similar part when fit evidence is missing. Route conflicting supersession records to the product-data owner and keep the recommendation unconfirmed.

How we work
with your team

We can guide your team, work alongside it, or deliver the work for you. Combine these approaches as your needs and capacity change.

Lead

Build capability

We guide your people through the work, building capability that stays with your team.

Support

Add specialist backup

Your team owns the work. We provide experienced backup and specialist help where you need it.

Do

Delegate delivery

We handle work that is one-time, specialized, or outside your core business, without adding an ongoing burden to your team.

Can your parts answer explain why the replacement fits?

Intuitive Stack can help connect illustrated content, part identifiers, and fit relationships with the installed-base data your parts team uses.