DEMO

Live Context for Supply Chain Resilience

Use Bob, Confluent, watsonx Orchestrate, OpenSearch and RAG to detect critical material risks early, evaluate mitigation options, and protect Oil & Gas turnaround readiness.

Building Blocks used:

ai.agents

data.pipelines

Skills used

Download skills for IBM Bob →

Products Used

1 Review use case

Supply-chain decisions are often made using information spread across procurement systems, supplier portals, inventory applications, logistics feeds, and static knowledge sources. In fast-moving situations, a supplier status, approved-vendor list, shipment position, or material-readiness condition can change after a report or RAG index was last refreshed. This creates a risk that planners and procurement teams make decisions using stale context.

This demo shows how Live Context can be brought into a supply-chain experience using Bob, Confluent, and IBM watsonx Orchestrate. Confluent provides the real-time event backbone and latest supply context, while watsonx Orchestrate exposes that context through an agent experience. IBM Bob is used to assemble and integrate the overall solution pattern, helping bring together streaming, agentic workflows, APIs, skills, and enterprise capabilities around the business problem.

Start Here

Watch this short overview

Preview the application

Explore key screens from the demo

2 Try the interactive application

Experience the interactive demo and explore its features. A demo script is provided to help when presenting the application to partners.

Have questions, want a walkthrough or found a bug?

Contact the demo owner for assistance.

Submit a request →

3 Explore how it was built

Supply-chain changes such as approved-vendor updates, shipment changes, inventory movements, and material-readiness events are published into Confluent as real-time business events. Confluent provides the latest supply context that can be retrieved at query time rather than relying only on static or periodically refreshed information. IBM watsonx Orchestrate provides the agent experience and coordinates the tools required to retrieve and use this fresh context. A user can ask about a critical material such as CVA-8842, and the agent can respond using the latest available supplier or sourcing state. IBM Bob sits at the build and integration layer, helping assemble the streaming, agent, API, skill, MCP, and user-experience components into a reusable solution pattern. The objective is not only to show a single turnaround use case. The architecture demonstrates a reusable Live Context pattern that can be applied wherever business decisions depend on rapidly changing enterprise information.

Architecture

4 Download and modify with IBM Bob

Download the source code and specifications for this application to set up and run it locally. Once downloaded, open the code in IBM Bob to modify and adapt it to your own use case.

Specifications

Source Code

Demo Script — Live Context with Bob, Confluent & watsonx Orchestrate for Turnaround Resilience

Step 1 — Set the Business Context

Start with the business problem: supply-chain decisions are often made using information distributed across multiple systems, and the context can become stale very quickly.
Explain the concept of Live Context: the user should be able to ask a business question and receive an answer based on the latest relevant supply event or state, not only a previously indexed snapshot.

Step 2 — Introduce the Turnaround Scenario

Introduce the Oil & Gas turnaround scenario and material CVA-8842, which is required for a critical turnaround activity.
Explain why material readiness is time-critical and the consequences of acting on outdated supplier or sourcing information.

Step 3 — Query the watsonx Orchestrate Agent

Ask the watsonx Orchestrate supply-chain agent for the latest approved-vendor or sourcing context for CVA-8842.
Show that the answer is based on the current Confluent real-time context rather than a stale indexed snapshot.

Step 4 — Publish a Live Supplier Change in Confluent

Publish or replay a supplier, approved-vendor, or sourcing change event in Confluent.
Briefly explain what the event represents and how it would affect turnaround readiness decisions.

Step 5 — Show the Agent Reflecting Updated Context

Ask the same or a related question again and show that the agent reflects the updated context at query time.
Highlight the contrast with a static RAG approach where the answer would still be based on the previous snapshot.

Step 6 — Explain the Business Value

Explain the business value: planners and procurement teams can identify sourcing exposure earlier and make better readiness decisions before a material issue affects the turnaround schedule.

Step 7 — Show How Bob Brings the Solution Together

Show how IBM Bob is used to assemble the end-to-end solution — Confluent for events and live context, watsonx Orchestrate for the agent and workflow experience.
Walk through the Bob skills, modes, MCP servers, APIs, and integrations used to build the solution pattern.

Step 8 — Close with Broader Applicability

Close by explaining that this is only one example. The same Live Context pattern can be applied to logistics disruption, supplier risk, inventory shortages, maintenance readiness, pressure/leak response, and other industry use cases where decisions depend on rapidly changing information.