AI System for Preparing Food Recall Traceability Files

The problem

In day-to-day operations, gaps in a lot chain can delay preparation of the scope. When raw-material lots, production batches, recipe consumption, dispatch and customer delivery records are scattered across sensors, documents, field records or team files, issues may not become visible in time.

This fragmented data delays preparation of the source-linked traceability file and forces teams to search manually for supporting evidence again. The food engineer and traceability lead must complete missing records and verify each conflict before making a decision.

A common exception is that rework or consolidated dispatch can complicate lot links. Incomplete or incorrect automation that fails to check this context could make the scope too narrow or unnecessarily broad, so no physical or operational action can be carried out directly.

What we set out to improve

• Number of lot links corrected by the specialist
• Proportion of outputs corrected or rejected by the food engineer and traceability lead
• Time between the source event and the review output

How the system works

1. 01 Define the review scope and the roles of the authorised food engineer and traceability lead
2. 02 Retrieve the inputs: raw-material lots, production batches, recipe consumption, dispatch and customer delivery records
3. 03 Check source identity, date, calibration or version, and data recency
4. 04 Link raw-material and production lots
5. 05 Add dispatch and delivery records to the chain
6. 06 Check for exceptions: rework or consolidated dispatch may complicate lot links
7. 07 Place low-confidence or conflicting records in a separate specialist queue
8. 08 Write the source identity, rule, output and timestamp to the audit trail
9. 09 Have the food engineer and traceability lead approve, correct, defer or reject the output

Methods we used

• Lot mapping and source-document matching
• Source, format, timing and required-field checks for raw-material lots, production batches, recipe consumption, dispatch and customer delivery records
• A missing-data warning instead of an estimate when inputs are incomplete or conflicting
• A separate exception check outside the main rule
• Combined retention of the source, rule result, source-linked traceability file and human decision

Where people stay involved

Data and security

Access to raw-material lots, production batches, recipe consumption, dispatch and customer delivery records is restricted to the minimum permissions required for the task. Commercial, location and employee information is masked where possible, and only the necessary portion of the dataset is sent to the model. Access, outputs and the decisions of the food engineer and traceability lead are logged; production use does not begin until the organisation has approved the retention period and data location.

Who this suits

Frequently asked questions