AI Compass
Compass

Quality assurance

Analysing complaints, capturing inspection records, spotting deviations: where AI helps in QA and what evidence duties come with it.

·2 min read·By Redaktion KI-Kompass
DETAIL
4 sections

What this is about

TaskValue
Grouping complaint texts and finding clustersvery high
Capturing inspection records from paper or PDFhigh
Classifying deviation reportshigh
Searching for links between batch and complaintmedium
Naming causeslow, stays with the department
Granting releasesnot without human confirmation

Introduction

  1. 01

    Sharpen the categories

    Two experts classify 100 complaints independently. Below 70 percent agreement, the definition is the problem.

  2. 02

    Work up the history

    Group two years of complaint text and name the groups. That often yields a finding immediately, without any model being trained.

  3. 03

    Then classify continuously

    Automatic classification goes live only once the categories hold.

  4. 04

    Secure the feedback

    Every correction by QA is a new label and feeds the next analysis.

  • Report accuracy per category, not as an overall figure. The rare categories are the interesting ones.
  • No threshold without a cost calculation: what does a missed cluster cost, what does a false alarm?
  • Free-text complaint fields contain customer names; pseudonymise before analysis.

Evidence for audits

An auditor asks not about the model but about control of the process. Five items carry:

ItemMeaning
Purpose and boundary of the systemWhat it does and expressly does not
Validation with date and resultFixed evaluation set, quality per category
Model version and change historyEvery change is a change to the process
Thresholds with reasoning and sign-offWho decided this and when
Monitoring in operationHow degradation is noticed

Those five simultaneously cover the requirements of ISO 9001 clause 8.5.1 and, where classified as high risk, substantial parts of Annex IV of the AI Act. See Preparing for audit.

Validation, concretely

  • An evaluation set of 200 to 500 real cases with expert-assigned labels.
  • The set is versioned and rerun on every model change.
  • Inter-expert agreement is reported alongside; it is the ceiling.
  • Per-category results with confidence intervals, not only point values.
  • The cases where the system was wrong, with examples, in the documentation.

Regulated environments

In GxP-regulated settings further requirements apply: computer system validation, change control, access restriction, complete audit trails, and the requirement that electronic records meet standards of completeness, legibility and durability. A self-learning system that changes in operation is routinely incompatible with that: the usual solution is a frozen model state with documented release per version.

Choosing a task in quality assurance

FREE ACCOUNT

Selection sheet and templates: quality assurance

A sheet that picks the first task out of the ones quality assurance actually has, with two tested templates and the review steps for them.

Worksheet3 items

No password needed. We send you a sign-in link. An account does not subscribe you to anything. The newsletter is separate.

Was this page helpful?
Quality assurance