Input data and information sources
Texts come from citizens, customers, parents or associations outside the organisation. Free-text responses often name people, places or personal circumstances.
Text analytics for feedback and consultation responses
Also known as: Text analytics of feedback and consultation responses
The system summarises large volumes of free-text survey, complaint or consultation responses, identifies themes and classifies each response.
Understand the use case
What defines this use case?
It shows at a glance how often themes occur and which views predominate. The Scottish government tested such a tool on a consultation; the UK's Ofsted is trialling another.
This page describes a typical system design. Actual data flows and permissions depend on your implementation.
- System design
- Generative assistance
- Ability to act
- Provides results for subsequent use
- Fields of use
- public administration
- Also known as
- sentiment analysis, topic analysis, free-text analysis, complaint analysis
How it works, step by step
System design and data flows
Input data
Free-text survey, complaint or consultation responses arrive together.
Texts come from citizens, customers, parents or associations outside the organisation. Free-text responses often name people, places or personal circumstances.
Processing
A model identifies themes and attitudes and classifies each response; a language model summarises themes.
Texts are prepared for comparison and analysed by topic, category or other specified characteristics. Depending on the system design, a model classifies individual responses or a language model produces a summary. Individual classifications, aggregation and interpretation should remain distinguishable in the results.
Results
The tool returns a theme overview with frequencies, summaries and example quotations.
A generated result is newly worded or created. To assess it, the instruction and context on which it is based must remain identifiable.
Use and impact
The overview feeds into reports, draft legislation or product and service decisions.
The model supplies information for subsequent use. Selection, adoption or a professional decision in the following workflow is a separate step and should not automatically be attributed to the model.
Explore the system design: Select a component to see its task, incoming and outgoing data, and role in the use case. The guided walkthrough explains each phase. Then use Yes, Uncertain and No to represent your specific system variant.
12 review first8 clarify8 baseline threats
- Present
- Depends on your system
- Absent
- Review first
- To clarify
How to use the model
The diagram shows the typical architecture. Select a component to see what happens there and adapt its features to your system. Enable “Analysis guidance” to see which threats need reviewing for this architecture. The page's checklist continues to describe the typical case.
Changes from the typical case
None yet. Each change will appear here.
Where most threats arise
- 4 review first
- 4 clarify
- 3 review first
- 2 review first
In this system design: 12 to review first, 8 to clarify, 8 baseline threats.
Architecture as a list
External access: Depends on your system
To clarify
Input: Part of every AI system
Review first
Baseline for every AI system
Third-party content: Present
Review first
- Prompt Injection: Indirect Review priority
AI model: Part of every AI system
Review first
- Sleepy Agent (Time/Event-Triggered Hidden Instructions)
- Prompt Injection: Direct
- Jailbreaks
- Meta Prompt Extraction
Baseline for every AI system
Provider service: Present
Review first
To clarify
Training and feedback: Depends on your system
To clarify
Result: Part of every AI system
Review first
- Factual Inconsistencies (Hallucinations) Review priority
- Model Denial of Service
Baseline for every AI system
person: Part of every AI system
Review first
- Overreliance Review priority
Affected person: Depends on your system
Unapproved AI services: Depends on your system
To clarify
Supply chain and technical foundations: 5 baseline threats applying to every AI system
Baseline for every AI system
How it differs from similar use cases
Generative AI assistant for staff
Summarises individual texts on request rather than analysing a whole collection
Detects and removes individual unlawful posts or rule violations
Data and information
Processing and operating environment
The language model generally comes from another provider.
Storage and further use
Logging, retention periods and possible use for training must be established for the specific implementation.
Results and data sharing
Cloud services send responses outside the organisation's environment.
Using a provider does not automatically determine where processing takes place. Storage location, subcontractors, deletion periods and use for training must be checked for the specific deployment.
Assess risks and determine measures
From understanding the system to analysing risks
- Define the system boundary
Record data, participants, interfaces and permissions. Resolve uncertain characteristics in the model.
- Investigate threats
Relate review candidates to actual data flows: what could happen, and who would be affected?
- Assess risk
Assess impacts and likelihood in the deployment context. The number of review candidates is not a risk score.
- Provide evidence of measures
Select appropriate controls, assign responsibilities and define effectiveness checks. Document residual risks and approvals.
Key threats in the application context
- 3 particularly important
- 9 typical
- 8 depending on the system
- 8 additional threats for every AI system
A total of 28 threats from the threat catalogue may be relevant to this use case.
Priority review points
Factual Inconsistencies (Hallucinations)
The model summarises a theme barely present or presents a minority view as the majority. Readers relying only on the summary draw incorrect policy or product conclusions.
An interest group submits many responses containing hidden instructions. Analysis then weights its position more heavily than the response count warrants.
The theme overview looks complete and is ordered by frequency. Rare but serious indications, such as danger, may never be read in full.
9 further review candidates in the typical design
Other relevant threats
Training data or an adopted base model can introduce hidden triggers for misbehaviour.
Listed because of this characteristic
- Uses another provider's model
Sleepy Agent (Time/Event-Triggered Hidden Instructions)
An instruction-following model can change behaviour at a particular time or event.
Listed because of this characteristic
- Performs natural language tasks
Users can override the system's working instructions through their inputs.
Listed because of this characteristic
- Performs natural language tasks
People requesting generated content may try to bypass intended limits.
Listed because of this characteristic
- Performs natural language tasks
Carefully crafted queries can reveal system instructions, which must therefore contain no secrets.
Listed because of this characteristic
- Performs natural language tasks
Complex or high-volume inputs can exhaust model computing resources.
Listed because of this characteristic
- Generates its own text
Targeted queries can recover some personal or protected training data from the model.
Listed because of these characteristics
- Processes personal data
- Processes confidential data
Sensitive Information Disclosure
Confidential content can appear in answers, supplied context or logs.
Listed because of these characteristics
- Processes personal data
- Processes confidential data
Exfiltration from ML Application
Protected data can leak through tools, network connections, storage or insiders.
Listed because of this characteristic
- Processes confidential data
Up to 8 further threats may apply, depending on your system design. Nine threats need to be reviewed for every AI system. One of these is particularly important here and is therefore listed above.
System features and open questions
Each Yes adds further threats to your checklist, up to 8 in total. If you cannot yet answer a question, include its threats in your review.
- Added by this Yes
- Also requires a Yes to another question
How your system is built
- Uses operational feedback2 threats
- Learns from your own data1 threat, plus 1 only in combination with other characteristics
- Learns from examples with correct answers1 threat
How you operate the system
- Accepts queries directly through an interface4 threats
- Accessible over a network1 threat, plus 1 only in combination with other characteristics
- Incurs costs with each query1 threat
- Shares computing resources with other customers or applications1 threat
- Used alongside unapproved AI services1 threat
How your system is built
Does your organisation train or fine-tune the model itself using its own data?
If yes, add
Is the model trained on examples to which someone has assigned the correct answer?
Traditional sentiment analysis learns from labelled examples; language models often work without these.
If yes, add
Does operational feedback or output later feed into analysis or training?
If yes, add
How you operate the system
These questions arise for almost every AI system.
Can people or programs query the model directly, for example through an interface?
If yes, add
Is the system accessible over a network or dependent on network services?
If yes, add
Do you pay per query or unit of computing time, so costs increase with use?
If yes, add
Does the system share servers or computing resources with other customers or applications?
If yes, add
Do staff also use AI services for this task that your organisation has not approved?
If yes, add
Controls and implementation
Measures for the priority review areas are expanded. Each linked measure explains how to implement it.
Review priorityFactual Inconsistencies (Hallucinations)3 measures
Review priorityPrompt Injection: Indirect3 measures
Review priorityOverreliance3 measures
Backdoor ML Model2 measures
Sleepy Agent (Time/Event-Triggered Hidden Instructions)3 measures
Prompt Injection: Direct3 measures
Jailbreaks2 measures
Meta Prompt Extraction2 measures
Model Denial of Service3 measures
Privacy Attacks3 measures
Sensitive Information Disclosure3 measures
Exfiltration from ML Application3 measures
Controls for the remaining threats are available on their pages in the threat catalogue.
AI Act provisions
-
Art. 4: AI literacy
For every AI system Applies since 2 February 2025.
-
Art. 53 para. 1 point b, Annex XII: Embedded general-purpose model
Depending on use Review trigger since 2 August 2025.
-
Art. 50 para. 4: Labelling deepfakes and published texts
Depending on use Review trigger since 2 August 2026.
Applies to every AI system
Art. 4: AI literacy
Applies if staff or appointed representatives operate or use AI systems.
Applies since 2 February 2025.
Obligations and details for Art. 4: AI literacy
- Who bears the obligations
- Provider, Deployer, Product manufacturer, Provider of a general-purpose AI model
Detailed obligations
May apply in particular uses
Art. 50 para. 4: Labelling deepfakes and published texts
Applies if an authority publishes generated consultation summaries without human editorial review and responsibility.
Applies since 2 August 2026.
Obligations and details for Art. 50 para. 4: Labelling deepfakes and published texts
- The general condition is
- Applies if the system creates deepfakes or AI texts on matters of public interest are published without editorial responsibility.
- Who bears the obligations
- Deployer
Detailed obligations
Art. 53 para. 1 point b, Annex XII: Embedded general-purpose model
Applies if your organisation builds the tool itself using a large language model or another third-party general-purpose model.
Applies since 2 August 2025.
Obligations and details for Art. 53 para. 1 point b, Annex XII: Embedded general-purpose model
- The general condition is
- Applies if another provider's general-purpose AI model is incorporated, such as a large language model.
- Points to consider
- The model provider bears its obligations. It must give you the Annex XII information; use it for your own documentation.
- Who bears the obligations
- Provider of a general-purpose AI model
Detailed obligations
Classify your system with the quick checker All obligations in the obligations compass
Cross-cutting threats
Review these threats for every AI system, whatever its purpose.
Atypical system features
View 18 further questions
If any of these features does apply to your system, add the listed threats.
Does the system generate or edit images, sounds, voices or videos?
If yes, add
Does the system create new content from open-ended requests that people read, see or hear directly? Translation, reading aloud and transcription do not count.
The system reproduces responses rather than creating content from open-ended instructions.
If yes, add
Does the system search its own collection of documents or records for relevant content?
If yes, add
Does the system formulate answers from retrieved documents?
If yes, add
Does the system use a knowledge graph storing concepts and their relationships?
If yes, add
Does the system remember content from earlier conversations or tasks and reuse it later?
If yes, add
Does the system call other programs, interfaces or search services itself, even if only to read?
If yes, add
Can the system change things itself, such as storing data, sending messages, initiating transactions or granting permissions?
If yes, add
Does the system determine its next steps itself based on earlier results?
If yes, add
Does the system delegate tasks to other AI agents or incorporate their results?
If yes, add
Is the system connected to tools or data sources through the Model Context Protocol (MCP)?
If yes, add
Do documents from several customers, departments or permission groups share one search store?
If yes, add
Does the system directly move or control something physical, such as motors, valves, vehicles or temperatures?
If yes, add
Can people outside your organisation use the system, including without login?
If yes, add
Does the system process several input types together, such as text with images or speech?
If yes, add
Does the system generate code, scripts or database queries for further use?
If yes, add
Does the system execute programs, scripts or commands itself?
If yes, add
Is the system intended to maximise a specified metric, such as revenue, utilisation or clicks?
If yes, add
Sources
- Report of a deployment
Incubator for AI, Evaluating Consult: An AI Tool for Enhanced Public Consultation Analysis
The report describes a test on a live Scottish government consultation and compares outputs with human analysis.
- Register or case collection
UK Algorithmic Transparency Record, Ofsted: Survey Summarisation Tool, 8 July 2026
A language model summarises free text and identifies themes; the tool is in private beta with selected users.
- Statistics
Federal Statistical Office (Destatis), AI-using enterprises by technology type, 2025
Among AI-using companies, 52 per cent use text mining.
Related use cases
Also in the field of Documents and casework
- Intelligent document processing (IDP)The system reads correspondence, invoices and forms, routes them to the responsible team and transfers their data into business systems.
- Automated anonymisation and redactionThe system finds names, addresses and other personal information in documents and suggests redactions for a person to approve.
- E-discovery and technology-assisted review (TAR)The system ranks large document collections by their likely relevance to an investigation or information request, making review easier.
Often used together with
Updated: 30 September 2026. Review checklist rules version 0.3.2, threat catalogue version 2026.10.24.2. How these pages are structured