Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.mention-me.com/llms.txt

Use this file to discover all available pages before exploring further.

We use generative AI technology to provide useful information while striving to minimise inaccuracies. We use reasonable efforts to ensure that personal information is not used in this process and, to the extent possible, automatically redact personal information before using AI. We strongly advise end-user consumers not to enter personal information into any AI-powered feature. For questions, contact legal@mention-me.com.

​
AI capabilities

Generative AI — We use generative AI to summarise, categorise, and make actionable the large volumes of verbatim text from your customers’ share messages and/or NPS feedback. This helps you optimise advocacy. We are also experimenting with generative AI to support programme optimisation as a platform assistant. Machine Learning — We use ML techniques for customer segmentation and personalisation predictions.

​
Technologies and frameworks

  • Predictive models: XGBoost (Propensity To Refer) and Keras (Extended Customer Revenue).
  • Summarisation and sentiment analysis: LLM models (ChatGPT 3.5, 4, and later).

​
Controls and safeguards

  • LLM output is never displayed to end customers. Only client employees see generative output.
  • Input filters reduce the likelihood of inappropriate content.
  • We have completed a DPIA covering our use of generative LLM and are satisfied the risk is low given our use cases.

​
Model maintenance

  • ML models are retrained at least monthly (some weekly) using the latest data.
  • Performance is monitored over time against a holdout group with incremental upside reported.
  • A team of data engineers monitors and manages pipelines with weekly training schedules.

​
Transparency and explainability

  • Feature importances are recorded for all ML models.
  • The SHAP framework is used to understand individual decisions, though this is not currently surfaced to users.

​
Ethics and fairness

  • Protected characteristics are not used as features in our models.
  • We have covered risks in our DPIA and are satisfied that our use cases carry low risk.

​
Performance metrics

  • Propensity To Refer: Model ROC AUC, predicted propensities in high and low groups, feature importances, and incremental revenue generated.
  • Individual models are built for each client using only their own data.
Last modified on March 31, 2026