Teneo Inquire stores and retrieves highly detailed transactional records from running conversational AI applications. Augmenters extend default log data by enriching or summarizing it in a format that can be accessed by standard queries. These have the benefit of both simplifying the subsequent querying and increasing performance.

There are two types of augmenters: adorners and aggregators.


As the name suggests, adorners allow log data to be enhanced with additional information. These can create extra data tags to allow easy classification of logs - for instance tagging all sessions that contain two consecutive safetynet hits, or any sessions that resulted in a handover. They can also be to add additional data that wasn't in the original log, for instance, if the IP address for a session was known, then an adorner could reverse geocode this and add the users country and city to the logs.

Adorners can be applied at the session level, transaction level or even event level.

Once an adorner is applied, it will go through all past logs and annotate them, and importantly all subsequent logs will automatically be annotated with this adorner too.

There are two significant advantages of using adorners.

Simplification of queries

Adorners are created by developers to label detailed information they may subsequently wish to query on. It is simpler to create smaller functions, such as labelling any session that contains transactions resulting in a Handover, once, then this label (adorner) can be reused in many queries along with other constraints.

For example if two adorners were created, one to s.2ConsecutiveSN to indicate any sessions that contain two consecutive transactions that hit the safetynet, and s.handover for any session that contains a handover to human then the tql statement to list all sessions in March 2020 containing two consecutive safetynet transactions and also a handover to human would be simplified

Example of a simplified query using adorners

la : s.a.s:2ConsecutiveSN == ‘true’, s.a.s:handover == ‘true’,  s.begineTime == ‘2020-03’ 

Improved performance

As the calculation of adorners for existing sessions is done as a one off batch job when they are applied and all new sessions are evaluated and adorned real time, this processing doesn't need to be done each time a query is run. This will result in a huge performance improvement.


Aggregators are used to build a numeric summary over time of various properties to both speed up performance and simplify querying. Aggregators can be constructed over sessions, transactions, events including those generated by adorners.

Like adorners, aggregators are calculated retrospectively on existing sessions as a batch job when they are applied, and all new sessions are automatically calculated real time.

Adorners and Aggrigators are not enabled on Teneo Developer Sandbox environments.


When building reports that are going to be executed regularly, or dashboards to BI systems, performance should be considered. By using Adorners and Aggrigators reports and dashboards will be much faster and result in significantly reduced server load. It is also advisable to consider using Inquires ‘Save Results’ and combine this with job scheduling, such as Cron, to prebuild data extracts to BI tools for ultimate performance and responsiveness.

Was this page helpful?