Agent Intelligence is a platform function
that provides a layer of artificial intelligence (AI) that empowers features and
capabilities across ServiceNow
applications to provide better work experiences.
Note: Agent Intelligence is not supported on
on-premise instances, as its solution training functionality requires processing in ServiceNow datacenters.
Agent Intelligence includes two
frameworks that you can use to create machine-learning solutions: one that predicts the correct
category for your record data, and one that recommends solution content for reuse based on record
similarity. You can enable this function on your instance by activating the Agent Intelligence
plugin (com.glide.platform_ml), which includes the Agent Intelligence Reporting
Agent Intelligence classification
Note: In artificial intelligence communities, the term "train" is used for machine-learning
discourse in the same way we use it for humans and animals. For example, you can train horses,
and you can train solutions.
The Agent Intelligence classification
framework enables you to use machine-learning algorithms to set field values during record
creation, such as setting the incident category based on the short description. You can train
predictive models so they act as an agent to automatically categorize and route work based on
your past record-handling experience.
Enable Agent Intelligence
higher volumes of incoming requests at lower costs. Automate the categorization and assignment
of requests to gain these benefits.
- Reduce task resolution times.
- Reduce the number of interactions required to resolve tasks.
- Reduce the error rates of categorizing and assigning work.
For information on how to use the classification framework, see Create and train a classification solution.
Agent Intelligence similarity
The Agent Intelligence similarity
framework identifies existing records that have similar values to a new record. You use the
framework to build a word corpus that functions as the vocabulary the system uses to compare
your trained records based on their textual similarity. For example, you can train a subset of
your incident records to recommend a resolution based on the information of a similar incident
record. By reusing similar closed incidents that have a proven resolution, you can help agents
and fulfillers quickly provide the best resolution for an incoming incident.
The similarity framework does not require an exact match of words for its text comparisons, as
its algorithms identify similar words and synonyms based on similar contexts. For example, the
phrases "printer not working" and "printer broken" are both captured in your word corpus. The
framework also collects, learns and applies your industry-specific context. For example, the
phrase "unable to join network" has a different context in a networking company than it does in
a healthcare insurance company.
To keep your word corpus up to date, retrain your solution periodically and refresh your
Similarity Window frequently. To see how the Similarity Template helps you to configure your
solution using similarity windows, filters, and input fields, see Create and train a similarity solution.
Note: The similarity framework currently only supports the English language.
Training your machine-learning solutions
Agent intelligence enables you to train predictive models and machine-learning solutions that
you can apply to your business processes, such as:
You can also extend Agent Intelligence
to other processes by creating your own predictive models and training them on your past record
A predictive model consists of these components, some of which you must provide.
- Solution definition
- A data record you create and configure that specifies these values for training a
- The records used to train the model. For example, only train on incidents that have been
resolved or closed within the last 6 months.
- The input fields the model uses to make predictions. For example, use the incident short
description to make a prediction.
- The output field whose value the model predicts. For example, set the incident category
based on the short description.
- The frequency to retrain the model. For example, retrain the model every 30 days.
- A Java object produced when you train a solution definition at a ServiceNow datacenter. Agent Intelligence uses this object to
predict a target field value given one or more input field values. All solutions specify
- The solution precision is the aggregate percentage of correct predictions.
For example, a precision of 50 means that out of 100 predictions, half of them should have
the correct value.
- The solution coverage is the aggregate percentage of records that receive a
prediction. For example, a coverage of 50 means half of all eligible records actually
receive a prediction.
- The solution classes are the output field values for which the model can
make predictions. Each class is an output field value with a list of possible precision,
coverage, and distribution metrics to choose from. For example, the Incident Categorization
solution has a class for each category such as software, inquiry, and database.
- The class distribution is the percentage of records from the entire table
that have this particular output field value. For example, a distribution of 50 for the
inquiry class means that half of incidents have the inquiry category.
- Business rule
- A rule that calls the solution data set to generate a prediction when a new record is
Selecting data records for training your solution
A solution is only as good as the record data you use to train it. In general, a good training
dataset has these characteristics.
- The solution definition input fields are available to users when creating records. To make
predictions at record creation, the solution must have the input field values at record
- The solution definition output field is a choice field. To make more accurate predictions,
limit the output field to a finite set of possible values.
- The training records only contain correct values for the output field. To make more
accurate predictions, filter out any records that have unreliable output field values. For
example, if recently closed incidents are subject to review and change for a month, filter out
any recently-closed incidents.
- The training records contain multiple examples of each output field value you want the
solution to predict. To provide more record coverage, include multiple examples of each output
- The training records include common variations of the input fields. To provide more record
coverage, include multiple examples of input field values.
Exporting your solution for training
To train a solution, you export its solution definition and associated records to the nearest
training service at a ServiceNow
datacenter. If you have data sovereignty requirements, training is not available. When training
is complete, the training service exports the solution back to the instance and deletes all
customer training data from the training service servers.
Note: All communications between the
instance and the training service are over HTTPS.
Prediction business rules
By default, the system uses these business rules for Agent Intelligence
|Default Task Based Prediction
||A business rule that runs before inserting new task records to make a field value
prediction based on the solution definition output field and the solution dataset. Use this
business rule as a template to create your own prediction logic. This business rule calls
the Agent Intelligence API.
|Update Prediction Results
||A business rule that runs before closing task records to update the solution
statistics with the actual precision and coverage results.
Monitoring your predictive model coverage and precision
You can track the coverage and precision of each predictive model using the Solution
Statistics dashboard, which provides reporting on these prediction areas by default.
|Average Prediction Coverage (last 30 days)
||Shows the average prediction coverage of a solution for the last 30 days. The value
represents the percentage of predictions that yielded an outcome out of the total number of
predictions attempted. Click the coverage score to see a breakdown by class.
|Daily Prediction Coverage
||Shows the daily prediction coverage of a solution. The value represents the
percentage of records created on a given day where the solution was able to predict an
|Average Prediction Precision (last 30 days)
||Shows the average prediction precision of a solution for the last 30 days. The value
represents the percentage of predictions where the predicted value was the same as the
final value of the field when the record closed. Click the precision score to see a
breakdown by class.
|Daily Prediction Precision
||Shows the daily prediction precision of a solution. The value represents the
percentage of records closed on a given day where the predicted field value was the same as
the final value.
For instructions on how to use the dashboard, see Review solution statistics.