AI-Assisted Search FAQs

If AI-assisted search is enabled on your Percipio site, learners see it automatically whenever they perform a search. The AI-assisted search response displays at the top of search results.

There are some exceptions which will not generate an AI-assisted response. Those exceptions include when learners:

• Search on a content UUID or ISBN
• Enter content type searches, such as CAISY or Skill Benchmarks
• Enter text and select from an auto-suggest or type-ahead list
• Use a keyword not included in the AI-assisted search keyword list.

AI-assisted search will attempt to provide a natural language response to a learner's search query. Learners can rate the response with a thumbs up or thumbs down.

Learners also see suggested topics in which to search further. Below the AI response are content recommendations.

Learners can choose to turn off the AI response by unselecting Always show AI answer.

Currently, AI-assisted search is only available in English, but we will be extending it to more languages in the near future

Whenever AI-assisted search generates a response, feedback controls in the way of thumbs up and thumbs down icons are displayed. The learner can click the appropriate feedback icon to submit positive or negative feedback about the response. When negative feedback is submitted, an additional modal displays to ask for more information.

There are some exceptions which will not generate an AI-assisted response. Those exceptions include when learners:

• Search on a content UUID or ISBN
• Enter content type searches, such as CAISY or Skill Benchmarks
• Enter text and select from an auto-suggest or type-ahead list
• Use a keyword not included in the AI-assisted search keyword list.

AI-assisted search does not store user IP addresses, nor does it collect location data, or any personal information (PII) from the learner. Skillsoft network security separately logs IP addresses for the purposes of addressing security risks, such as Distributed Denial-of-Service (DDOS) attacks and intrusion detection. Learn more about how we protect your privacy by reviewing our Privacy Notice - Skillsoft.

For performance, Percipio caches all search queries and responses generated by the AI-assisted search, which includes the search query, the AI response, the date, time, and model information.

When learners click one of the feedback options, we store the search query and AI response along with the provided feedback for general analysis.

• All data entered is encrypted in transit and at rest.
• The information that the learner enters into search passes to the Large Language Model (LLM) to generate the AI response.
• The LLM does not store any conversation data. Skillsoft has MS Azure OpenAI prompt moderation exception so no Generative AI inputs or outputs are logged or reviewed by Microsoft. Similarly, no data from the AI-assisted search is distributed to third parties or is available to train any models.
• Skillsoft stores AI conversation data in authenticated and encrypted AWS storage.

• Feedback learners submit via the thumbs up icon is logged in the conversation logs.

  

  The feedback is periodically reviewed by the Product teams for sentiment, requested improvements, and potential issues. Appropriate enhancements or improvements are considered and prioritized.

• Any data that you share helps Skillsoft improve the service. For example, we use your feedback to increase the effectiveness of AI safety policies.
• Skillsoft has a process for improving the AI-assisted search, which includes review of responses reported as being low quality. This helps us identify common types of problematic responses and how the AI-assisted search might improve.
• Only limited Skillsoft employees can access and review conversation data.

Yes. All data entered is encrypted in transit and at rest.

The AI-assisted search guardrails will simply refuse to respond to input that is off topic or controversial.

We don't attempt to address jailbreaks because in the event of an adversarial attack, the generated output would only be visible to the affected learner and would not have any bearing on the experiences or outcomes of other learners. The localized impact of such an attack minimizes the overall risk to our platform and its users.

All Percipio AI utilizes default content filters. Skillsoft's additional guards enhance protection by preventing many inputs that prevents the AI from providing inappropriate responses.

While it is not zero, it is low and extensive testing has not revealed issues that have raised concerns.

It is improbable the AI-assisted search could produce any hallucinations or bias based on demographics because the search doesn't capture any demographics information, such as country, gender, or age, and all learners use the same AI model version.

In addition, the AI-assisted search uses the LLMs default content filtering and adds additional tests and guards to detect and minimize inputs that might stimulate bias or other inappropriate responses.

Extensive Quality Assurance testing has not revealed significant issues with outputs. The AI-assisted search uses GPT to respond to simple search queries and questions. Each prompt has a detailed description that includes guidance which guards the response.

AI-assisted search utilizes the built-in LLM guards and adds additional guards which review and evaluate the user inputs for off-topic, abuse, and misuse. If these are detected, a response will not be generated.

Users are warned that responses might not be accurate.Users acknowledge the risk by using AI-assisted search.

AI-assisted search uses generative AI in an ethical and responsible way through the implementation of appropriate guardrails, widely recognized as important for AI systems.

In addition, the AI-assisted search uses the LLMs default content filtering and adds additional tests and guards to detect and minimize inputs that might stimulate bias or other inappropriate responses.

AI-assisted search is developed and hosted on AWS and does not use other ChatGPT consumer products. The features utilize the security capabilities of Microsoft Azure:

• Encryption: The LLM automatically encrypts the user's data. The encryption protects their data and helps customers meet organizational security and compliance commitments.
• Data Security: The LLM offers us the ability to do regional deployments to ensure EU hosted data is processed in EU and North America hosted customers data is processed within North America.
• Limited Access Review: Modified Abuse Monitoring - The LLM does not store any conversation data. Skillsoft has MS Azure OpenAI prompt moderation exception so no Generative AI inputs or outputs are logged or reviewed by Microsoft. Similarly, no data from the AI-assisted search is distributed to third parties or is available to train any models. Skillsoft only logs conversations based on opt-in/out or explicit sharing when reporting feedback within the AI simulator.

Additional security layers help to mitigate biases in training data, promote fairness, reduce the spread of false information, and prevent offensive or inappropriate responses through the interactions that learners have with AI-assisted search.

For more information about the technology we used for the different parts of , see:

• Dynamic Conversation: OpenAI GPT-4
• Guides (guardrails): Azure OpenAI GPT-3.5-Turbo

Data is encrypted in flight with TLS 1.2+ and encrypted at rest per FIPS 140-2.

The current models that are used are Commercial off-the-shelf (COTS) models. The models are created by the LLM and hosted by MS on Azure with enhanced data security and content filtering for safety. They do not list all the data that was used for training.