The AI assistant (beta) is your smart assistant on your platform. The assistant helps you quickly and easily find the right information without having to search through all documents and information pages yourself. Thanks to artificial intelligence (AI), the AI assistant can search all content within Plek and provide relevant answers to your questions. The assistant can also help you write or translate content.
The AI assistant is not enabled by default.
Would you like to activate the AI Assistant? Email support.plek@bcs-hr.com.
The AI assistant uses Azure AI to provide smart answers to questions within our platform. This is done through several AI services:
- Azure OpenAI: Generates answers based on available information.
- Azure AI Services: Ensures secure storage and optimization, so that answers are as accurate as possible. Azure OpenAI is a feature within the AI services.
If no relevant information is available within the platform, the AI assistant bases its answers on general knowledge from public datasets.
What can the AI assistant do?
The AI assistant currently has two features:
-
Searching for information
Quickly and efficiently find answers to your questions without manually browsing all information pages and documents. -
Helping to create posts
Whether you need inspiration, translations, or improvements: the AI assistant supports you in writing engaging and high-quality content.
Searching with the AI assistant
1️⃣ Ask a question
Type your question in the chat with the AI assistant.
Example: “How do I request leave?”
Or use one of the predefined prompts.
2️⃣ Searching the platform
The AI assistant scans all info pages and documents to find relevant information.
3️⃣ Formulating an answer
The assistant provides a clear and concise answer based on the information found.
4️⃣ Source references
You receive an overview of the sources used, so you can click through to the original documents.
Using the AI assistant for posts
When creating a post, you can open the AI assistant via the Assistant button below the text editor. The assistant appears in the top-right corner of your screen.
Create a post: start with a prompt
Not sure how to start? Use a prompt to generate a draft.
Example:
"Create a post announcing that two new employees, Ella and Nathan, will start as Sales interns from March 2025."
Happy with the result?
- Click Copy to copy the text to your clipboard.
- Click Play to insert the text directly into the post editor.
Improve a post
Do you already have a draft but want to refine it?
- Write your draft in the text editor.
- Click the AI assistant button and choose a prompt to improve your text.
- The assistant rewrites, simplifies, or optimizes your text.
ℹ️ Note: The assistant always works with the content of the text editor. Make sure the latest version of your text is there.
What information does the AI assistant use?
✅ Platform-wide documents and information
✅ Documents and info pages from groups you are a member of
If no relevant information is found, the assistant uses general knowledge from public datasets (up to a certain point in time).
Is my data safe?
Yes. The AI assistant is built with Azure AI, which meets strict security and privacy standards:
- Your data remains yours: Microsoft does not use your data to train AI models.
- Strong encryption: Data is always encrypted during transmission and storage.
- Secure access: Only authorized people have access via Azure Active Directory.
- Compliant with GDPR and ISO certifications: Including ISO 27001 and SOC 2.
- Full transparency: Plek can always verify how data is processed and stored.
Requirements for the AI assistant
- Up-to-date content: All information must be current.
- Sufficient info pages: A well-filled knowledge base ensures better answers.
- Logical structure: Clear main and subpages help the assistant understand relationships.
Limitations of the AI assistant
❌ Cannot search images (text only).
❌ No access to external documents (such as SharePoint or Google Drive).
❌ Answers are based on available information and the way the question is phrased; no rights can be derived from them.
Tips for an effective PROMPT
1. Be specific and clear
The more specific your question, the better the assistant can respond. Avoid vague or overly broad questions.
Bad example: "Tell me something about sick leave."
Good example: "How should I report sick according to my department’s policy?"
2. Provide context
Give the assistant enough context so the answer better matches your question.
Bad example: "How does it work?"
Good example: "How does the process of requesting leave work in our HR system?"
3. Ask one question at a time
Assistants may struggle to process multiple questions in a single prompt. Therefore, focus on one question at a time.
Bad example: "How do I request leave and how do I change my working hours?"
Good example: "How do I request leave in our system?"
4. Keep your question short but informative
Long, complex sentences can cause confusion. Phrase your question clearly and concisely.
Bad example: "I was wondering if you might be able to explain how the new safety procedures introduced last month work?"
Good example: "Can you explain the new safety procedures introduced last month?"
5. Ask for specific formats or styles
If you want the answer in a certain format or style, make that clear.
Bad example: "What are the benefits of working from home?"
Good example: "Can you list the benefits of working from home in five bullet points?"
6. Avoid ambiguity
If a question can have multiple interpretations, provide clarification.
Bad example: "What are the rules?"
Good example: "What are the rules for requesting leave in my department?"
7. Use examples
If you expect a specific type of answer, you can provide examples to help the assistant understand what you mean.
Bad example: "What are the guidelines for working from home?"
Good example: "Can you list the guidelines for working from home, such as working hours and availability requirements?"
8. State your goal
If you have a specific goal in mind, state it to receive more targeted answers.
Bad example: "How do I improve my presentations?"
Good example: "How can I improve my presentations to better engage my audience?"
With these tips, you ensure that the AI assistant understands your questions better and can provide more useful and targeted answers!
FAQ
Does my data stay within my environment?
In short: your questions do not, but your data does. Your data never leaves the application and is not used to train AI. The AI assistant is hosted via Azure Bot Services. When a user asks the AI assistant a question (a "prompt", in technical terms), it is sent to these services. Azure temporarily uses this data to generate answers. We have configured our Azure services with Microsoft-Managed Keys for encryption and they store NO data for purposes other than processing our requests (according to their privacy policy). The source material — Info pages and Documents — is securely stored in our Elasticsearch instance, which means the content remains private and protected.
Is my data visible on other platforms?
No, your data stays within your environment. For each platform, an index is built where the answer to your question is searched within your own content via the AI Search Index. When using AI Search Reindex in our system, OpenAI (via Azure AI Services) is used to create vector embeddings for the document content. These vectors are then stored in our own Elasticsearch instance. When a user's search query is processed, OpenAI is used to convert the query into a vector embedding using the same embedding model. This embedding is then used to search for the most relevant content in Elasticsearch.
Vector storage is a specialized data storage method that allows information to be indexed and retrieved based on vector representations. These vectors, called embeddings, capture the semantic meaning of embedded data. Vector storage is often used to search unstructured data such as text, images, and audio, to retrieve relevant information based on semantic similarity rather than exact keyword matches. Elasticsearch is a vector store.
How does the AI assistant use our data to answer questions?
This is how it works:
- Data Indexing: When using AI Search Reindex in our system, OpenAI (via Azure AI Services) creates special data representations called vector embeddings for your content.
- Data Storage: These vectors are securely stored in our Elasticsearch instance.
- Query Processing: When you ask a question, OpenAI converts it into a vector embedding. This embedding is then used to find the most relevant content in Elasticsearch.