Gi Bot is GFoundry's company assistant for employees and managers. It answers questions about company knowledge, policies, contacts, training, and platform guidance using uploaded documents and public platform content, and adapts responses to each employee profile. Admins manage its source documents and review chat sessions from the backoffice. The AI provider never receives employee names or emails.

Gi Bot is a company assistant that helps employees find information quickly and in the right language. It can answer questions about company knowledge, policies, contacts, training material, and platform guidance.

It uses the information available in your GFoundry environment to return answers that match the question and the context.

Employees: Gi Bot can help employees find information about the company mission, values, career progression, compliance policies, benefits, and other common internal questions.

Managers: Gi Bot can also support managers by helping them locate information they may need for talent management, internal mobility, and other people-related decisions.

Gi Bot can use two sources of knowledge.

Documents are organized by domain so questions are routed to the most relevant knowledge area:

Gi Bot can adjust its response based on the employee profile available to the system. This allows it to vary the tone and suggestions according to the user's stage in the company.

For example, if a new employee asks about career growth, Gi Bot can suggest onboarding, training, and integration steps. If a long-tenured employee asks the same question, Gi Bot can focus on practical actions, well-being resources, or internal mobility opportunities.

Personalisation uses non-identifying attributes (such as tenure band or role family). The AI provider never receives the employee's name or email.

If Gi Bot does not find enough information, it returns that gap instead of inventing an answer. This helps identify missing content in the knowledge base so you can update the available documents or public content.

Gi Bot checks the relevant knowledge areas for the question, combines the results into a single answer, and replies in the same language used in the prompt.

In practice, this means users can ask one question and receive a response based on the appropriate company knowledge, with the language and context adjusted to them when available.

Conversations with Gi Bot are stored inside the platform to improve answer quality and to identify gaps in the knowledge base. Administrators can review individual chat sessions in the backoffice as a content-quality tool, not as a surveillance tool. Employees should be made aware of this through a short notice presented at the chat entry point.

The AI provider (OpenAI API, under a contractual no-training clause) receives the user's question, the relevant document excerpts, and a pseudonymous identifier. It does not receive the user's name, email, or manager name. The provider is contractually prevented from using prompts or responses to train its models.

Group-based document visibility is enforced at the retrieval step. A document that is restricted to a specific group is never used to answer a question from a user outside that group, even if the document would otherwise be the best match.

All Gi Bot data, including conversations and the document corpus, stays inside the European Union.

Chat history retention is configured per tenant; clients can request the retention window they want. Employees can request deletion of their chat history through their administrator. The full Data Processing Agreement, including the list of sub-processors, is available on request.

Admins have a dedicated area in the backoffice to keep Gi Bot's source content up to date and to monitor how people are interacting with it.

Create a new document with New Document, then give it a name, upload a file, choose a visibility, and assign a document category. Documents can be set to public or private.

Public documents are visible to all users. Private documents are still used by the bot for AI generation, but users cannot see them in the help center.

You can also segment a document by groups. If no groups are selected, the bot can use that document for any user.

In the document list, you can search, sort, open View Details, and delete a document. In document details, you can review the file, category, visibility, group segmentation, status, and available actions.

The chat sessions area lists conversations with the first user message, the date, and the number of interactions. From there, open View Details to read the full chat history.

Inside a session, each exchange shows the user's message and Gi Bot's response. If a session has more than one page of messages, you can use pagination to move through it.

If there is no chat history for a session, the page shows that no history is available.

Each document has a history section that records changes such as file updates, category changes, status updates, and group segmentation changes. This lets you see how the document used by the bot has changed over time.