Gi Admin Bot: People Analytics in the Backoffice
Gi Admin Bot is the conversational analytics assistant inside the GFoundry backoffice. Admins, managers, and CSMs ask questions in natural language and get back insights on talent, performance, engagement, learning, and recognition. The AI provider never sees employee names, emails, or manager information.
What is Gi Admin Bot?
Gi Admin Bot is a backoffice assistant for administrators, managers, and customer success teams. You ask questions in plain English or Portuguese about your people, teams, and activity, and the bot replies with structured insights, tables, and trends drawn from your own GFoundry data.
It is the admin counterpart to Gi Bot: where Gi Bot helps employees in the front-end with company knowledge and platform guidance, Gi Admin Bot helps the people who run the platform make sense of what is happening inside it.
Who is it for?
HR managers and team leaders: understand team composition, performance gaps, training needs, and well-being signals.
People analytics and CSMs: explore trends, build ad-hoc reports, and identify at-risk groups.
Executives: get strategic answers on engagement, recognition culture, and talent profiles without writing a query.
What can I ask?
Gi Admin Bot supports several question categories. The examples below are illustrative, not exhaustive.
Performance and evaluation cycles
"Who were the top performers in the last cycle based on their final scores?"
"Which teams have the lowest average goal completion rates?"
"Who has not had an evaluation in the last 6 months?"
Individual development and growth
"List all employees with active Individual Development Plans and their priorities."
"Who has not engaged with their development plan in the last quarter?"
People profiles and team composition
"What is the archetype breakdown of my Sales team?"
"Show me the people profiles across all departments."
"Which teams are over-indexed on Overstretched Achievers?"
Churn signals and disconnection risk
"Who are the high-risk disconnected users this month?"
"Which employees have been inactive on the platform in the last 30 days?"
"Show teams with low well-being signals."
Learning and training
"Which training programs have the highest completion rates?"
"Who enrolled in the leadership program but did not finish it?"
"List employees who could benefit from courses on time management."
Recognition and culture
"What badges are given most often in the organisation?"
"Which teams are most active in peer recognition?"
"Are there isolated groups with little recognition activity?"
Organisational directory
"Find all employees in Finance with a Manager role."
"Who works in the Lisbon office?"
"List all team leaders by department."
How is it different from Gi Bot?
Audience: Gi Admin Bot is for admins and managers; Gi Bot is for every employee.
Data: Gi Admin Bot answers from your live people and activity data; Gi Bot answers from published content and uploaded documents.
Output: Gi Admin Bot returns analytics, tables, and Excel exports; Gi Bot returns content guidance and policy answers.
Scope: Gi Admin Bot looks at teams, segments, and trends; Gi Bot focuses on the individual asking.
Data security and privacy
What the AI provider sees
When you ask Gi Admin Bot a question, the service constructs a prompt to send to an external AI provider (OpenAI API, with a contractual no-training clause). Before the prompt leaves your tenant, every employee reference is replaced by a pseudonymous internal identifier. The AI provider receives those identifiers together with the structured attributes relevant to the question, for example performance scores, completion rates, or archetype labels. It does not receive employee names, email addresses, manager names, or free-text notes about employees.
Pseudonymisation is not anonymisation. The mapping from identifier to person is kept inside your tenant, which means GDPR continues to apply to this processing. Your DPO can exercise data subject rights (access, erasure, restriction) on the underlying records through the standard backoffice tools.
Where the data lives
All employee data used by Gi Admin Bot stays in the European Union. The application, the database, and the analytics layer are all hosted in EU regions.
Tenant isolation
Every query is filtered by your tenant identifier at the data layer before any value reaches the AI provider. A request issued from one tenant cannot return rows belonging to another tenant, and the AI model has no mechanism to bridge across tenants.
Read-only by design
Gi Admin Bot can answer questions about your data. It cannot modify records, trigger workflows, or push data anywhere outside your tenant.
Excel exports
Excel exports are generated server-side, scoped to your tenant, and never sent to the AI provider. Names appear in the file because the file is meant for you. Exports are stored encrypted and removed after a short retention window configured for your tenant.
Controls available to your DPO
Data Processing Agreement: a DPA covering Gi Admin Bot, including the list of sub-processors, is available on request.
No-training contract: the AI provider is contractually prevented from using your prompts or responses to train its models.
Conversation retention: prompts, responses, and exports follow the retention windows configured for your tenant.
Sub-processor changes: GFoundry notifies tenants in advance of any change to the list of AI sub-processors.
What it does not do
It does not change data. Gi Admin Bot is read-only.
It does not cross tenants. Each admin only sees their own organisation's data.
It does not give prescriptions. The bot surfaces facts and patterns; people decisions stay with the people who own them.
It does not expose names to the model. Real names appear only in the answer or export presented to you.
Tips for better answers
Be specific. "Top 10 performers in Sales last cycle" beats "show me performance".
Mention the segment. Add the team, department, time window, or role to scope the query.
Ask for an export. If you expect more than a few dozen rows, ask the bot to send the result as Excel.
Follow up naturally. The bot keeps context, so "and the Marketing team?" works after a previous question.