Data Analyst Agent: People Analytics in Natural Language
Ask a question in your own words in the backoffice and get people analytics answers, tables, charts and Excel exports from your own GFoundry data. Employee names are replaced by pseudonymous identifiers before the data reaches the AI model.
What it does
The Data Analyst Agent is a backoffice assistant. You ask questions in natural language about your people, teams and activity, and it replies with structured answers, tables, charts and Excel exports drawn from your own GFoundry data. It answers in the language you write in.
Open it with Ask AI at the top of the backoffice. The button is shown to administrators and to users who were given access to the assistant.
Key capabilities
Ask in natural language: no SQL, no filters, no dashboards to configure.
Evaluations, development plans, training, recognition and activity: covers the people data your organisation has in GFoundry.
Exports to Excel: files generated on request, with a download link.
Pinned charts: when the assistant draws a chart, you can pin it so it stays under Pinned charts after the conversation ends.
Pseudonymisation of names: the model works with identifiers, and names are put back only in the answer you see.
What can each user see?
A full administrator can ask about the whole organisation. Other users only get answers about the modules their backoffice permissions cover and about the people they have access to. If a module or a type of data does not exist in your organisation, the assistant says so instead of inventing an answer.
Examples of what to ask
The examples below are illustrative. What the assistant can answer depends on the modules and data your organisation uses.
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?" (only where behavioural archetypes are computed for your organisation)
"Which teams are over-indexed on Overstretched Achievers?"
Engagement and activity
"Which employees have been inactive on the platform in the last 30 days?"
"How many people accessed the platform this week?"
Learning and training
"Compliance training completions by team?"
"Which training programs have the highest completion rates?"
"Who enrolled in the leadership program but did not finish it?"
Recognition and culture
"What badges are given most often in the organisation?"
"Which teams are most active in peer recognition?"
Organisational directory
"Find all employees in Finance with a Manager role."
"List all team leaders by department."
How it relates to Gi
Audience: the Data Analyst Agent is for backoffice users; Gi, the conversational assistant, is for employees on the platform.
Data: the Data Analyst Agent answers from your people and activity data; Gi answers from published content and uploaded documents.
Output: the Data Analyst Agent returns analytics, tables, charts and Excel exports; Gi returns content guidance and policy answers.
Data security and privacy
What the AI provider sees
When you ask a question, the service sends a prompt to an external AI provider (OpenAI). Employee references in the data are replaced by pseudonymous identifiers, and columns such as names, emails, manager names and usernames cannot be selected for a chat answer. The provider receives those identifiers together with the attributes relevant to the question, for example scores, completion rates or archetype labels.
Two things do reach the provider as written:
Your own question. If you type a person's name or email, that text is sent. The assistant then looks the person up inside GFoundry and works with their identifier.
Business text in the data. Fields such as goal titles, goal descriptions and evaluation comments can be part of an answer, so avoid asking for them when they hold sensitive notes.
Pseudonymisation is not anonymisation. The mapping from identifier to person stays inside GFoundry, so GDPR continues to apply.
Strict tenant isolation
Every query is scoped to your own organisation. A request from one organisation cannot return rows belonging to another.
Read-only on your people data
The assistant can only read your people data. It cannot change evaluations, users or any other record. The only things it saves are your conversations, the Excel files you ask for and the charts you pin.
Excel exports
Excel exports are generated inside GFoundry, scoped to your organisation, and are not sent to the AI provider. Names appear in the file because the file is meant for you. The download link is valid for 24 hours and then expires.
Contractual documents
The Data Processing Agreement, including the list of sub-processors, is available on request.
What it does not do
It does not change your people data. It only reads it.
It does not cross organisations. Each user only sees their own organisation's data, within their permissions.
It does not make decisions. The agent surfaces facts and patterns; people decisions stay with the people who own them.
It can make mistakes. Check important figures before you use them.
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 question.
Ask for an export. If you expect more than a few dozen rows, ask for an Excel.
Follow up naturally. The agent keeps the context of the conversation, so "and the Marketing team?" works after a previous question.