Four agents coordinate interviews, keep every candidate informed, run each new starter's onboarding, answer policy questions and analyse anonymous surveys. They never rank candidates, score employees or read emotions, and they work within the employment law of each country you operate in.
Four agents, coordinated by one that reports to your HR lead.
Follows the hiring pipeline every day and onboarding every week, and escalates anything sensitive to a person at once. Reports to your HR lead.
Schedules interviews, keeps every candidate informed of the next step and the pipeline up to date. Hiring managers read every application and decide.
Prepares each new starter's first weeks: documents for their country, accounts requested, schedule, introductions, reminders.
Answers policy questions from your documents, saying it is an AI, and analyses anonymous surveys by team, never by person.
Rank or score candidates, predict who will leave, monitor employees' messages or behaviour, infer emotions from voice, video or typing. Under the EU AI Act the first three are high-risk uses, and inferring emotions at work has been prohibited since February 2025.
In several countries a works council must be informed, consulted or must agree before such a tool arrives: France, Germany, the Netherlands and Italy among them. The launch gives you what they need: what each agent does, what it can reach, what it never decides.
The team works from a reference of employment and data-protection rules for more than thirty jurisdictions in Europe, the Americas, Asia-Pacific and the Gulf, each rule with its official source. It applies the rules of the country where each person works or applies.
Workday (read)
Greenhouse (read, notes)
Google Workspace, Microsoft 365
Your documents, Confluence, Notion, Google Drive, Microsoft OneDrive
Slack, Microsoft Teams
Each agent gets only the access its role needs, granted by you and listed in the access register. Another system can be connected through its API or an MCP server.
Each agent has its own SPIFFE identity and signing key. Every action records which agent acted, under which rule, and for whom.
Approvals where you want them. Autonomy widens only on measured results and steps back by itself when results slip.
Agents reach only what you grant. One switch stops an agent or the whole team, and the stop is on the record. 32 governance packs, including the EU AI Act and GDPR, apply your rules on your own model keys.
Which HR work the team takes on, in which countries, and the policies it learns from, reviewed by you.
A charter per agent with its limits, and your tools connected with least access.
Real work, every action approved by a person, until the team earns autonomy.
At the autonomy it earned, measured against where you started.
Three to six weeks from scope to go-live. How a team launch works · What you keep control of · Other teams