Skip to main content

AI Agents

Phase 5 replaces the old landing page with an Agent Dashboard — a set of AI agents that watch for work in your HR data, propose what to do about it, and wait for you to approve.

Each agent proposes. You decide. Nothing an agent suggests reaches an employee, a candidate or a policy until someone approves it.

Who can use them

HR and Admin only

Every agent, the approval Inbox and the agent history are restricted to the HR and Admin roles. Employees and Managers do not see the Agent Dashboard and cannot approve agent proposals.

The dashboard

The dashboard is titled Your agent workforce. Each agent appears as a card showing whether it is switched on:

On the cardMeaning
Enabled chipThe agent is switched on and working
OpenOpens that agent's own page
Coming soon (greyed out)Built but not yet available to switch on

Agents are enabled individually, so you can start with one and add others later.

The three agents

Sourcing Agent

Watches for new candidates, reads each one against the job description, and proposes either interview or reject with its reasoning.

Once you approve a proposal, the agent sends the candidate notification automatically — you do not have to send it separately.

Onboarding Agent

Two jobs:

  • Chases onboarding. Monitors who has outstanding onboarding items and sends reminders, so HR is not manually following people up.
  • Recommends leave entitlements for new starters. Once you approve, the agent writes the entitlements to the employee record.
Pairs with the onboarding pages

This agent acts on the same items staff complete under My Profile → Onboarding. See Onboarding Operations for what HR configures, and Onboarding for the employee's side.

Policy Agent

Reviews your existing policies for gaps, internal conflicts and compliance concerns against Australian policy requirements, then gives recommendations.

This one is advisory — it reports findings for you to act on rather than editing policies itself. See Policy Management for where policies live.

The approval Inbox

Agent proposals collect in the Inbox. Each proposal shows what the agent found, what it wants to do, and its reasoning, with actions to approve or decline.

Working through the Inbox is the normal way to use the agents — you are reviewing a queue of decisions rather than hunting for work.

An agent's own page

Clicking Open on an agent card takes you to that agent's page, which is where its settings and its record live.

SectionWhat it holds
DutyWhat this agent is responsible for
Waiting on youIts proposals that need a decision — the same items that appear in the Inbox
Recent activityWhat the agent has done lately
Data it can seeThe scope of HR data this agent reads. Worth checking before enabling an agent
AutonomyWhether it must ask before acting — see below
Model routingWhich AI model handles its work
SettingsThe agent's own configuration

Turn off stops the agent from that page.

Check "Data it can see" first

Before you enable an agent, read Data it can see. It tells you which HR records that agent can read — the quickest way to satisfy yourself the access is appropriate before it starts working.

History and audit trail

Every agent keeps two records:

RecordWhat it holds
HistoryWhat the agent did and when
Event trailThe decisions taken on its proposals

Both are reached from the agent's own page, under Recent activity. Together they mean an agent's actions are always traceable back to who approved them — useful for compliance, and for understanding why an agent proposed something.

Autonomous mode

Each agent's page has an Autonomy setting. Left alone it reads Always needs your approval, which is the safe default.

Keep human approval on for now

Autonomous mode is in BETA. The recommendation is to leave every agent on Always needs your approval for the interim, so each action is reviewed before it reaches a candidate or an employee record. Turn autonomy on only once you have watched that agent's proposals for a while and trust its judgement.

Hera

Hera has not gone away. It remains the assistant you ask questions of — about your organisation, your employees and the HR tool itself — and answers from your real HR data.

The difference in Phase 5: Hera answers, agents act. Ask Hera a question; let an agent propose a change.

What powers all this

All agents run on Xagent. Phase 5 also moved the AI features that already existed onto Xagent:

FeatureWhere you use it
Job description creationRecruitment Management
Candidate reviewerCandidates Management
Policy summarizerPolicy Management

Those features work as before — the change is the engine behind them, not how you use them.

Related