We won the Open Agentic AI Innovation Award at the first AAIF Technical Excellence Awards.We won the Open Agentic AI Innovation Award Read why

AI agents for HR, from hiring to onboarding

Agents for the admin around every hire

Agents screen applications, answer policy questions and run onboarding steps, while a person makes every decision about a candidate or employee.

Book a free consultation How we build agents
people-desk

  1. HR partnerYour team

    A new analyst starts on Monday. Can the onboarding agent get everything ready?

  2. Onboarding agentAgent

    1. hris.get_employee role, team and start date
    2. docs.check signed contract and tax forms
    3. it.request_access laptop and accounts for the role

    The contract and forms are in. The role asks for access to the finance system, so it needs a sign-off.

    Needs a personAccess to the finance systemNew analyst starting on Monday
    Approved by HR manager

  3. Onboarding agentAgent

    1. calendar.schedule first week meetings

    Accounts are requested and the first week is in the calendar. The welcome email goes out on Friday.

Example data. An agent at work in a team channel, with a person approving the step you choose.
Mixam: conversion to a final sale from about 20% to about 40%
Where agents help

Hiring and onboarding run on admin.

Agents take that admin over and leave every decision about people to your team.

  1. 01

    Where it stallsApplications pile up faster than recruiters can read them.

    What we do An agent reads each application against the role's criteria and prepares a summary. A recruiter decides.

  2. 02

    Where it stallsHR answers the same policy questions every week.

    What we do An agent answers employees from your handbook and policies and hands sensitive cases to HR.

  3. 03

    Where it stallsOnboarding depends on someone chasing every step.

    What we do Agents collect documents, request accounts and equipment, and tell HR what is still missing.

What we build

What we build for HR teams

Whatever comes in, every project is built from the same parts below, set up for your files and your systems.

HR work we take on

  • Application screening
  • Interview scheduling
  • Onboarding
  • Policy questions
  • Benefits questions
  • Leave requests
  • Employee records
  • Offboarding

How we build it

  • Application screening with a recruiter deciding

    Each application read against the role's criteria and summarised, with the decision left to a recruiter.

  • HR policy and benefits assistant

    Answers from your handbook and policies, limited to what each employee is allowed to see.

  • HR system, calendar and IT connections

    Agents read and update your HR system, calendars and IT requests with the permissions you set.

  • Personal data access and audit trail

    Access to personal data limited by role, and every step on a candidate or employee logged.

Not seeing your case? Bring the HR request your team answers most and we start from that.

Tell us about your workflow
How we build agents

Agents that work as part of your team

They work in the tools your team already uses, take on whole tasks and stop for a person where you decide.

  1. Routines: agents that start on a schedule, on new GitHub issues or on an API delivery.
  2. Connected systems: GitHub, Linear, Notion, Slack, Jira and other tools an agent may call, each connected with its own sign-in.
  3. Approvals log: each action that waited for a person, with who asked, who decided and when.
Routines: agents that start on a schedule, on new GitHub issues or on an API delivery.
Connected systems: GitHub, Linear, Notion, Slack, Jira and other tools an agent may call, each connected with its own sign-in.
Approvals log: each action that waited for a person, with who asked, who decided and when.

Screens from the workspace our agents run in, with example data.

Industries

Industries we build agents for

Each page shows where agents fit in that industry and what we have built there.

All industries
Engineering in the open

We help build what agentic AI runs on

Open standards, open-source tooling and published research, all public, so you can check our engineering before you hire us.

Shaping agentic AI

Agentic AI Foundation

Vstorm was the first agentic AI engineering company to join the Agentic AI Foundation and received its 2026 Open Agentic AI Innovation Award.

Read the announcement

Open source

We build open-source agent tooling that other engineering teams install

10M+ PyPI downloads
4,000+ GitHub stars
33 public repositories

Framework contributors

When the framework breaks, we fix it at the source

We maintain our own open-source agent framework and contribute fixes to the frameworks our agents run on, through official partnerships with their teams. Breaking changes reach us before they reach your codebase.

Research

Our engineers and PhDs publish peer-reviewed research

Peer-reviewed papers on agent architectures, evaluation and AI security, and an open benchmark anyone can rerun against our results.

Track record

Frontier AI teams now build on what we shipped first

Our client agents were in production before most of today's agent frameworks had a stable release. You get a team that already knows what breaks between a promising demo and a system people rely on every day.

Case studies
All case studies
Engagement models

Ways to start

Each path starts with a free call with a founder or senior AI engineer. A build goes ahead only after its Proof of Value meets the agreed threshold.

Start with one workflow

We map one workflow with your experts and agree a success threshold before any build.

Best whenYou want the success test agreed before you commit to a build.

Book a free consultation
  1. Process redesign and build Best whenYou want one team accountable for the outcome.
FAQ

Questions about AI agents for HR

What are AI agents for HR? +
AI agents for HR are software agents that take over the admin in hiring and people operations: reading applications, answering policy questions, collecting onboarding documents and requesting accounts. They work in your HR system, email and chat with the access you give them. Decisions about candidates and employees stay with your HR team and managers.
Where do AI agents help first in HR and recruitment? +
Start with work that repeats and follows written rules: policy and benefits questions from employees, onboarding checklists, or a first read of applications against a role's criteria. We go through the process with your HR lead, pick one task, agree a success threshold and test the agent on your own past cases before it meets an employee or candidate.
Have you built AI agents for HR teams? +
There is no published case for an HR workflow yet. Three builds come closest. For ARIJ Network, which serves 22 countries, one English and Arabic agent supports journalist training. For STCC, a guideline-executing agent reached 98% on an open 50-scenario clinical benchmark, where a raw LLM scored 42%. For a US health insurer, a specialist still decides every claim the agents prepare.
How do you keep AI in recruitment under control? +
Hiring is a high-risk use under the EU AI Act, so the agent prepares and a recruiter decides on every candidate. Screening criteria are written down with your team and tested on past applications before launch. Access to personal data is limited by role, and every summary and decision is logged so you can show how it was made.
How do you know it works before the full build? +
We agree a success threshold with your team before the build and test the agent on your own cases in a Proof of Value. It measures accuracy and running costs, and the build goes ahead only when the threshold is met. Corrections from your team go back into the test set, so every later version is checked against them.
Who owns the system, and which models does it run on? +
You own the code, prompts, evaluation sets and rules by contract. The agents run in your environment on hosted or open-weight models. The model sits behind an interface in code, so you can change it when accuracy, speed or your hosting rules change, without rebuilding the agent.
Start with one workflow

Test one workflow on your own data

A Proof of Value shows accuracy and running costs before the full build.

Book a free consultationRead case studies