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 candidate screening with recruiters deciding

Every application read against the role you defined

An agent reads each CV against the criteria you set for the role and shows the evidence for every match, and a recruiter makes every decision.

Book a free consultation How we build agents
hiring-desk

  1. RecruiterYour team

    The backend engineer role closed with a long list of applications. Can the screening agent go through them?

  2. Screening agentAgent

    1. ats.list_applications CVs and answers for the role
    2. criteria.get_role must-haves set by the team
    3. screening.match evidence for each criterion

    Every application has a summary with evidence for each criterion. The shortlist is ready for your review.

    Needs a personShortlist for first interviewsEach match explained with evidence
    Approved by Recruiter

  3. Scheduling agentAgent

    1. calendar.propose_slots interview times
    2. ats.update_stage shortlisted candidates

    Interview slots sent to the shortlist. No candidate was rejected automatically.

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

Recruiters skim long CV piles and good people get missed.

Agents read every application, and your recruiters make every hiring decision.

  1. 01

    Where it stallsSkimming under deadline misses strong candidates.

    What we do An agent reads every application in full and summarises the evidence for each criterion.

  2. 02

    Where it stallsScreening differs from one recruiter to the next.

    What we do The criteria are set once per role and applied the same way to every application.

  3. 03

    Where it stallsHiring rules ask you to explain each decision.

    What we do Each summary links to the lines in the CV behind it, and every decision is logged with who made it.

What we build

What we build for candidate screening

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

Roles we screen for

  • Engineering roles
  • Sales and account roles
  • Customer support
  • Operations and logistics
  • Finance and accounting
  • Healthcare staff
  • Seasonal and volume hiring
  • Internal moves

How we build it

  • CV reading with evidence

    Experience, skills and answers read from each application, each finding linked to its line.

  • Role criteria in tested rules

    Must-haves agreed with the hiring manager and checked against your past screening decisions.

  • ATS and calendar connections

    Summaries, stages and interview slots written to your ATS with the access rights you set.

  • Fairness and audit controls

    Protected traits kept out of screening, outcomes checked for bias and every decision logged.

Not seeing your case? Bring the role that floods your inbox and we start from that one.

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.

Where it runs

Teams and industries that use it

Each page shows where agents fit in that team or industry.

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

AI candidate screening, answered

What is AI candidate screening? +
AI candidate screening uses an agent to read each application against the criteria you set for a role. It summarises the evidence for every criterion, links each finding to the line in the CV and prepares a shortlist for a recruiter. The recruiter decides who moves on and who is turned down. The agent does the reading, and people make every hiring decision.
Which roles suit AI resume screening first? +
Roles with many applications and clear must-haves, such as engineering, support or operations roles you hire for often. Agree the criteria with the hiring manager, then test the agent on applications your recruiters have already screened. When its summaries match their judgement, use it on live roles. Senior or unusual roles can stay with recruiters from the start.
Have you built AI candidate screening before? +
We have no published case on candidate screening yet. The closest builds apply written criteria to long documents with a person deciding. For a US health insurer, claim processing was cut from 3 hours to 8 minutes, with a specialist still deciding. Our guideline-executing agent scored 98% on an open 50-scenario clinical benchmark, against 42% for a raw LLM.
How do you keep AI screening fair under the EU AI Act? +
The EU AI Act lists AI used to screen or rank job applicants as high-risk, so the system is built for human oversight and record keeping. Protected traits are kept out of the criteria, outcomes are checked for bias across groups, and no candidate is rejected without a recruiter. Every summary and decision is logged with its evidence and the person who decided.
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
From the blog

Reading on AI in recruitment

All articles
Strategy

Will AI eliminate Recruitment departments?

Explore the impact of AI on recruitment departments. Discover how AI is revolutionizing the hiring process and shaping the future of talent acquisition.
Agentic AI

Human in the loop for AI agents: when the agent needs permission to change the plan

Human in the loop for AI agents: who approves a change of plan, what evidence they need, how to stop approval fatigue and keep bookings matched to approvals.
Agentic AI

AI agent evaluation and reliability

Why a single-run score overstates an AI agent's reliability, what to measure instead (pass^k, traces, judges) and how to set a target you can defend.