HIRE — 01

Khoji – AI Candidate Sourcing Agent

Find, Rank & Engage Top Talent Automatically

Khoji is an AI recruiter that sources, ranks, and engages candidates across the web, delivering faster and smarter AI candidate sourcing for modern recruiting teams.

Live demo

Khoji at work

Sourcing

A demonstration of the Khoji agent, playing in four acts on a loop. Use the arrow keys to step between acts, space to pause, Home to return to the first act.

The request: “Hey Khoji, find me an AWS Architect from a product company in Pune, India, and a Product Specialist with 4+ years in AI/ML from Silicon Valley.”

The same request is also shown in Hindi, Spanish, Tamil, Arabic, Malay — it can be written in any language.

The agent answered: “Sure. Anything else you need?”

The requester then added: “Yes — I forgot a Store Assistant in Singapore, full-time, 5+ years, and a Production Engineer with 2+ years in Saudi Arabia.”

The agent answered: “Got it — four roles, four markets. Give me a moment.”

It then searched 1,269 profiles across 4 markets using six sources, and returned 12 candidates.

Pune, India — Cloud Architecture. 3 of 468 profiles read.

  • Ananya Deshpande, Senior Cloud Architect, Pune, MH. Vital score 9.4 out of 10. Available now. Ran the AWS platform at a product company, at this scale.
  • Imran Shaikh, AWS Solutions Architect, Pune, MH. Vital score 9.1 out of 10. 30-day notice. Cost and reliability specialist, services background.
  • Jasleen Kaur, Cloud Platform Architect, Pune, MH. Vital score 8.8 out of 10. Passive — open to hear. Built the platform the others build on, not looking.

Silicon Valley, US — AI/ML Product. 3 of 391 profiles read.

  • Elena Vasquez, AI Product Specialist, Palo Alto, CA. Vital score 9.2 out of 10. Available now. Took two ML products from nothing to shipped.
  • Daniel Okafor, Product Specialist, ML Platform, San Jose, CA. Vital score 8.9 out of 10. 30-day notice. Platform-side depth, lighter on discovery.
  • Yuki Tanaka, Technical Product Specialist, AI, Mountain View, CA. Vital score 8.5 out of 10. Passive — open to hear. Exactly the 4-year bar, and moving quickly through it.

Singapore — Retail. 3 of 236 profiles read.

  • Nur Aisyah, Senior Store Assistant, Singapore. Vital score 8.7 out of 10. Available now — full time. Seven years on a flagship floor, full-time from day one.
  • Marcus Ong, Store Assistant — Flagship, Singapore. Vital score 8.3 out of 10. 2-week notice. Steady on the floor, less stockroom ownership.
  • Devi Krishnan, Retail Store Assistant, Singapore. Vital score 8.0 out of 10. Available now — full time. Meets the 5-year bar, strongest of the three on service.

Saudi Arabia — Production. 3 of 174 profiles read.

  • Faisal Al-Otaibi, Production Engineer, Jubail, SA. Vital score 8.6 out of 10. Available now. Petrochemical line experience, well past the 2-year bar.
  • Noura Al-Qahtani, Process & Production Engineer, Riyadh, SA. Vital score 8.4 out of 10. 60-day notice. Process depth, and the clearest documentation in the group.
  • Abdulrahman Nasser, Manufacturing Engineer, Dammam, SA. Vital score 8.1 out of 10. Available now. Fast on the line, still building process ownership.

Top match: Ananya Deshpande, vital score 9.4, scoring AWS depth 96, Architecture 94, Reliability 90, Communication 92.

Lifecycle phase

Hire

Data sources

50+ platforms

Indexing speed

10K profiles/min

Match freshness

Real-time updates

> Phase: Hire · Sources: 50+ platforms · Pool: 2.4M profiles · Sync: real-time · Dedup: 99.8%

What it does

What Khoji does

  • 01

    Requests in plain language

    Describe the role the way you would to a colleague, in any of six languages. Khoji reads it into a structured search instead of asking you to fill in a form.

  • 02

    Parallel search across six source types

    Job boards, professional networks, regional boards, ATS connectors, alumni networks and referral graphs are worked at the same time, not one after another.

  • 03

    Regional sub-agents

    A sub-agent runs each market's leg of the search, so one brief can span Pune and Silicon Valley without being flattened into a single market.

  • 04

    Ranked against the brief

    Every candidate is scored against what you asked for rather than against a keyword list, and de-duplicated across sources so nobody appears twice.

  • 05

    A vital score with the reasoning shown

    Each score arrives with the factors behind it, so a recruiter can see why someone ranked where they did, and disagree.

How it works

How Khoji works

  1. 01

    Input

    A hiring request in plain language, in any of six languages.

  2. 02

    Processing

    Regional sub-agents search six source types in parallel, then de-duplicate and rank what comes back.

  3. 03

    Output

    A ranked shortlist, each candidate with a vital score and the reasoning behind it.

  4. 04

    Human approval

    A recruiter reviews the ranking and decides who moves on to screening.

Inputs and outputs

What goes in, what comes out

Takes in

  • A hiring request or job brief
  • Your connected sources and internal talent pools
  • Referrals

Produces

  • A ranked candidate list
  • A vital score with reasoning for each person
  • Passive-talent matches

Hands off to

Human control

Where a person decides

A person approves

  • Which candidates move on to screening
  • Any change to the ranking criteria

Runs on its own

  • Searching and de-duplicating across sources
  • Scoring every candidate against the brief
  • Refreshing results as new profiles appear

Works with

What Khoji connects to

  • Job boards

    Job board APIs and regional job boards, searched alongside everything else.

  • Professional networks

    Global professional networks, for the people who are not actively applying.

  • ATS connectors

    Applicant tracking systems, read as one more source.

  • Alumni networks

    Alumni networks, read as a source in their own right.

  • Referral graph

    Referral routing, so a referral is ranked next to everyone else.

  • Internal talent pools

    Your own pools and past candidates, kept current and de-duplicated.

FAQ

Khoji: frequently asked questions

What is Khoji?

Khoji is an AI candidate sourcing agent that finds, ranks, and engages talent across the web. It acts as an AI recruiter designed to accelerate and improve the speed and quality of candidate sourcing for modern recruiting teams.

What does Khoji do?

Khoji searches multiple sources to identify relevant candidates and ranks them on job fit with a vital score, showing the reasoning behind each one. It turns a job brief into a qualified shortlist faster than traditional sourcing methods.

How does Khoji help recruiting teams?

Khoji cuts manual sourcing time and surfaces passive talent at scale. Each candidate gets a vital score showing role fit and likelihood to join, so recruiters can focus on high-value conversations instead of searching.

Is Khoji a standalone tool or part of a larger system?

Khoji is one of the specialized AI agents within PilatusOS, the agentic talent management suite. It works independently for sourcing and also connects seamlessly with other agents such as Screener, Interview, and Orchestrator for end-to-end hiring workflows.

Which sources does Khoji use to find candidates?

Khoji sources talent from a wide range of online platforms and professional networks across the web, enabling access to both active and passive candidates beyond traditional job boards.

Can Khoji engage candidates automatically?

Khoji doesn’t contact candidates itself. It finds and ranks them, giving each a vital score with the reasoning behind it. Your recruiter uses that ranking to decide who moves on to screening and engagement.

How does Khoji fit into the overall hiring process?

Khoji handles the top of the funnel — discovering the perfect candidates. Once shortlisted, candidates can flow into other PilatusOS agents for screening, interviewing, scheduling, and beyond, creating a continuous AI-powered hiring workflow.

What does getting started with Khoji look like?

Teams typically begin with a demo or discovery call to define role requirements. Khoji is then configured for specific hiring needs, after which it starts sourcing and ranking candidates. Support continues with optimization and scaling as hiring volume grows.

How much does Khoji cost?

Pricing for Khoji is subjective and depends on the number of users or employees, along with your sourcing volume. After understanding your needs, we share a clear estimate for this AI candidate sourcing tool within our AI hiring platform.

How long does it take to implement Khoji?

Khoji is designed as a ready-to-use solution and can be deployed quickly when adopted as a standalone product. When implemented as part of the full suite, setup remains streamlined. However, if integration with your existing HR or ATS systems is required, the timeline may extend based on the complexity of those connections and data migration needs.

See Khoji in your own workflow

Tell us about your hiring volume and HRIS stack. We will tailor a walkthrough of PilatusOS to your workflow.