The platform

One core.
Eight portals.

Hiring, HR, operations and finance. One source of truth.

LinkMatch is not a recruiting tool with add-ons. It is one core that carries eight portals, an explainable match engine, AI agents and 60+ automated routines. All of them read and write the same data.

01  /  PortalsEveryone has their own way in
01 / 08 · Staff

The team’s workspace

For

Recruiters, coordinators, account managers, HR, finance and management. Each sees the screens their permissions open.

Inside
RolesCandidatesMatchesInterviewsClientsEmployeesBillingReportsNoa
02 / 08 · Candidate

The candidate’s personal portal

For

Anyone looking for their next role, or being looked for by it. Built for the phone first.

Inside
MatchesApplicationsInterviewsDocumentsMessagesReferralsOnboardingMaya
03 / 08 · Client

The hiring company, without the email back-and-forth

For

Hiring managers and HR on the requesting side. They approve, interview and decide from inside the portal.

Inside
RolesCandidatesInterviewsEmployeesDocumentsBillingAnalytics
04 / 08 · Employee

Everything an employee needs, in one place

For

Whoever was hired, from day one. The profile built during hiring carries on with them.

Inside
ContractPayslipsTimesheetsLeaveDocumentsGrowthBonusesReferrals
05 / 08 · Manager

My team, at a glance

For

Team leads and direct managers. Only what concerns their team, without the noise.

Inside
TeamCandidatesInterviewsApprovalsAnalytics
06 / 08 · Vendor

Sub-vendors, in the same process

For

Agencies and vendors who submit candidates. Every submission is recorded, and candidate ownership is clear.

Inside
RolesSubmissionsPoolInvoicesFinance
07 / 08 · Referrer

The network that brings good people

For

Anyone who knows someone good. They refer, follow along, and earn a bonus when the placement holds.

Inside
ReferralsTrackingEarningsLeaderboardIdentity check
08 / 08 · Admin

Platform administration

For

System administrators. Organizations, the shared pool, monitoring and control, with a separate audit trail.

Inside
OrganizationsShared poolPermissionsMonitoringAudit trail
Explainable by design
02  /  Match engineA score without a reason is a guess

Eight dimensions. One clear reason.

Every candidate is scored against every role on eight dimensions. Each organization sets its own weights and knockout conditions, and the engine writes an explanation a non-recruiter can follow.

Technical and skillsExperienceEducationLocationPayClearanceLanguagesAvailability
  • Weights and knockouts per organization, and per role where needed
  • Semantic search: finds people by meaning, not only by keywords
  • A rerank of the leaders, with a deeper read of the profile
  • Proactive rediscovery of strong candidates who nearly made it before
03  /  AI agents20+ capabilities, inside the work

AI that works inside the process, not beside it.

Two agents with a name and a job, and a row of capabilities working in the background. Anthropic’s Claude is the primary model, with OpenAI as fallback.

Agent · Staff

Noa. The hiring team’s agent.

She answers, searches and acts, with 14 families of tools: candidates, roles, interviews, clients, HR, finance, analytics and more. Every action is checked against the user’s permissions.

Agent · Candidates

Maya. The candidates’ assistant.

She walks candidates through the career page and the portal: answers questions about roles, explains the process and guides them to apply. In Hebrew and English.

20+ · Capabilities

What the AI actually does

CV parsingExplained matchingRerankingSemantic searchProactive rediscoveryRole completenessSkill extractionCandidate analysisScorecardsInterview copilotCall summaryMeeting summaryJourney insightsMarket pay, sourcedPurchase-order parsingAbsence-document parsingBilling-basis parsingClient summaryCash-flow summaryNoa, the team’s agentMaya, the candidates’ assistant
Limits · Guardrails

AI with limits

  • Identifying details are masked before reaching the model
  • Protection against prompt injection
  • A usage quota and a daily spend cap per organization
Trust and security
04  /  AutomationWhat needs no person waits for no person

60+
routines that run without being asked.

Reminders, syncs, checks and processing that run on a fixed schedule. What stalls gets a nudge, and what is about to expire gets an alert.

05  /  ScopeFour worlds on one database

What enters at hiring does not vanish on the way to the invoice.

Recruiting

  • Roles and publishing channels
  • Candidate pool and sources
  • Explained matching
  • Interviews and scorecards
  • Offers and signatures
  • Career page and job feed

HR

  • Onboarding and offboarding
  • Contracts and documents
  • Absences and reserve duty
  • Training and performance
  • Pulse and retention
  • Growth and mentoring

Operations

  • Security clearance
  • Safety and work accidents
  • Attendance and timesheets
  • Hearings and terminations
  • Team tasks and SLA
  • Messages and reminders

Finance

  • Clients and framework agreements
  • Purchase orders
  • Billing bases and monthly billing
  • Payment demands and collections
  • Vendor payments
  • Commissions and bonuses
06  /  Under the hoodMeasured in the code, not in a deck
340+data entities in the data model
1,400+API endpoints, documented in OpenAPI 3.1
30+predefined user roles
230+separate, action-level permissions

An architecture built for organizations

A PostgreSQL database with vector search, a job queue for background processing, and tenant isolation enforced at row level too.

Hebrew and English, right to left

The system was built right-to-left from the start: screens, emails, documents and signatures. The AI’s explanations are written in natural Hebrew as well.

SaaS in IsraelOn-premisesOpenAPI 3.1Signed webhooks
Common ground

It is easier to see than to read.

Thirty minutes on the live system, with a real role of yours.