SAP × AIForward Deployed Engineer
ENEnglish
中文中EnglishEN한국어KO日本語JA
Talk about your project
WorkServicesOpen SourceAboutContact
中ENKOJA
Public source · 2026Back to work

HR Workstation

An AI workspace for HR workflows

A modular workspace for recruiters, HRBPs, SSC, C&B and HR directors. Plugin agents turn resume screening, JDs, interview guides, offers, automation monitoring and notifications into one traceable pipeline.

hand-in-hcm-workstationNext.jsTypeScriptPrismaTailwindAgent pluginsPublic source · actively maintained
GitHub repositoryFour-language READMEOpen an issue
HR workstation UI to agent plugins, Prisma data and notification channelsHR WORKSTATION / AGENTSLIVEHR USER5 role viewsrecruit → HRDNEXT.JS UIWorkspacetasks + statusAGENT LAYERPlugins + LLMscreening · JD · offerDATAPrisma + SQLiteroster importJOBSState machinePENDING → DONENOTIFYHubWeCom · SMTPRESULTSJSONaudit trail4 CORE MODULESROLE-BASED VIEWS

The problem

High-frequency HR work is scattered across email, spreadsheets, ATS and chat. Repetition is high, status is invisible, and failed automations are hard to trace.

Approach

  • Use a microkernel plus plugin agents so new scenarios plug in without cramming all logic into one page.
  • Run long tasks in a background executor with a PENDING → RUNNING → SUCCESS / FAILED state machine and visible progress.
  • Unify WeCom, Feishu, DingTalk webhooks and SMTP into a notification hub so completion and failure are traceable.

What is inside

  • Recruitment: batch resume scoring, JD generation, STAR interview guides and offer assembly.
  • Automation hub: state machine, progress, duration, failure diagnosis and structured JSON drill-down.
  • Notifications and data: WeCom/Feishu/DingTalk/SMTP, Excel/CSV roster import and external API sync.
  • Role-based HR views with colour-coded automated, high-efficiency and planned capabilities.

Live system interface & core modules

Screenshots from the live deployment of HR Workstation, covering candidate screening, automation monitoring, notification hub and data ingestion:

HR Workstation Dashboard
Workspace OverviewRole-based views & module navigation
Talent Acquisition Studio
Talent Acquisition StudioResume batch scoring & STAR interview guide generation
Automation Monitor
Automation Execution MonitorReal-time state machine, duration & structured JSON inspection
Notification Hub
Notification HubEnterprise webhook bots & SMTP email dispatch audit
Data Hub & Ingestion
Data Hub & IngestionExcel/CSV roster parsing & external HCM API sync

Deploy it yourself

terminal / quickstarthand-in-hcm-workstation

Prerequisites

Node.js 20+ and local SQLite are enough; prepare an OpenAI-compatible API config if you want model calls.

  1. Clone, run npm install, copy .env and configure the database plus optional model API.
  2. Run npm run seed for seed data, then npm run dev to open the local workspace.
  3. Walk through a recruitment or automation task, verify notifications and state changes, then connect real data.

Keep demo data separate from real employee data, and confirm privacy and masking requirements before using personal information.

Next projectSAP ABAP MCP — S/4HANA development inside an AI conversation
Next step

A system to ship, or a workflow to improve?

Tell me the current state, the outcome you need and your timeline. I reply within 24–48 hours and start with whether it is worth doing — and the fastest path.

Send a private messageEmail directly