HRAI Services

AI-Powered Internal HR Knowledge & Talent Search Chatbot

An internal chatbot that searches HR policy and talent profiles so recruiters find answers in seconds.

AI-Powered Internal HR Knowledge & Talent Search Chatbot

Key Details

ChallengeHR teams could not find policy answers or candidate skills quickly across fragmented drives and ATS notes.
SolutionAxtra Labs built a RAG chatbot over HR documents and talent profiles, with access control and citations.
TechnologiesAzure OpenAI, LangChain, SharePoint, Elasticsearch

Technologies used

Azure OpenAI SharePoint Elasticsearch Python

Client background

A multi-country professional-services firm with 4,000+ employees managed HR policy across SharePoint libraries, email threads and an aging ATS. Recruiters spent hours hunting for answers, and people-ops could not trust a single source of truth when policy changed.

Key challenges

  • Policy PDFs, FAQs and ATS notes lived in separate systems with inconsistent permissions.
  • Recruiters asked the same questions repeatedly; answers depended on who was online.
  • No citations — employees could not verify whether an answer matched the current handbook.
  • Talent search was keyword-only, so skill matches and past project experience were easy to miss.

Product screenshots

Light indigo chat interface: a recruiter asks about parental leave, the assistant replies with numbered citations, and a right-hand panel shows the highlighted source paragraph from an HR policy document with access level.
An HR assistant answers a leave-policy question and cites the exact policy paragraph it used, shown in a source panel beside the chat.
Indigo-on-white talent search screen: a natural-language query is parsed into filter chips, and ranked candidate cards show a match score ring, skill tags, project evidence and availability.
Talent search turns a plain-language request into filters and ranks internal profiles by skills, past projects and availability, with a reason for each match.

What we built

  • RAG chatbot over SharePoint HR docs and curated talent profiles, with role-based access.
  • Citation panel that links every answer back to the source paragraph.
  • Talent search that ranks candidates by skills, projects and availability signals.
  • Admin console for ingesting new policies and retiring outdated versions.

Project team: 6 engineers across AI/ML, backend and domain specialists — delivery over 14 weeks.

Architecture design

Employees
Employees
Ask HR questions
Recruiters
Talent search
People-ops admins
Manage policies
Applications
Chat with citations
Source paragraph
Talent search
Skills, projects, availability
Admin console
Ingest & retire
AI layer
RAG chatbot
LangChain
Answer generation
OpenAI
Ranking
Talent signals
Data & search
Search index
Elasticsearch
HR documents
SharePoint
Talent profiles
Curated
Role-based access
Permissions
Cloud & AI services
LLM
OpenAI
Answers
LangChain
RAG
Search & content
Elasticsearch
Index
SharePoint
HR documents
Cloud
Azure
Hosting
Technology stack
AI & ML
OpenAILangChain
Backend & APIs
Python
Data
Elasticsearch
Cloud & DevOps
Azure
Integrations
SharePoint

How we delivered

01

Discover

Mapped HR workflows, permission boundaries and the highest-volume question types.

02

Ingest

Normalized SharePoint and ATS exports into a searchable index with ACL metadata.

03

Pilot

Rolled out to HR ops first, then recruiters, with feedback loops on answer quality.

04

Harden

Added eval sets, access audits and a change process for policy updates.

Business impact

70%Faster policy answers
3 systemsReplaced by one assistant
Same dayRollout to HR ops

Services used

We empower businesses with AI, ML, and data solutions.

Response within 1 business day. You will hear from an engineer, not a salesperson.

Contact Us →