Model Online / On-Site
Duration
Modules 6 modules

Course Objective & Scope

Employees and support agents lose hours hunting for answers across SharePoint sites, Confluence spaces, HR portals, policy PDFs and ticket archives. A successful enterprise knowledge assistant is more than a vector index: it combines multi-source connectors, multi-turn conversational query resolution, clarifying questions on ambiguous prompts, interactive source citations and safe handoffs to transactional tools.

Participants design and build an end-to-end cited, permission-aware enterprise knowledge assistant tailored to their organisation's knowledge sources and user personas.

Who Should Attend?

  • Software and AI engineers building employee assistants (HR, IT service desk, legal/compliance, sales enablement) or agent copilots
  • Solution architects designing enterprise knowledge management and digital workplace systems
  • Technical product teams delivering internal assistant products
  • Prerequisite: web/API development in Python or TypeScript and basic LLM/RAG familiarity

Key Takeaways

  • Unify heterogeneous repositories (wikis, PDFs, FAQs, tickets) into a canonical document and metadata schema
  • Handle multi-turn coreference resolution and ask clarifying questions when user queries are underspecified
  • Deliver role-, department- and location-aware answers while enforcing document permissions
  • Combine knowledge retrieval with action tools (creating tickets, pre-filling forms, escalating to a human)
  • Build a content-gap analytics loop from user feedback and unanswered query logs

Curriculum

Knowledge Assistant Architecture and Enterprise Connectors
  • Unified ingestion schemas across SharePoint, Confluence, Google Drive, Jira/ServiceNow and PDFs
  • Source authority ranking: prioritising official policies over informal wiki pages or ticket comments
Conversational Retrieval, Coreference Resolution and Disambiguation
  • Rewriting follow-up questions ("how do I cancel it?") into standalone retrieval queries
  • Detecting underspecified prompts and asking targeted clarifying questions before answering
Persona-Aware Responses, Citation UX and Trust Design
  • Filtering and tailoring answers by user role, department, location and ACL permissions
  • Streaming answers, inline citation badges, document preview drawers and suggested follow-ups
From Knowledge to Action: Tool Calling and Human Escalation
  • Pairing informational answers with transactional tools (opening IT/HR tickets, checking status via MCP/APIs)
  • Seamless escalation to human support with structured conversation summaries on sensitive or unresolved issues
Content-Gap Analytics and Continuous Knowledge Curation
  • Tracking thumbs-up/down, citation click-through rates and zero-answer query clusters
  • Alerting document owners to outdated, conflicting or missing articles
Project: Building a Cited Enterprise Knowledge Assistant
  • End-to-end assistant prototype for an internal HR, IT, operations or support use case
  • Architecture, security and acceptance test review

Other Courses in This Category

  • Text-to-SQL and Conversational Analytics over Enterprise Databases

    Engineering Text-to-SQL and conversational analytics systems that translate natural-language business questions into accurate SQL queries, tables and charts over PostgreSQL, BigQuery, Snowflake and SQL Server.

    RAG & Enterprise Knowledge Systems Corporate
    Live Course
    6 modules
    View
  • Semantic Layers and Governed Metric Definitions for Text-to-SQL and AI Analytics

    Preventing inconsistent numbers in AI analytics by grounding LLMs in a governed semantic layer (Cube, dbt Semantic Layer, YAML metric definitions, canonical joins and business glossaries).

    RAG & Enterprise Knowledge Systems Corporate
    Live Course
    6 modules
    View
  • SQL Query Validation, Guardrails and Access Control for Text-to-SQL

    Securing production Text-to-SQL systems with AST validation (SQLGlot), read-only execution sandboxes, Row-Level Security (RLS), column masking, query cost guards and semantic verification.

    RAG & Enterprise Knowledge Systems Corporate
    Live Course
    6 modules
    View
  • Text-to-SQL Accuracy Evaluation and Enterprise Benchmarking

    Evaluating Text-to-SQL systems rigorously using Execution Accuracy, result-set matching, AST structural comparison, query efficiency scoring and enterprise benchmark construction.

    RAG & Enterprise Knowledge Systems Corporate
    Live Course
    6 modules
    View
  • RAG with LangChain RAG with LangChain

    Hands-on workshop on building an end-to-end Retrieval-Augmented Generation (RAG) chatbot using LangChain, covering document chunking, embeddings, vector databases, and a Gradio interface.

    RAG & Enterprise Knowledge Systems Corporate, Individual Workshop
    Live Course
    6 modules
    View
  • Multimodal RAG Multimodal RAG

    Hands-on workshop on building a Multimodal RAG system with LangChain to extract, embed, and query text, tables, and images from complex PDF documents.

    RAG & Enterprise Knowledge Systems Corporate, Individual Workshop
    Live Course
    6 modules
    View

Get in touch