Juhi Tiwari
Juhi is a Research Lead at Kore.ai, driving market intelligence, competitive insights, and analyst-facing strategy that strengthens the company’s industry positioning. She also works as a content strategist, creating deep technical content that translates complex AI concepts into clear, compelling narratives. Her work supports Kore.ai’s vision, credibility, and thought leadership across the AI landscape.
Articles by this author
How is RAG reinventing enterprise search and reducing time-to-insight?
RAG for enterprise search transforms traditional information retrieval into an intelligent, context-aware experience that helps employees move from questions to insights faster. This article explains retrieval-augmented generation, semantic retrieval, enterprise data grounding, Agentic RAG, multi-source search, contextual answers, and time-to-insight. It shows how RAG can evolve enterprise search from document discovery into a decision-support layer that delivers relevant answers, anticipates follow-ups, and accelerates action.
Choosing the right orchestration pattern for multi agent systems
Multi-agent orchestration determines how AI agents coordinate, share context, delegate tasks, and execute complex workflows. This article explores three AI agent orchestration patterns: Supervisor, Adaptive Agent Network, and Custom, comparing their trade-offs across latency, cost, scalability, control, and traceability. It explains when each pattern fits enterprise use cases and how Kore.ai enables flexible, governed orchestration for real-time, regulated, and complex multi-agent AI systems.
ChatGPT enhances conversational AI but it’s not a business solution
ChatGPT and conversational AI serve different roles in enterprise environments. This article explores how large language models enhance natural language understanding, intent recognition, generative AI, semantic search, and conversational experiences, while enterprise conversational AI platforms provide integrations, security, business process execution, analytics, and governance. It explains how organizations can combine LLM capabilities with enterprise conversational AI to deliver secure, context-aware, and task-oriented customer experiences.
Breaking knowledge silos with RAG: The future of enterprise search
RAG-powered enterprise search breaks knowledge silos by retrieving and synthesizing information across structured and unstructured enterprise data. This article explores Retrieval-Augmented Generation, semantic search, hybrid multi-vector search, contextual answers, Agentic RAG, data grounding, personalization, and knowledge discovery. It explains how Kore.ai Search and Data AI combines unified data ingestion, enterprise-grade security, citations, guardrails, and 100+ connectors to deliver accurate, context-aware insights faster.
Agentic RAG : A comprehensive guide
Agentic RAG combines AI agent reasoning with retrieval-augmented generation to deliver more accurate, contextual, and adaptive enterprise AI. This article explores agentic retrieval, iterative search, query rewriting, multi-hop retrieval, context augmentation, validation, knowledge graphs, and enterprise data connectivity. It explains how Kore.ai applies Agentic RAG within Search AI to orchestrate retrieval across distributed sources while supporting grounded generation, governance, observability, and access controls.