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
What are context graphs and how do they make AI agents smarter?
Context graphs are an enterprise AI infrastructure layer that captures how organizations make decisions, including reasoning, exceptions, precedents, and decision lineage. This article explains how context graphs complement knowledge graphs and RAG by giving AI agents access to organizational judgment, not just documented information. It explores agentic AI, decision intelligence, contextual memory, AI agent observability, and autonomous decision-making, highlighting how Kore.ai uses context graphs within Artemis to improve agent accuracy, continuity, and enterprise-scale decision-making.
What is AI agent interoperability, and why does it matter
AI agent interoperability enables AI agents across different platforms, vendors, and enterprise systems to communicate, share context, discover capabilities, and hand off tasks without custom integrations. This article explains the role of MCP, A2A, and ACP, alongside data governance, security, identity, and multi-agent orchestration. Kore.ai Agent Management Platform (AMP) supports MCP and A2A compatibility, heterogeneous agent environments, legacy systems, governance, and auditable cross-agent workflows.
What is AI agent memory?
AI agent memory enables AI agents to retain, retrieve, and build on information across interactions, making them more contextual, personalized, and effective over time. This article explains semantic, episodic, procedural, and working memory, along with memory extraction, storage, consolidation, retrieval, governance, and multi-agent scoping. It also distinguishes agent memory from RAG and explains Kore.ai’s Memory Stores architecture, including session, persistent, access-controlled, and retention-managed memory.
Agent management platform: Why do enteprises need one ?
An AI agent management platform provides the centralized control layer enterprises need to govern, monitor, evaluate, and optimize AI agents at scale. This article explores agent governance, observability, ROI attribution, compliance, cost management, multi-agent orchestration, A2A, MCP, and lifecycle management. It explains how Kore.ai’s Agent Management Platform provides vendor-agnostic governance across agents built with different frameworks, models, clouds, and enterprise systems.
AI agent governance: A practical guide to risk, trust, and compliance
AI agent governance provides the policies, guardrails, monitoring, and oversight required to deploy autonomous AI agents safely at enterprise scale. This article explores AI risk management, compliance, observability, decision provenance, guardrails, data security, model governance, bias monitoring, multi-agent governance, human oversight, and auditability. It explains how Kore.ai embeds governance into the agent architecture, enabling controlled autonomy, continuous monitoring, and accountable AI agent operations.
What is Enterprise AI: A complete guide
Enterprise AI enables organizations to embed intelligence across data, workflows, applications, and business operations to drive measurable outcomes at scale. This article explores enterprise AI architecture, agentic AI, data readiness, governance, orchestration, AI agents, interoperability, observability, and the pilot-to-production journey. It explains how enterprises can move from isolated AI initiatives to governed, autonomous systems that connect people, processes, data, and technology across the organization.