Session 2 — The Context Gap: What AI Agents Need to Work Across the Enterprise
Are you a CIO, CTO or enterprise architect connecting AI agents to enterprise systems? Access to applications is only part of the challenge. This session examines the Human Context agents need to make decisions and operate within enterprise governance.
Session 2 of 4 in The Agentic Enterprise, a WORK-SELF webinar series on turning agentic deployments into measurable ROI.
Thursday, 5 November 2026 · 2:00 PM GMT · 9:00 AM EST · 30 minutes
Giving an AI agent access to a model, CRM, knowledge base and workflow platform does not mean it has enough context to act correctly.
Agents also need to understand the task, the employee responsible for the outcome, the operating rules around the work and the point at which human judgement is required.
This session explores the enterprise context stack and the architecture needed to deliver that context to agents at the moment of work.
Beyond Connectivity: The Context AI Agents Need
Connecting an AI agent to enterprise applications gives it access to information, but not necessarily the operating context required to act correctly.
Agents need to understand the employee responsible for a task, their decision authority, the current workflow state, applicable policies and when human intervention is required.
Human Context Infrastructure is emerging as an essential layer of the enterprise AI stack, bringing governed employee and workflow information together and making it available to approved agents at runtime.
Through Maya Enterprise, WORK-SELF provides this context using an identity-aware data layer, employee-specific Work Contracts, permissioned Context Capsules and MCP interoperability.
What we’ll cover
Why access to enterprise tools and data is not the same as situational context
The role of enterprise data, workflow state and human operating context
How semantic retrieval, interoperability and MCP support dynamic context delivery
How context infrastructure can be applied inside a real enterprise workflow
About the speakers
Wolf Magdelinic
Founder and CEO, WORK-SELF
Wolf has more than 20 years of experience building AI-assisted workflow automation and enterprise technology. He founded and exited Overbond AI, led an applied machine learning research lab involving more than 30 PhD researchers, and is the inventor of a granted US AI patent.
Previously at PwC, Deloitte and CIBC, he holds an Electrical Engineering degree from the University of Toronto and an MBA from Ivey Business School. His work has been featured in The Economist, Reuters, Bloomberg, Forbes and the Financial Times.
Wolf leads the development of WORK-SELF’s Human Context Infrastructure and is co-authoring The Human Feedback Loop: Agentic Enterprise Transformation with Prof. John O’Dwyer.
Armando Gonzalez
CEO and Co-Founder, RavenPack | Founder, Bigdata.com
Armando Gonzalez is a technology entrepreneur and the CEO and Co-Founder of RavenPack, a leading provider of AI-powered data analytics for financial institutions. He brings more than 20 years of experience in artificial intelligence and natural language processing, and has led the development of technologies that turn unstructured information into reliable, actionable intelligence.
He also founded Bigdata.com, an AI platform that helps financial professionals access trusted data and make informed decisions. His research and commentary have appeared in The Wall Street Journal and the Financial Times.
He holds degrees in Economics and International Business Administration from the American University of Paris.
RavenPack | Bigdata.com | LinkedIn
Who it’s for
CIOs, CTOs, CDOs, CAIOs, enterprise architects, AI platform leaders and integration leaders responsible for deploying agents across the enterprise.
About WORK-SELF
WORK-SELF builds Human Context Infrastructure for the agentic enterprise.
Maya Enterprise (a WORK-SELF offering) brings authorised employee, role, task, policy and workflow information into a governed Human Context layer.
Through employee-specific Work Contracts, permissioned Context Capsules and Model Context Protocol (MCP) interoperability, Maya provides approved AI agents with the context required to respect decision authority, human oversight, escalation rules and accountability.
Operating alongside existing enterprise applications and AI systems, Maya helps organisations coordinate human and agent workflows, reduce employee rework and measure the value of completed work.
Part of The Agentic Enterprise, a four-part WORK-SELF webinar series.