World Congress 2026 Europe Jul 9, 2026 Session details

The Agent Interface Layer: Protocols, Tools and Trust Boundaries

David Soria Parra , Duan Lightfoot , Malte Ubl , Taroon Mandhana

How do you securely connect autonomous AI agents to enterprise systems? Discover how the Model Context Protocol and dynamic permissions redefine trust boundaries for non-deterministic workflows.

Pause
Mute Enter Fullscreen
#1 about 3 min

Origin and purpose of the Model Context Protocol

How MCP was created to provide AI systems with the connectivity needed for broader knowledge work.

#2 about 4 min

Identifying viable business use cases for agents

Why automating repetitive tasks with clear boundaries yields more success than tackling open-ended business problems.

#3 about 4 min

Managing trust and permissions for write-capable agents

Implementing safe permission models, human-in-the-loop workflows, and offline evaluations before granting agents write access.

#4 about 7 min

Adapting deterministic infrastructure for autonomous agents

The shift from traditional static permissioning and testing toward evaluation-based oversight for probabilistic systems.

#5 about 4 min

Ensuring portability across evolving agent platforms

How abstracting agent skills and curating context engineering reduces lock-in and dependency on specific models.

#6 about 3 min

Running agents efficiently at enterprise scale

Strategies for managing token costs through granular context curation and continuous framework optimization.

#7 about 4 min

Comparing runtime harnesses and retrieval context approaches

Why orchestrating models via programmatic tool calling enhances output quality beyond static semantic search.

#8 about 2 min

The evolving role of software engineers alongside agents

How developers are transitioning from writing all code to acting as technical leads who orchestrate agentic workflows.

Matching moments

3:25 min

Understanding foundational concepts of LLMs, agents, and MCPs

Perf + AI

2:28 min

Integrating autonomous agents using the model context protocol

Fabian Hedin Fabian Hedin · WWC Europe 2026

1:42 min

Standardizing autonomous agent logic with model context protocol

Timo Salm Timo Salm · WWC 2025

1:11 min

Shifting security models from passive chatbots to active agents

Péter Farkas Péter Farkas · Europe 2026 Virtual

2:44 min

Understanding language models and autonomous executing agents

Chris Heilmann +2 · LIVE

1:25 min

Standardizing interoperability with the model context and agent protocols

Julián Duque Julián Duque · WWC 2025

Upcoming sessions on this topic

Open session

World Congress 2026 North America

MicroAgents: The Microservices of the Agentic Era

Ashish Shubham

Runs the show bussiness at ThoughtSpot

Ashish Shubham
Open session

World Congress 2026 North America

Securing AI Agent Infrastructure: Identity, Attestation, and Trust at Scale

Abdel Fane

Founder of OpenA2A

Abdel Fane
Open session

World Congress 2026 North America

When Agents Became Users: Rearchitecting Identity and Permissions for AI at Scale

Yoav Gal, Dor Cohen

Yoav Gal
Dor Cohen
Open session

World Congress 2026 North America

AI-Powered Incident Triage: How We Built GenAI Agents with MCPs to Automate On-Call Workflows

Prakshal Doshi

Site Reliability Engineer

Prakshal Doshi
Open session

World Congress 2026 North America

AI Agents are Only as Smart as their Context: Building a Real-Time Context Engine at Intuit

Bharat Patel

Lead Software Engineer at Intuit

Bharat Patel
Open session

World Congress 2026 North America

Give the Agent a Budget, Not a Token

Sachin Malhotra

MTS @Anthropic

Sachin Malhotra