World Congress 2025 • Aug 20, 2025 • Session details

One AI API to Power Them All

Roberto Carratalá

A fragmented AI ecosystem doesn't have to slow down your multi-agent architecture. Llama Stack acts as an open-source, universal API to deploy complex AI workflows without rewriting code.

Pause
Mute Enter Fullscreen
#1 about 5 min

Evolution and challenges of building AI applications

Transitioning from basic chatbots to multi-agent production configurations introduces severe workflow integration complexities.

#2 about 4 min

Unifying AI components with the Llama Stack API

A standardized modular API provides a streamlined pathway for assembling and deploying robust applications.

#3 about 3 min

Standardizing model inference and active safety guardrails

Intercepting generation payloads ensures secure communications across diverse local and remote language models.

#4 about 3 min

Hot-swapping components for retrieval augmented generation pipelines

Abstracting the retrieval process grants engineers the flexibility to replace vector databases without rewriting code.

#5 about 2 min

Integrating external tools via the Model Context Protocol

Adopting the Model Context Protocol establishes a universal standard for integrating external tools with agents.

#6 about 3 min

Orchestrating agent workflows and complex reasoning patterns

Orchestrating multi-step executions relies on utilizing reasoning frameworks like react and chain of thought.

#7 about 4 min

Tracing agent telemetry with OpenTelemetry and Jaeger tools

Exposing granular execution spans via observability standards clarifies complex internal calls and network lags.

#8 about 5 min

Demonstrating local AI development and active safety shields

Running local container environments demonstrates agent tool capabilities and verifies active prompt safety shields.

#9 about 7 min

Deploying complex multi-agent application workflows to production clusters

Promoting a multi-tool agent system into live web environments demonstrates automated orchestration over diverse services.

Matching moments

3:14 min

Building a community-governed LAMP stack for open AI

Raffi Krikorian Raffi Krikorian · World Congress 2026 Europe

1:22 min

Leveraging the comprehensive generative artificial intelligence stack

Duan Lightfoot Duan Lightfoot · World Congress 2024

4:13 min

Empowering developers with comprehensive AI software stacks

Markus Hacker Markus Hacker +1 · World Congress 2025

7:30 min

Implementing an AI mesh architecture stack on AWS

Olga Woschitz Olga Woschitz +1 · Europe 2026 Virtual

50 sec

Adopting a layered approach to agent safety systems

Darko Mesaros Darko Mesaros · World Congress 2026 North America

3:25 min

Constructing scalable AI solutions using LangChain and LangGraph

Julián Duque Julián Duque · World Congress 2025

Upcoming sessions on this topic

Open session

Teaching AI Coding Agents to Build It Right the First Time

  • Sajeetharan Sinnathurai

    Microsoft

    Principal Product Manager

Open session

Architecting Trusted AI: Coupling Multi-Agent Systems with dbt Semantic Store for Zero-Hallucination

  • Pushkar Mishra

    J.P. Morgan

    Senior Vice President

Open session

Build a Zero-Cost AI Agent in Your Browser

  • Aishwarya Mathuria

    Adobe

    Computer Scientist

  • Nishant Thakur

    Adobe

    Senior Computer Scientist

Open session

Java is Coming for Python’s Lunch: The Rise of JVM AI Agents

  • Frederik Pietzko

    Jetbrains

    Developer Advocate

Open session

Beyond File Dumps: Context Engineering for Coding Agents

  • Animesh Dutta

    Arm

    Senior Software Engineer

Open session

Beware of Strangers Bearing Code: Open Source Trust in the Agent Era

  • Vikram Vaswani

    Consultant