InfoQ - Architecture - Presentations

Presentation: Context Engineering at LinkedIn: How We Built an Organizational Context Layer for AI Agents with MCP

Ajay Prakash — Sat, 19 Sep 2026 11:00:00 GMT

Ajay Prakash discusses how LinkedIn overcomes AI agent limitations in large codebases. He explains Contextual Agent Playbooks and Tools - built on Model Context Protocol (MCP) - which serves procedural memory, code search, and runbooks directly to coding agents. Prakash shares architectural details and operational guardrails that deliver a 20% productivity boost with zero loss in reliability.

By Ajay Prakash

Presentation: Complexity and Creativity in Software Engineering

Phillip Mortimer — Fri, 18 Sep 2026 11:00:00 GMT

Phillip Mortimer discusses the shift toward write-only software driven by AI code generation. He explains why traditional pull requests are broken and shares how engineering leaders can manage complexity by decoupling intent from implementation, automating code reviews, and building self-healing architecture to unleash developer creativity across senior engineering and architecture teams.

By Phillip Mortimer

Presentation: Decision Models in Agentic Architectures: from Production to Agent Skills

Alex Porcelli — Mon, 14 Sep 2026 11:00:00 GMT

Alex Porcelli discusses the critical gap in enterprise AI: non-deterministic output and lack of accountability in high-stakes decisions. He shares how integrating DMN decision models with LLMs, agent skills, and NeMo guardrails creates auditable, deterministic agentic architectures - allowing business leaders to own decision logic while engineers maintain robust architectural governance.

By Alex Porcelli

Presentation: From Retrieval to Reasoning: Building Production-Ready Agentic AI Systems with Knowledge Graphs

Cassie Shum — Sat, 12 Sep 2026 11:00:00 GMT

Cassie Shum discusses why knowledge graphs serve as a critical foundation for agentic systems. Moving beyond basic RAG, she explains 4 practical architectural patterns: context bundling, decision provenance, code as truth, and agent visibility. She demonstrates an engineering harness built on a knowledge graph to streamline feedback loops, optimize token usage, and maintain system reliability.

By Cassie Shum

Presentation: How to Run on Three Clouds at Once, and When Not to

Ross McFarlane, Kevin Holditch — Fri, 11 Sep 2026 11:00:00 GMT

Ross McFarlane and Kevin Holditch discuss Form3's evolution from a single-cloud setup to a triple active multi-cloud architecture. They share key engineering strategies for cross-cloud networking, distributed databases with CockroachDB and NATS, custom Kubernetes operators, and navigating distinct regional disaster recovery expectations across the UK, Europe, and US financial markets.

By Ross McFarlane, Kevin Holditch

Presentation: Accelerating Performance by Incrementally Integrating Rust into Existing Codebase

Lily Mara — Thu, 10 Sep 2026 09:34:00 GMT

Lily Mara explains how to avoid high-risk software rewrites through incremental FFI refactoring. She shares how engineering teams can replace Python bottlenecks with Rust via PyO3, demonstrating how to achieve dramatic function-level speedups, seamless integration testing, and meaningful infrastructure cost savings without microservice overhead.

By Lily Mara