QCon AI Boston’s Early Program Focuses on the Engineering Work Behind Production AI

2026-03-05 · Source: InfoQ · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Cloud Computing & IT Infrastructure · Depth: Intermediate, quick

Summary

The QCon AI Boston conference, scheduled for June 1-2, 2026, is shifting its focus from theoretical AI capabilities to the practical engineering challenges of deploying AI systems in production. The early program, curated by experts like Eder Ignatowicz, Meryem Arik, and Hien Luu, addresses critical themes for building trustworthy AI. Key topics include context engineering, agent explainability, advanced Retrieval Augmented Generation (RAG) using knowledge graphs, bridging offline and live performance evaluations, Zero Trust Agent Systems for security and governance, and developing robust GenAI platform layers. Speakers from companies like Redis, Dataiku, RelationalAI, Netflix, Broadcom, DoorDash, Microsoft, and Amazon will present on these areas, emphasizing the need for dependable and scalable AI under real-world constraints.

Key takeaway

For AI Architects designing and deploying AI systems, you must prioritize robust engineering practices over initial model performance. Focus on building comprehensive surrounding systems that ensure reliability, observability, explainability, and security in production. Your strategy should include advanced context management, agent decision visibility, and a scalable GenAI platform layer to bridge the gap between development and real-world operational demands.

Key insights

Production AI demands robust engineering for reliability, explainability, security, and scalability beyond initial demos.

Principles

• AI is a systems design problem.
• Visibility into agent decisions is crucial.
• Offline metrics rarely match live performance.

Method

The program emphasizes context engineering over basic prompting, using knowledge graphs for complex reasoning, and building Zero Trust Agent Systems for auditable functionality.

In practice

• Implement context engineering for production prompts.
• Utilize knowledge graphs for advanced RAG.
• Design for agent explainability and tool selection.

Topics

• AI Engineering
• Context Engineering
• Agent Explainability
• Knowledge Graphs
• GenAI Platform

Best for: AI Architect, MLOps Engineer, AI Engineer, Machine Learning Engineer

Related on AIssential

• Six Sessions at QCon AI Boston 2026 That Take Productionizing AI Seriously — The core challenge in productionizing AI agents lies in robust system engineering beyond model capabilities.
• QCon AI Boston 2026 Schedule: Agents in Production, Inference Cost, and AI in the SDLC — QCon AI Boston 2026 addresses the practical engineering challenges of deploying AI agents and models into production.
• Designing Data and AI Systems That Hold Up in Production — Full-stack thinking and system-level design are crucial for building reliable, scalable, and trustworthy AI and data systems.
• An AI state of the union: We’ve passed the inflection point, dark factories are coming, and automation timelines | Simon Willison — AI has fundamentally reshaped software engineering, making code generation cheap and amplifying experienced engineers' capabilities.
• Mission-Critical Generative AI in Action • Scott Shaw • YOW! 2025 — Production-ready GenAI demands a structured platform and adapted engineering practices to manage inherent unpredictability and rapid model churn.
• Most AI Agents Fail in Production Because They’re Built Backwards — Production AI agents require a bottom-up, distributed systems architecture, not a top-down, model-centric approach.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by InfoQ.