InfoQ Homepage AI, ML & Data Engineering Content on InfoQ
-
The Agent Harness: Control Planes, Invariants, and Approval Boundaries for Production AI Agents
OpenAI’s Vinoth Govindarajan explains how to build reliable AI agent harnesses in production, focusing on state ownership, mutation ordering, scoped authority, and user-visible proof of action.
-
Context Engineering at LinkedIn: How We Built an Organizational Context Layer for AI Agents with MCP
Ajay Prakash shares how LinkedIn built Contextual Agent Playbooks and Tools to give AI coding agents internal stack context, automating 600+ workflows and raising productivity 20%.
-
Teaching Engineers, Trusting AI: How Education Enabled Autonomous Code Review
Sarah Deitke shares how Duolingo scales AI adoption through engineering literacy programs and demonstrates how AI-driven code reviews reduced pull request merge times from 18 to 12 hours.
-
Decision Models in Agentic Architectures: from Production to Agent Skills
Alex Porcelli explains how combining deterministic DMN decision models with agentic AI resolves enterprise AI challenges around accountability, rule governance, and non-deterministic logic.
-
From Retrieval to Reasoning: Building Production-Ready Agentic AI Systems with Knowledge Graphs
Cassie Shum shares lessons learned on using knowledge graphs as the foundation for agentic software systems, covering 4 key architectural patterns to optimize context, provenance, and team efficiency.
-
Fixing the AI Infra Scale Problem by Stuffing 1M Sandboxes in a Single Server
Felipe Huici discusses scaling microVM sandboxes for AI workloads, explaining how millisecond cold boots, high density, and stateful scale-to-zero achieve efficient, secure cloud isolation.
-
Platform Engineering in the Age of AI
The panelists discuss how internal developer platforms adapt for AI-assisted engineering, balancing standardization, guardrails, and developer autonomy to shape next-gen platform engineering.
-
From AI Agent Demo to Production: Automated Testing and Evaluation
Zhou Yu explains why 95% of AI agents fail to reach production and shares how simulation-driven evaluation, synthetic users, and automated CI/CD testing unlock enterprise deployment.
-
A Few Predicted Talks From QConAI 2030
Meryem Arik shares 2030 predictions on rising token costs, parallel agent architectures, non-developer app explosion, vendor lock-in, incoming AI regulations, and shifting software engineering roles.
-
From S3 to GPU in One Copy: Rethinking Data Loading for ML Training
Onur Satici discusses Vortex, an open-source columnar file format designed to bypass CPU bottlenecks, enabling ultra-fast S3-to-GPU data streaming and dynamic query pruning at up to 60 Gbps.
-
Beyond Prompting: Context Engineering for Production-Grade AI
Ricardo Ferreira explains how context engineering overcomes LLM latency, cost, and memory limitations in AI systems, sharing architectural lessons from building a custom Alexa backend with Redis.
-
Running AI at the Edge: Running Real Workloads Directly in the Browser
James Hall explains why engineering teams should shift AI workloads on-device. He shares local inference strategies, WebGPU optimization techniques, and architecture choices for zero-trust privacy.