InfoQ Homepage AI, ML & Data Engineering Content on InfoQ
-
AI Agents to Make Sense of Data at OpenAI
OpenAI’s Bonnie Xu explains Kepler, their internal AI data analyst agent built on MCP. She shares how they scale data discovery across 600+ PB using automated context, RAG, and AST-based evals.
/presentations/data-aware-ai-agents/en/mediumimage/bonnie-xu-medium-1781164411672.jpg)
-
Write-Ahead Intent Log: a Foundation for Efficient CDC at Scale
Vinay Chella and Akshat Goel explain why they outgrew traditional CDC at scale. They share how they built Write-Ahead Intent Log (WAIL) using a proxy layer to decouple data replication.
/presentations/write-ahead-intent-log/en/mediumimage/vinay-chella-akshat-goel-medium-1781177310280.jpg)
-
From Hype to Strong Foundations: What the Rise, Fall and Resurgence of Agents Can Teach Us about Outlasting the Cycle
Aditya Kumarakrishnan discusses "Agents: The Missing Manual," sharing four historically grounded ideas to build modular, durable, and hyper-tenant AI agent architectures.
/presentations/llm-compound-ai-systems/en/mediumimage/medium-1781082183297.jpg)
-
Automating the Web with MCP: Infra that Doesn’t Break
Paul Klein explains how to automate the web with MCP. He shares architectural strategies for running multi-tenant, cloud-hosted Chromium sandboxes to power AI browsing agents.
/presentations/parallel-agents-production/en/mediumimage/paul-klein-medium-1781168002415.jpeg)
-
Moving Mountains: Migrating Legacy Code in Weeks Instead of Years
Principal AI Engineer David Stein explains how ServiceTitan uses AI coding agents to automate large-scale legacy code migrations, compressing quarters of technical debt into weeks.
/presentations/refactoring-ai-agents/en/mediumimage/david-stein-medium-1780059292714.jpeg)
-
Beyond Prompting: Context Engineering and Memory Management for AI Systems at Scale
Adi Polak explains how to scale agentic AI by shifting from stateless prompt engineering to stateful, low-latency context engineering with Apache Kafka and Flink.
/presentations/context-engineering-data/en/mediumimage/adi-polak-medium-1780059098035.jpeg)
-
Beyond Speed Limits: Exploring the Performance Power of Valkey
Viktor Vedmich explains how to achieve sub-millisecond application latency using Valkey, an open-source, high-performance in-memory fork of Redis supported by AWS.
/presentations/valkey-datastore/en/mediumimage/viktor-vedmich-medium-1780058022702.jpeg)
-
Platform Teams Enabling AI - MCP/Multi-Agentic Tools across Linkedin
LinkedIn’s Karthik Ramgopal and Prince Valluri explain how to scale engineering with agentic AI. They discuss building centralized platform foundations for orchestration, tooling, and context.
/presentations/ai-multi-agentic-tools/en/mediumimage/medium-1779867927919.jpg)
-
Choosing Your AI Copilot: Maximizing Developer Productivity
Coinbase ML platform engineer Sepehr Khosravi discusses the state of AI-assisted development. He explains how to maximize productivity using advanced techniques in Cursor and Claude Code.
/presentations/choosing-ai-copilot/en/mediumimage/medium-1779867439150.jpg)
-
Building Evals for AI Adoption: from Principles to Practice
Mallika Rao explains how evaluation debt silently triggers regressions in distributed AI systems. She shares a five-layer evaluation stack to align metrics directly with long-term user trust.
/presentations/eval-ai-adoption/en/mediumimage/medium-1779185675202.jpeg)
-
Designing AI Platforms for Reliability: Tools for Certainty, Agents for Discovery
Aaron Erickson explains how to balance deterministic systems with stochastic AI agents. He shares lessons from NVIDIA on building purpose-built agent hierarchies and scaling robust evals.
/presentations/ai-platforms-reliability/en/mediumimage/medium-1779182751443.jpg)
-
AI Native Engineering
Ian Thomas discusses Meta’s shift to AI-native engineering. He shares how Reality Labs reduced toil and grew an AI productivity community to 400+ members, boosting tool adoption to over 80%.
/presentations/ai-native-engineering/en/mediumimage/medium-1778664122266.jpeg)