InfoQ Homepage QCon AI 2025 Content on InfoQ
-
Autonomous Data Products for the Autonomous Era: Rethinking Data Architecture for GenAI
Jörg Schad discusses how to bridge the gap between prototypes and production by standardizing data access for GenAI, using autonomous data products to prevent context rot and ensure safety.
/presentations/ai-framework-data-infrastructure/en/mediumimage/medium-1784107102579.jpeg)
-
From Copy-Paste to Composition: Building Agents Like Real Software
Jake Mannix explains how to mature AI agents using "virtual tools" for encapsulation, interface abstraction, and deterministic taint tracking to prevent lethal data exfiltration risks.
/presentations/agent-software-engineering/en/mediumimage/jake-medium-1784183841742.jpeg)
-
From OTEL to SLMs: Distilling Frontier Model Behaviour from Production Telemetry
Ben O'Mahony shares how to build a data flywheel for AI agents using OpenTelemetry, explaining how behavioral user signals can be mined to distill and fine-tune smaller, localized language models.
/presentations/otel-slm-ai/en/mediumimage/benomahony-medium-1783500827260.jpeg)
-
Postgres for Production Agents: Your Relational Foundation for Enterprise AI
Gwen Shapira discusses how to power enterprise AI features using Postgres, explaining advanced relational SQL context retrieval, pgvector semantic tuning, and transitioning to agentic workflows.
/presentations/postgres-ai-agents/en/mediumimage/gwen-shapira-medium-1783500671134.jpeg)
-
Chaos Engineering GPU Clusters
Bryan Oliver explains how to apply chaos engineering to massive GPU clusters. Learn how to handle hardware variability, NUMA nodes, and network faults to secure your AI infrastructure.
/presentations/chaos-engineering-gpu/en/mediumimage/bryan-oliver-medium-1782819161258.jpeg)
-
The Multi-Agent Approach: Building Reliable and Controllable Software Development Automation
Itamar Friedman explains how to transition from "vibe coding" to reliable software delivery. Learn how to govern agent communication and build a context-driven SDLC that scales.
/presentations/multi-agent-ai-architecture/en/mediumimage/itamar-friedman-medium-1782818996066.jpeg)
-
Fine Tuning the Enterprise: Reinforcement Learning in Practice
Will Hang and Wenjie Zi explain how OpenAI's Agent RFT (Reinforcement Fine-Tuning) optimizes reasoning models end-to-end, enabling autonomous agents to learn efficient tool use and cut latencies.
/presentations/rft-openai-model/en/mediumimage/WenjieZiWillHang-medium-1782220624463.jpg)
-
Graph RAG: Building Smarter Retrieval Workflows with Knowledge Graphs
Cassie Shum explains how to move beyond traditional RAG limits using GraphRAG to inject enterprise logic and complex multi-hop reasoning into scalable knowledge graphs within a data warehouse.
/presentations/graph-rag-llm/en/mediumimage/CassieShum-medium-1782291352027.jpeg)
-
AI Works, Pull Requests Don’t: How AI is Breaking the SDLC and What to Do about it
Michael Webster explains how autonomous "headless" AI agents are flooding pipelines with code. He shares how CircleCI addresses the resulting technical debt and bottlenecked PR reviews.
/presentations/ai-sdlc-pull-request/en/mediumimage/michael-webster-medium-1781688909041.jpeg)
-
Rules for Understanding Language Models
Naomi Saphra explains why language models act like populations rather than individuals. She discusses how data diversity drives generalization, why LLMs mirror users and how tokenizers alter behavior.
/presentations/5-principles-llm-behavior/en/mediumimage/naomi-saphra-medium-1781688751052.jpg)
-
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)
-
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)