InfoQ Homepage Development Content on InfoQ
-
Adaptive Recommenders in the Real World: Inference, Evals, and System Design
Mallika Rao shares why building adaptive recommendation systems requires shifting focus from isolated ML models to real-time feedback loops, retrieval freshness, and production-level constraints.
/presentations/adaptive-recommendation-systems-architecture/en/mediumimage/mallika-medium-1789632229433.jpeg)
-
Spritely: Infrastructure for the Future of the Internet
Christine Lemmer-Webber and David Thompson discuss Spritely's vision for a decentralized web, explaining capability-based security, actor models, and local-first tech to build resilient apps.
/presentations/spritely-decentralized-architecture/en/mediumimage/cd-medium-1789633126216.jpg)
-
Designing Fast, Delightful UX with LLMs for Mobile Frontends
Balakrishnan Ramdoss explains how to scale AI-driven conversational app experiences using server-driven UI, BFF architectures, optimized prompting & high-performance on-device models for low latency.
/presentations/llm-mobile-frontend/en/mediumimage/bala-medium-1789631604448.jpeg)
-
APIs for Agents: Rethinking API Programs in the MCP Era
Jim Gough and Andreea Niculcea explain how Morgan Stanley leverages Architecture as Code with CALM and MCP to scale secure, compliant API platforms for AI agents and future protocols like A2A.
/presentations/mcp-calm-api-architecture/en/mediumimage/jim-gough-andreea-niculcea-medium-1789021410351.jpg)
-
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.
/presentations/ai-agent-harness/en/mediumimage/vino-medium-1789631870270.jpeg)
-
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%.
/presentations/linkedin-context-engineering/en/mediumimage/ajay-prakash-medium-1789021803159.jpg)
-
Complexity and Creativity in Software Engineering
Phillip Mortimer explains why all code is now write-only in the AI era, detailing how software leaders must shift focus from line-by-line PR reviews to detailed tests and self-healing architecture.
/presentations/ai-software-engineering-complexity/en/mediumimage/philip-mortimer-medium-1789021228203.jpeg)
-
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.
/presentations/duolingo-ai-literacy-code-review/en/mediumimage/sarah-deitke-medium-1788338781338.jpeg)
-
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.
/presentations/decision-models-agentic-ai/en/mediumimage/alex-porcelli-medium-1789021621084.jpeg)
-
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.
/presentations/knowledge-graphs-agentic-systems-patterns/en/mediumimage/cassie-shum-medium-1788338916792.jpeg)
-
Accelerating Performance by Incrementally Integrating Rust into Existing Codebase
Lily Mara explains how engineering teams can achieve 100x function-level speedups and lower infrastructure costs by using PyO3 to incrementally refactor critical Python codebases into Rust.
/presentations/rust-refactoring/en/mediumimage/lily-mara-medium-1788338447565.jpeg)
-
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.
/presentations/unikraft-microvm-sandboxes-cloud-scaling/en/mediumimage/felipe-huici-medium-1787813506607.jpg)