InfoQ Homepage Programming Content on InfoQ
-
10 Reasons Your Multi-Agent Workflows Fail and What You Can Do about It
Victor Dibia discusses multi-agent systems, detailing how to build them with AutoGen, common failure points, and strategic approaches for senior software developers and engineering leaders.
/presentations/multi-agent-workflow/en/mediumimage/victor-dibia-medium-1753425805213.jpeg)
-
From Autocomplete to Agents: AI Coding State of Play
Birgitta Böckeler explains how to use AI coding assistants effectively and responsibly, from fighting complacency to fostering a healthy team culture.
/presentations/ai-coding-agents/en/mediumimage/birgitta-böckeler-medium-1753358841121.jpg)
-
Key Lessons from Shipping AI Products beyond the Hype
Phil Calçado shares key learnings from building and scaling an AI startup, offering a product-centric approach for engineering leaders and architects navigating generative AI.
/presentations/microservices-ai-systems/en/mediumimage/phil-calçado-medium-1754401544039.jpeg)
-
Optimizing Custom Workloads with RISC-V
Ludovic Henry shares how RISC-V's open, modular architecture optimizes custom workloads, addressing urgent AI hardware demand & proprietary limits.
/presentations/risk-v-workloads/en/mediumimage/ludovic-henry-medium-1752753882609.jpeg)
-
The Form of AI
Savannah Kunovsky, who leads IDEO's Emerging Tech Lab, explains how combining engineering rigor with design thinking creates impactful, user-centered AI products.
/presentations/ai-trends/en/mediumimage/savannah-kunovsky-medium-1752570905189.jpeg)
-
Refactoring Stubborn, Legacy Codebases
The speakers explain Stripe's successful approach to refactoring stubborn Ruby monoliths. They share lessons on improving developer experience, code quality, and maintainability.
/presentations/refactoring-legacy-codebases/en/mediumimage/jake-zimmerman-getty-ritter-medium-1752753549991.jpg)
-
Maximizing Deep Learning Performance on CPUs using Modern Architectures
Bibek Bhattarai demystifies Intel AMX, explaining how this CPU architecture accelerates deep learning workloads via low-precision matrix multiplication and efficient data handling.
/presentations/dl-cpu-architecture/en/mediumimage/bibek-bhattarai-medium-1752752658387.jpg)
-
High Performance Serverless with Rust
Benjamen Pyle discusses high-performance serverless with Rust on AWS Lambda, covering multi-Lambda projects, the Lambda runtime and SDK, and IaC for cost-effective, scalable solutions.
/presentations/serverless-rust-aws/en/mediumimage/benjamen-pyle-medium-1752656143641.jpeg)
-
Enhance LLMs’ Explainability and Trustworthiness with Knowledge Graphs
Leann Chen discusses how knowledge graphs provide structured data to enhance LLM accuracy, tackling common challenges like hallucinations and the "lost-in-the-middle" phenomenon in RAG systems.
/presentations/llm-knowledge-graphs/en/mediumimage/leann-chen-medium-1752655617585.jpeg)
-
Designing for Defense: Architecting APIs with Zero Trust Principles
Renato Losio and security experts discuss designing for defense and architecting APIs with Zero Trust principles, covering challenges, common vulnerabilities, and practical advice for developers.
/presentations/zero-trust-principles/en/mediumimage/infoqlive-540x400-1752487145764.jpg)
-
From Junior to Staff and beyond: Lessons Learned
Bruno Rey discusses career growth in tech, sharing how to accelerate your path to staff engineer and effectively mentor others, drawing on 17 years of professional experience.
/presentations/junior-principal-lessons/en/mediumimage/bruno-rey-medium-1752147307553.jpg)
-
AI Agents & LLMs: Scaling the Next Wave of Automation
The panelists discuss AI agents and LLMs, exploring their definitions, architectures, use cases, reliability, and impact on the SDLC and future of automation.
/presentations/llm-ai-agents/en/mediumimage/infoqlive-540x400-1751881899008.jpg)