InfoQ Homepage Artificial Intelligence Content on InfoQ
-
Opening the Black Box: Critical Explainability for AI Agent Tool Selection with Kiji Inspector
Hannes Hapke explains how to move beyond post-hoc narratives by using Sparse Autoencoders with Kiji Inspector to uncover true causal mechanistic interpretability in production LLM agent decisions.
/presentations/explainable-ai-llm-agent-decisions/en/mediumimage/HannesHapke-medium-1793278895069.jpeg)
-
Batch Intelligence at Scale: Cost-Efficient Multi-Agent LLM Workflows with Built-In Resilience
Aditya Mulik shares how Walmart scaled resilient multi-agent LLM batch workflows across 4,700 stores, cutting monthly inference costs by 90% while enforcing semantic validation and bounded retries.
/presentations/scaling-multi-agent-llm-batch/en/mediumimage/AdityaMulik-medium-1793278766506.jpeg)
-
Zero Trust Agent Systems that Pass Audits and Still Ship
Advait Patel explains how to secure AI agents in production by moving security boundaries to the tool layer, enforcing workload identity, and capturing structured audit traces for compliance.
/presentations/zero-trust-ai-agents-production-security/en/mediumimage/advait-patel-medium-1792655207658.jpeg)
-
The Ladder is Missing Rungs: Engineering Progression When AI Ate the Middle
Alasdair Allan shares data on the "missing rungs" of software engineering, explaining how AI coding tools stunt junior developer skill growth and disrupt future technical leadership pipelines.
/presentations/ai-software-engineering-pipeline/en/mediumimage/alasdair-allan-medium-1791451156021.jpeg)
-
Serving LLMs at Scale: the Hidden KV Cache Advantage
Khawaja Shams explains how distributed systems engineering solves modern LLM inference bottlenecks, covering KV caching, memory cliffs, prompt prefilling, and disaggregated execution.
/presentations/llm-inference-kv-cache/en/mediumimage/medium-1792066105733.jpeg)
-
AI is an Amplifier: Scale High Performance, Not Dysfunction
Nathen Harvey discusses key findings from the 2025 DORA research, explaining how AI adoption, internal platforms, and organizational guardrails drive real software engineering performance.
/presentations/dora-ai-adoption-engineering-performance/en/mediumimage/medium-1791447741420.jpg)
-
Beyond the Prototype: Scaling Framework Agnostic AI Agent Infrastructure with Ray
The speakers explain how to run and autoscale LLM agents in production using Ray, detailing system architecture, control planes, multi-region deployments, and CI/CD pipelines with LLM evals.
/presentations/scale-llm-agents-production-ray/en/mediumimage/medium-1792065446239.jpg)
-
Exploding GPUs and the AI Infrastructure Challenge
Andrew Martin explains why AI security relies on Kubernetes security, highlighting new threat vectors like prompt injection, unconstrained agents, and the unique risks facing GPU infrastructure.
/presentations/ai-security-kubernetes-gpu-threats/en/mediumimage/andrew-martin-medium-1790846331295.jpeg)
-
You Can't Trust Your AI Bill. And Neither Can I
Erik Peterson shares why AI costs are eclipsing cloud bills, explaining how token spend, unit economics, and AI autonomy impact software architects and engineering leaders.
/presentations/ai-cloud-cost-economics/en/mediumimage/erik-peterson-medium-1791451373591.jpg)
-
Multi-Agent Patterns from Spotify’s AI Powered Advertising Platform
Pratik Rasam explains how Spotify Ads Manager builds multi-agent AI systems in production using Google ADK Java, detailing guardrails, domain ownership, and key architectural patterns for scale.
/presentations/spotify-multi-agent-ai-architecture/en/mediumimage/pratik-rasam-medium-1790847111671.jpeg)
-
The Reinvention of the Dev Team
Hannah Foxwell explains how agentic AI reshapes dev teams, urging software leaders to rethink team structures, eliminate delivery friction, and focus on human-centric value and reliability.
/presentations/agentic-dev-teams/en/mediumimage/medium-1790242915891.jpeg)
-
Building Reusable Evaluation Frameworks for Agentic AI Products
Susan Chang shares how Elastic built a production-grade AI agent evaluation framework, detailing lessons on tracing, LLM-as-a-judge, programmatic evals to prevent regression across engineering teams.
/presentations/elastic-ai-agent-evaluations/en/mediumimage/susan-chang-medium-1790846586191.jpeg)