Section
Agents – Page 10
The latest Agents news, analysed daily by the i10X newsroom.
FilterCompanies & models
More stories
-
AI Voice Agents in Retail: Edge Computing Breakthrough
Voice AI agents now handle complex retail purchases in noisy stores, proving real-time LLM performance. Learn how edge infrastructure enables this shift from digital chatbots to…
-
Morris II: First Generative AI Worm Threat Analysis
Discover how Morris II, the first generative AI worm, uses prompt injection to spread across LLM agents. Explore risks of excessive agency and zero-trust mitigation strategies.
-
AI Agents: Shifting from Chatbots to Autonomous Execution
The AI industry is pivoting from chatbots to autonomous AI agents, triggering an infrastructure race among cloud giants and edge developers. Learn about the shift to…
-
CyberStrike: Autonomous AI Red Teaming for Enterprise Security
CyberStrike converts LLM subscriptions into autonomous red-team agents that perform continuous penetration testing. Learn how it accelerates remediation and the challenges of governed autonomy in offensive…
-
Supabase Evals: Benchmark for AI Coding Agents on Infrastructure
Supabase Evals is an open-source, containerized suite testing AI agents on real database tasks like migrations and RLS. Learn how it bridges the gap from benchmarks…
-
-
WANDR Benchmark: Perplexity’s Framework for AI Research Agents
WANDR is Perplexity AI’s open benchmark of 500 tasks testing LLM agents on multi-hop web research and citation accuracy. Explore how it bridges gaps in RAG…
-
Autonomous Agents Reshaping AI Infrastructure
Autonomous agents are shifting AI from chatbots to continuous reasoning engines, raising inference demands and new security challenges. Learn the infrastructure and governance implications for enterprise…
-
LLMOps Evaluation: Controlling LLMs in Production
Enterprises face new challenges with LLMs in production: evaluation, observability for agentic systems, and cost management. Learn how to build robust, verifiable AI infrastructure.
-
Model Context Protocol: The Standard for AI Tool Integration
Anthropic’s open-source Model Context Protocol standardizes how AI models connect to tools and data sources. It reduces fragmentation and improves enterprise compliance and security. Explore the…
-
LLM-First Architecture: The Reset for Enterprise AI
Enterprises are pivoting from brittle agent pilots to LLM-first designs with RAG, caching and evaluations. Discover how this approach tames costs and unlocks reliable production AI.
-
Anthropic Opus 5: Near-Frontier AI at Half the Inference Cost
Anthropic Opus 5 optimizes enterprise AI with half the inference costs and higher throughput. See how it tackles rising compute expenses for scalable, agentic workflows. Discover…