Schema-guard prevents AI agents from writing invalid SQL
A new open-source tool uses schema snapshots to catch hallucinated table and column names before AI-generated SQL runs, eliminating false blocks in benchmarks.
Results for “agents”
Daily coverage of AI, developer tools and infrastructure. Each story explains what happened and why it matters, with a link to the original source.
CounterSteer defends LLM agents against indirect prompt injection
A new inference-time defense called CounterSteer suppresses indirect prompt injection by subtracting a specific activation vector from tool results, reducing attack success rates significantly without
OpenAI safety lead resigns, citing broken culture and rogue agent risks
David Robinson leaves OpenAI, warning that rapid development cycles and a lack of safety rigor are creating dangerous vulnerabilities in autonomous AI systems.
Engineering agentic compliance with deterministic guardrails and real-time audits
Santhosh Sundar outlines how to build compliance systems that enforce rules at the point of decision using deterministic code for hard limits and agents for interpretation.
Optimizing developer workflows with Opus 5.5 in Claude Code
Opus 5.5 introduces autonomous long-running tasks and built-in reasoning. Learn how to adjust prompts, manage subagents, and handle new safety flags for better coding results.
Anthropic integrates always-on Cowork agents into Claude
Anthropic has merged its scheduled task agent, Cowork, into the main Claude app for Pro and Max users, competing with OpenAI Dots and Meta Muse in the race for trusted automation.
OpenAI's Dot agent targets enterprise workflows over personal convenience
OpenAI's new Dot agent platform prioritizes business software integration and local computer access, contrasting with consumer-focused competitors like Meta Muse.
Fine-tuning search agents with multi-turn reinforcement learning on SageMaker
Amazon demonstrates how multi-turn RL fine-tunes a Qwen3.6-27B search agent, cutting failure rates from 22% to under 1% while improving retrieval quality.
Implementing persistent agent memory with NVIDIA NeMo and AWS S3 Vectors
A technical guide details how to build scalable, consistent long-term memory for AI agents using NVIDIA NeMo Agent Toolkit and Amazon S3 Vectors on EKS.
AWS releases Strands Decider 2B for local agent validation
AWS launched Strands Decider 2B, a downloadable decision model that validates AI agent actions locally with sub-100ms latency.
How BootLoops uses AI agents to solve cross-disciplinary scientific integrals
Physicist Matthew Schwartz developed BootLoops, an open-source toolkit that leverages LLM agents to solve complex quantitative problems in physics, ecology, and genetics.
When to add graph structures to retrieval-augmented generation systems
Graph RAG adds explicit relationship evidence to vector search, helping agents answer multi-hop questions about dependencies and policies without hallucinating connections.
Cloudflare's paid MCP tools shift spending control to agent runtimes
Cloudflare’s Monetization Gateway uses the x402 protocol to let AI agents pay for API access, forcing developers to manage budgets and retries in the runtime.
Cloudflare launches competition to build agent-native Git platforms
Cloudflare invites developers to build the next generation of Git infrastructure using Artifacts and Workers, targeting workflows designed for autonomous AI agents rather than human collaborators.
Magnitude: An open source inference engine that tunes itself to your hardware
Magnitude compiles and tunes kernels on-device to run open models up to 2x faster than llama.cpp across Apple Silicon, NVIDIA, AMD, and CPU setups.
