Skip to the yard
AI Tools & Apps
-
000124
Managed Deep Agents Brings File-Based Agent Projects to LangSmith Cloud
Managed Deep Agents runs the open-source Deep Agents harness on LangSmith, with memory, schedules, sandboxes and integrations configured in project fi...
-
000023
PhoenixAI Targets Unpredictable Agent Queries With Real-Time Database Tools
PhoenixAI is building for bursts of agent queries, with deployment options and a planned context layer for data access controls.
-
000045
Cloudflare Opens Private Origins Routing to More Customers
Cloudflare can apply WAF, caching, bot management and Workers to private origins over existing network connections, with setup and routing requirement...
-
000127
Agent Loop Engineering: Four Layers for Reliable, Improving Workflows
A four loop design connects tool using agents to verification, event triggers and trace driven improvements, with humans overseeing judgment and sensi...
-
000126
How LangChain Built a Paid Media Agent for Cross-Channel Analysis and Campaign Changes
LangChain’s agent combines ad data, warehouse metrics and human review, cutting reporting time and helping paid media drive 20% of marketing pipeline.
-
000011
Securing AI Infrastructure With NVIDIA BlueField and Continuous Verification
NVIDIA BlueField separates infrastructure controls from host workloads, while Eclypsium checks hardware, firmware and configuration for changes over t...
-
000128
Scheduled Runs Give Managed Deep Agents a Path to Proactive Work
Managed Deep Agents uses scheduled runs for memory, monitoring, reminders and orchestration, with static schedules or runtime tools.
-
000129
OpenWiki and Evidence Graphs Improve Agents’ Cross-Document Answers
In tests on synthetic insurance documents, an OpenWiki memory layer improved cross-source accuracy; adding evidence links raised accuracy and citation...
-
000024
Monte Carlo Data’s Bayes Agent Monitors and Repairs AI Workflows
Bayes tracks deployed agents and their data pipelines, investigates failures and can apply fixes, with early users reporting fewer false alerts.
-
000025
Prophecy DataGPT Turns Chatbot Data Requests Into Reviewable Workflows
DataGPT builds reusable data workflows inside ChatGPT, Claude and Copilot, with human review, Git-backed code and execution on company data platforms.
-
000092
Four Challenges to Scaling Trusted Data Access Across the Enterprise
Trusted data sharing at scale depends on clear definitions, business ownership, easy discovery and access controls that work for people and AI.
-
000098
pg_pinecone Brings Compact, Filtered Vector Search to Postgres
The Apache 2.0 extension adds compact vector indexing and search inside Postgres, with optional Pinecone services and unchanged SQL queries.
-
000049
Cloudflare’s Post-Quantum GeoKey Manager Keeps Key Unwrapping Region-Bound
Cloudflare’s closed-beta service pairs hybrid post-quantum key wrapping with regional controls, while failing closed when keys or location checks are...
-
000012
Kazakhstan Builds AI Compute Capacity for Local Models and Industrial Applications
Kazakhstan is expanding GPU infrastructure while local firms pursue generative media, robotics and autonomous mobility applications.
-
000134
Flint-interactive Gives AI Agents a Higher-Level Language for Interactive Charts
Flint-interactive maps user selections to chart updates, helping agents build linked visualizations and dashboards with less low-level rendering work.
-
000013
NVIDIA Minerva Connects AI Factory Telemetry to Trace Infrastructure Problems
Minerva links GPU, network, storage and workload data to detect anomalies, group incidents and help teams investigate AI factory performance.
-
000135
KLS Conjecture Proof Establishes Dimension-Independent Bound in High-Dimensional Geometry
A proof of the 31-year-old KLS conjecture gives a dimension-independent bound, with human-guided AI aiding the search and independent proofs adding co...
-
000051
Cloudflare WAF Adds Full Transaction Detection and Response Rules
Cloudflare WAF can now assess request and response evidence together, then block selected origin responses. The features are available across all plan...
-
000015
Google Cloud A5X Brings NVIDIA Vera Rubin Systems to Reinforcement Learning and Agent Workloads
Google Cloud’s A5X instances pair Vera Rubin hardware with high-speed networking and liquid cooling for reinforcement learning and agentic workloads.
-
000016
European AI Clouds Expand Compute, Open Models and Agent Controls
Regional providers are adding AI capacity, model services and runtime controls, with reported gains in inference throughput and specialized-task effic...
-
000094
AI Agent Evaluation Needs Full Trajectories, Real-World Evidence and Independent Review
A new research agenda maps 33 trends in agent evaluation, from costly trace analysis to the need for independent, real-world testing.