#ai-agents
Every summary, chronological. Filter by category, tag, or source from the rail.
Agentic Aggregators for Electric Bus Fleet Management
Agentic systems can optimize electric bus fleets by balancing grid flexibility and operational constraints, but profit-oriented configurations risk extracting value from public transport operators.
Scaling Enterprise AI: Agent Registry and ADK
Google Cloud's Agent Development Kit (ADK) and Agent Registry provide a governed, scalable architecture for orchestrating AI agents and tools, enabling enterprises to transform legacy APIs into secure, reusable MCP-compliant services.
Google Cloud TechScaling AI and Vibe Coding: What's New in Google Cloud Run
Google Cloud Run is evolving into a comprehensive platform for AI agents, 'vibe coding,' and high-scale microservices, introducing features like spend caps, GPU support, ephemeral sandboxes, and dedicated worker pools.
Figma Updates: Code Layers, Motion, and AI Agent Workflows
Figma is blurring the lines between design and engineering by introducing native code layers, built-in motion/shader support, and AI-driven agent workflows that connect to external tools like GitHub and Notion.
OmniPath: Automating Wheelchair Accessibility Audits with AI
OmniPath improves accessibility mapping by fusing OpenStreetMap data with high-density LiDAR to identify physical barriers like slope and surface discontinuities that standard maps ignore.
RIFT-Bench: A Framework for Automated Agentic AI Red-Teaming
RIFT-Bench provides a standardized, graph-based methodology to automatically discover and stress-test autonomous AI agent architectures, enabling unified security evaluation across heterogeneous systems.
Fika Jobs: Building a Video-First AI Hiring Marketplace
Fika Jobs raised $4M to replace static resumes with AI-conducted video interviews, allowing candidates to maintain a searchable, personality-driven profile for employers.
5 Essential Concepts for Modern AI Agent Architecture
Modern AI agents rely on five key standards and patterns—agents.md, agent skills, MCP, A2A, and sub-agents—to manage context, interact with external tools, and coordinate complex workflows.
Perplexity Brain: Self-Improving Memory for AI Agents
Perplexity's 'Brain' system shifts AI memory from user-centric profiles to agent-centric performance, using an overnight context graph to learn from past tasks, failures, and corrections to improve future efficiency.
Managing AI Agents in Enterprise Codebases
Transition from 'prompting' to 'coaching' by treating AI agents as digital interns, using custom skills, automated self-correction loops, and background task management to maintain production-ready standards.
Google Cloud TechBuilding AI Agents with Model Context Protocol (MCP)
The Model Context Protocol (MCP) acts as a universal adapter, allowing AI agents to securely interact with external tools and live data via a standardized input/output interface, decoupling agent logic from tool implementation.
WorldLines: Benchmarking Long-Horizon Stateful Embodied Agents
WorldLines introduces a new benchmark and modeling framework designed to evaluate how embodied AI agents maintain state and execute complex, long-horizon tasks over extended periods.
Vercel's Eve: A Filesystem-First Framework for AI Agents
Vercel has released Eve, an open-source framework that treats AI agents as directories of files, mapping specific capabilities like tools, skills, and schedules to file paths to eliminate boilerplate and production plumbing.
Architecting AI Agents for Production Workflows
Successful AI agents in production function as coordination layers that orchestrate multi-system workflows, enforce strict policy governance, and maintain human-in-the-loop control rather than acting as standalone decision makers.
Building Custom Vision Agents with Gemini, MCP, and Veo 3
Learn how to build a cloud-native vision agent that orchestrates real-time camera input, image style transfer via Nano Banana, and cinematic video generation using Veo 3, all controlled via natural language.
OpenAI's Deployment Simulation for Agentic Coding Risk Assessment
OpenAI has introduced a deployment simulation framework that uses simulated tool calls to evaluate the safety and reliability of agentic coding systems before they are deployed in real-world environments.
AI Agents, Patch Avalanches, and the New Era of Cyber Resilience
As AI agents begin automating password management and vulnerability discovery, security teams must shift from a mindset of total prevention to one of risk-based prioritization and cyber resilience.
Securing Multi-Agent Systems with Cryptographic Identity
To prevent 'confused deputy' vulnerabilities in multi-agent systems, move away from static path-based security and implement identity-based delegation chains using SPIFFE, OAuth2, and cryptographic headers.
IBM TechnologyManaging AI Agents as First-Class Enterprise Identities
NewCore has raised $66M to provide a dedicated identity and access management platform for AI agents, treating them as autonomous employees rather than simple service accounts.
Building an Agentic Incident Resolution System
By combining observability telemetry with organizational context, you can build an incident response system that auto-resolves known issues and provides full context for human-led escalations, significantly reducing triage time.
Building a QwenPaw Agent Workspace in Google Colab
A practical guide to deploying QwenPaw in Google Colab, featuring automated model provider configuration, custom skill development, and streaming API integration for agentic workflows.
Integrating Design Systems with AI via Model Context Protocol
By using the Model Context Protocol (MCP) to feed design system rules into AI agents, developers can ensure AI-generated code remains consistent, brand-compliant, and architecturally sound.
OpenAI Acquires Ona to Enable Persistent AI Agent Workflows
OpenAI is acquiring Ona to integrate secure, cloud-based execution environments into Codex, allowing AI agents to perform long-running, autonomous tasks within customer-controlled infrastructure.
Building AI Agents with Looker and MCP
Learn how to ground AI agents in enterprise data by connecting them to Looker using the Agent Development Kit (ADK) and the Model Context Protocol (MCP).
Google Cloud TechBuilding Agent-Ready Websites with WebMCP
WebMCP is a proposed web standard that allows developers to expose site functionality as structured tools for AI agents, replacing brittle screen-scraping with direct, reliable API-like interactions.
Jedify Raises $24M to Build Context Graphs for AI Agents
Jedify has raised $24M to provide AI agents with a multi-dimensional 'context graph' that connects disparate enterprise data, permissions, and workflows, enabling more accurate and secure autonomous operations.
Building Self-Driving Products: From Signals to PRs
PostHog is building an automated pipeline that ingests product observability data, groups related signals, and uses AI agents to research and submit pull requests, allowing developers to wake up to green PRs instead of dashboards.
Building Autonomous AI Agents with Google ADK
AI agents move beyond simple chatbots by using reasoning, planning, and self-correction loops to execute multi-step tasks autonomously.
Occlusion as a Benchmark for AI Spatial Memory
Current language agents often fail to maintain consistent spatial representations; the authors propose using occlusion tasks as a rigorous benchmark to test if agents truly understand 3D object permanence and spatial relationships.
How AI Agents Shift Knowledge Work from Search to Execution
A joint study by Harvard and Perplexity reveals that AI agents perform 26 minutes of autonomous work per session compared to 33 seconds for search, driving an 87% reduction in human time and 94% in cost for complex tasks.
Showing 30 of 81