#ai-agents
Every summary, chronological. Filter by category, tag, or source from the rail.
Building Production-Grade Multi-Agent Systems with ADK
Learn to build robust, state-aware multi-agent systems using Google's Agent Development Kit (ADK) and the Model Context Protocol (MCP) to handle orchestration, security, and persistence.
Google Cloud TechThe Steering Layer: Enforcing Brand and Code Cohesion in AI
A 'steering layer' is an intentional architectural component that sits between AI tools and a codebase, using context, guidelines, and retrieval systems to ensure AI output remains consistent with brand and development standards.
The Prompt is the Platform: Agentic Engineering for Distributed Systems
By moving agents upstream into the design phase using deterministic simulation, developers can synthesize bespoke, production-ready implementations from abstract specifications rather than relying on general-purpose libraries.
Automating ETL Pipeline Recovery with RL Agents
A reliable, safety-first architecture for ETL pipeline remediation that uses deterministic anomaly detection, Q-learning for action selection, and an external safety layer to reduce MTTR by 99.85%.
Hypertokens: Bridging the Gap Between Tokens and Components for AI
Hypertokens are a proposed design-system concept that bundles multiple style properties into a single, machine-readable unit. By providing AI agents with explicit intent rather than raw values, they reduce guesswork, prevent design drift, and enable automated, multi-format compilation.
Building a Design Stack for Claude Code
To get high-quality UI output from Claude Code, you must move beyond default engineering prompts by providing a structured 'design stack'—a combination of project briefs, design system tokens, and specialized MCP tools.
Vercel Ship 2026: Building Agentic Infrastructure
Vercel is shifting its focus toward 'agentic infrastructure,' providing a full-stack platform designed to build, deploy, and automate software agents securely at scale.
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.
Observability Patterns for Agentic Workflows
Vercel has introduced native observability for the 'eve' agent framework, providing structured tracing of agent turns, tool calls, and token usage with dual-mode views for developers and business stakeholders.
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 Agents and Inference on Google Cloud Run
Google Cloud Run is evolving from a web-service platform into a comprehensive runtime for AI agents, inference, and background tasks, introducing features like GPU support, sandboxed code execution, and custom scaling controls.
Scaling 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.
AI SDK 7: Production-Grade Agentic Workflows
AI SDK 7 introduces deep production capabilities for agents, including durable workflows, standardized reasoning, tool context, and provider-agnostic support for realtime voice and video generation.
Building Custom Figma Plugins with AI Agents
Designers can build custom Figma plugins to automate repetitive tasks by using a structured prompt formula: Trigger + Instructions + Desired Output.
AI SDK 7: Building Production-Ready Agents in TypeScript
AI SDK 7 shifts from simple model calls to a comprehensive agent platform, introducing durable execution, tool approvals, and standardized reasoning controls while requiring Node.js 22 and ESM.
Teaching AI Agents Product Design Standards
Vercel treats product design decisions as code by embedding a 'product-design' skill in the repository, using linters for deterministic rules, and maintaining a human-in-the-loop evidence workflow to ensure agents understand the 'why' behind UI patterns.
Design Systems in the Age of Agentic Authorship
Design systems are shifting from human-authored assets to agent-authored infrastructure. This transition requires moving away from passive governance toward versioned, API-like token management and rigorous review processes for machine-generated output.
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.
Building Scroll-Driven Interactive Web Experiences with AI
Create high-end, Apple-style scroll-triggered animations by combining AI-generated video assets, frame-by-frame decomposition, and AI-assisted coding.
UI CollectiveFika 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.
Showing 30 of 97