Agents & MCP

Agentic patterns, subagents, MCP servers, and tool integrations.

The collection25 saves · newest AUG 23

Player 1 · this device

0 / 25 adopted

LV.1Vercel Agent Browsers: 15x Fewer Tokens for Claude Browser Automation
LV.2Why You Cannot Test an AI Feature Like Regular Code
LV.3Why You Need Evals When Building with AI (LLM Output Is Unpredictable)
LV.4Kanban Board for Claude Code: Drag Tasks to Trigger Multi-Agent Sessions
LV.5How IBM's Enterprise AI Coding Agent "Bob" Balances Safety, Control, and Developer Trust
LV.6Builder + Checker Agent Loop That Self-Fixes Until All Tests Pass
LV.7Two Types of AI Loops: Deterministic vs. LLM-as-Judge
LV.8Why 'Human in the Loop' Is Failing: and What Agent Accountability Looks Like
LV.9Claude Tag: Claude Now Joins Your Slack as a Team Member with Its Own Permissions
LV.10Clips: Free Open Source Agent-Native Alternative to Loom
LV.11Subagents for Beginners: Spawning Claude Agents and 6 Formations
LV.12Claude Dynamic Workflows: orchestrating parallel verifying subagents in Claude Code
LV.133 Agent Harness Fixes: State Object, Validator Loop, Granular Tools
LV.143 Lessons From Anthropic's Fable 5 Workshop: Outcomes, Advisor, Parallel
LV.15Agentic OS Part 1: Unattended Overnight Claude Loops With Report Cards
LV.16Set Guardrails Before Connecting Any Tool to Claude
LV.17Three agent-engineering interview questions, and the modern way to scale to thousands of agents
LV.18Seven Scoped Agents Instead of One Doing Six Jobs
LV.19Knowledge Graphs Are Easy to Build Now, and That Changes Grounding
LV.20From Prompt Engineering to Loop and Graph Engineering
LV.21Common AI Agent Mistakes and What to Do Instead
LV.22Five Agentic Design Patterns Every AI Engineer Should Understand
LV.23How to Answer the Agent Latency Interview Question
LV.24Five Agent Metrics That Matter More Than Accuracy
LV.25Four Agent Observability Tools and the Five Things to Log