Stop Giving Your Agent Every Tool
Large tool catalogs break agent context. Tool search fixes that by letting agents discover and load only what they need.
I walk through the tool-context problem I hit in Emma, the Anthropic tool-search pattern for large tool surfaces, and why I replaced my custom version with Mastra’s built-in ToolSearchProcessor. You’ll see the full search, load, and call loop in Mastra Studio, from an agent with no direct tools to a targeted tool invocation.
Building an AI agent?
I help teams design and ship agentic systems — from architecture to production.
See how I can help
Stop Letting AI Agents Run the Whole Workflow
One inbox agent should not classify, research, score, route, and draft replies in one loose loop.
Harness Engineering: 4 Levers to Diagnose Any AI Agent
Most agent failures aren't model failures. They're harness failures. Here's the 4-lever framework I use to diagnose what broke.
Building Approval Gates AI Agents Can't Route Around
How to wire human-in-the-loop on tool calls — and why system prompt instructions like "always ask before sending" don't actually hold.
Your AI Assistant Doesn't Need a Bigger Model. It Needs Colleagues
The multi-agent supervisor pattern in Mastra: eight specialist agents on one local LLM, one supervisor, structural trust boundaries — using TypeScript.
Get new videos and posts by email
Weekly videos on AI engineering, plus deeper dives in the newsletter.
Occasional emails, no fluff.