LINKED LIST [txt mode] ▸ @cass ▸ Evaluating and Improving Agents

home explore | log in

Evaluating and Improving Agents

by @cass · last added 2026-04-16 · 12 items

Tips & advice on building agents with notes on,

- harness wisdom (MCP advice)
- evals
- etc

─── 2026-04-16 (1) ─────────────────────────────────────

* Notion’s Token Town: 5 Rebuilds, 100+ Tools, MCP vs CLIs and the Software Factory Future — Simon Last & Sarah Sachs of Notion

─── 2026-04-15 (5) ─────────────────────────────────────

* MCP Tool Design: Why Your AI Agent Is Failing (And How to Fix It)

* 54 Patterns for Building Better MCP Tools

* Writing Effective Tools for Agents: Complete MCP Development Guide

* Speed, Structure, and Smarts: The Notion AI Way

* Notes from Token Town: Negotiating for the Fortune 5 Million

─── 2026-04-14 (6) ─────────────────────────────────────

* Understanding MCP Evals: Why Evals Matter for MCP

* Writing effective tools for AI agents—using AI agents

* Block's Playbook for Designing MCP Servers

* Build MCP Tools Like Ogres... With Layers

* Designing MCP tools for agents: Lessons from building Datadog's MCP server | Datadog

* GitHub - toon-format/toon: 🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.