Advanced

Going Further

Measure before you change, budget before you build, and run an Agent that plans its own steps.

Start this path5 lessons / about 9 min

Design

01
Evaluating Agent output: build a 20-question test set

Before you change a prompt, a model or a tool, know whether the result got better. A small, honest evaluation set is the only way, and it takes an afternoon.

Tutorial·Advanced·2 min·Members
Required
02
Cost and latency budgets for Agents that run every day

A daily workflow costs what it costs times 365. How to estimate before you build, measure after, and the three cheapest fixes when a workflow gets expensive.

Tutorial·Advanced·2 min
Required

Project

03
Multi-Step Research AgentPick

An Agent that plans its own searches, reads across sources, checks claims against each other, and writes a cited report. With the evaluation set and cost budget that keep it honest.

Project·Advanced·3 min·Members
Required

Keep up

04
The Model Context Protocol, explained for people who do not write code

MCP is a standard way for Agents to plug into tools and data. Here is what it changes for someone who uses workflow tools rather than builds them, and why it is on our roadmap.

News·1 min·Nov 5, 2026
Optional
05
What to do when an AI vendor changes its pricing

Price changes on models and workflow tools arrive every few months. A short routine for finding out what it does to your daily workflows before the invoice does.

News·1 min·Nov 5, 2026
Optional