SShogo Learn

Library

Every guide and one-prompt build from Russell's videos. Free, no account needed. Copy a prompt, paste it into Shogo, and see what it builds.

Guides

2026-10-30 · REVIEWMake the hard questions an agent's jobWhat you'll have running: a dev team of agents where every card has to answer four questions before it reaches you (*Is this the safest way? Is it the cheapest way? What could this break? Which tests prove it works?*) and a one-block Judgement from QA that you2026-10-30 · LESSONSMake your agent write down what it got wrongWhat you'll have: a small file of one-line lessons that every task reads at startup — plus the three questions that stop a "lesson" from being a restatement of the bug you just fixed.2026-10-30 · ROLESStop paying the big model to do the cheap workWhat you'll have: a team split by role across two models — the expensive one plans and reviews, the cheap one executes — and the one sentence you put in the plan so the cheap model doesn't start second-guessing it.2026-10-28 · EVALSTurn a real moment from your workspace into an evalWhat you'll have running: a small suite of evals built from moments that actually happened in your workspace. Each one is a prompt, a seeded workspace, mocked tools, criteria scored in three phases, and a list of anti-patterns. You re-run the suite whenever yo2026-10-24 · LOOPGive your agent a way to check its own workWhat you'll have running: an agent that, before it says "done", opens your app, looks at it at phone width, hits the endpoint with `curl`, runs the test that proves the change, and shows you all three in its reply. You judge the change from a screenshot instea2026-10-24 · SIXSix ways to run an agent in 2026 — the one-prompt buildWhat you'll have: the exact prompt that built the decision table in the reel, the steps to build it yourself in one message, and what to check before you trust what comes back.2026-10-23 · POSTMORTEMThe one prompt behind the pageWhat you'll have: the exact prompt I gave Shogo for the incident-postmortem page in the reel, why each rule in it is there, and why the small line at the bottom is the part I actually care about.2026-10-21 · CLEANUPAgents ship it, another agent cleans it upWhat you'll have running: a cleanup agent that goes back over every card your agent team finished, picks up the crumbs (dead code, a helper written twice, a component nobody renders, code that works but takes a minute to understand) and writes the tests that g2026-10-21 · TEAMRun your dev work with a team of agentsWhat you'll have running: one channel where you post ideas in plain words, and a team of agents (a planner, three developers and QA) that turns each one into a planned card, a tested branch and a pull request, handing work to each other in the open. You make t2026-10-21 · REFLECTThe expensive model is the coach, not the typistWhat you'll have running: an agent called Reflection, powered by your biggest model (I use Opus 5.5), that, every morning, reads everything your agent team did in the last 24 hours, asks "how did this happen?" about every mistake, and writes a short lesson int

One-prompt builds