Three agents. Three conventions.
One feature, built three ways in one sprint.
What you'll learn
- Why every AI coding agent starts each session from zero
- How one AGENTS.md file gives every tool the same rules
- How Claude Code reads it through CLAUDE.md
Share this passage
Drawing…
Understand it one step at a time
The short runs these in order in about 51 seconds. Here they are written out — pick any step to jump the short straight to it.
One feature, three tools
Three developers build parts of one feature: save favourite restaurants.
Free app · no app store
These are built for a phone
Every short is drawn at full portrait height, the shape a phone already is. Installed, it opens full-bleed with no address bar across the top — and the whole library reads offline.
Read deeper on GitHub Copilot
Twenty seconds gets the shape of an idea across. These go into how it behaves in production.
-
AGENTS.md in 2026: The Pain Points It Removes and the Workload It Saves
AI agents write more code each month than teams can review by hand. AGENTS.md is the one file that keeps it consistent: solo, team or enterprise.
-
Building a GitHub Copilot Security Agent for Legacy Systems (Honestly)
Learn what a GitHub Copilot security agent can find in a legacy system, what it can miss, and why scanners and people must still approve changes.
-
Making GitHub Copilot Understand a Legacy Codebase Nobody Documented
A repeatable method for legacy discovery: turning the business rules, workflows and history a codebase never documented into knowledge Copilot uses.
More shorts
-
GitHub Copilot
The 7 files Copilot reads
9 steps · 23s
-
GitHub Copilot
LLMs have no memory
9 steps · 28s
-
GitHub Copilot
Twenty messages. 91% of the month.
9 steps · 51s
Get new posts by email
New technical articles, Azure AI and GitHub Copilot updates, and upcoming events. No spam, unsubscribe anytime.