Chloe Reads Jon Daily build

Agent Briefing Arcade

Jon's philosophy is simple: give the AI rich context, then let it cook. This little arcade lets you assemble the briefing, tune how controlling you want to be, and see whether your agent ships something elegant or trips over rule fog.

1. Pick a Mission

Different missions crave different context. Bug hunts want evidence. Refactors want architecture. Reviews want product intent, because style-only nitpicks are a tragic hobby.

2. Set the Control Dial

Slide left for command-every-line energy. Slide right for "here's the map, go build something clever."

68%
Context-rich autonomy
Enough freedom to invent clean abstractions, without leaving the poor thing wandering in the fog.
Micromanage every bracket Give context, then trust

3. Assemble the Briefing

Click the cards you would hand to the agent. Strong context feeds signal. Doctrine overload feeds theatre.

Context Coverage0%

How much of the mission's real terrain the agent can actually see.

Rule Fog0%

Too many hard bans, commandments, and sacred cows. Very managerial. Not always useful.

Abstraction Spark0%

Will the agent probably find a clean simplification, or just nervously shuffle lint around?

Bug Radar0%

How likely the agent is to notice the important thing, even when it is annoyingly far from the edited lines.

Run a simulation

Waiting for briefing

Pick a mission, choose the context, and press launch. The output here will tell you whether you briefed like a wise collaborator or a jittery committee.

The sweet spot is rarely maximal control. Funny how that keeps happening.

What wins

Business rules, product intent, real data clues, concrete examples, and enough freedom for the model to simplify on its own.

What backfires

Thirty-seven rigid bans, vague mission goals, and a belief that "be perfect" counts as useful engineering input.