The weekly loop

What the loop is

Side projects rarely stall on code. They stall because nobody has said out loud what is actually holding the thing up, so the evenings go into whatever is nearest. The loop is three sessions that fix that, and it is the same loop a lot of teams already run at work, pointed at your own project instead.

Name the blocker that is really holding the project. Size one experiment that produces evidence about it. Then look at what the evidence said.

The three sessions

Each one is a conversation with your own agent. You start it by asking, and your agent fetches the session from Senvi and runs it.

Refinement

Say "run refinement" at the top of your week. Your agent asks what is in the way, pushes past the first comfortable answer, and stops when there is one blocker left, in your words. What gets written down is that blocker and the thing it puts at risk.

Sprint plan

Say "plan the sprint" straight after refinement. Your agent sizes one experiment against the hours you actually have this week, not against how big the blocker feels. It writes down the experiment, and what result would count as an answer.

Retro

Say "run the retro" at the end of the week. You go through what happened and what it told you, including the weeks where the answer is that you did not get to it. You come away with your read on the experiment, and where that leaves the question you were trying to settle.

Where it shows up

Every session your agent records lands as a typed step, not as a note somebody has to read later. The plan panel on your dashboard reads those steps, so your dashboard and your next session start from the same place.

Cadence is yours

Senvi puts nothing in your calendar. Your first session is where you and your agent settle on a rhythm. If you want a reminder for it, use the calendar you already keep.

What any of this costs is answered in one place, near the top of Connect your agent.