THE FRESH-START BRIEF
From AutoJate (autojate.com/fresh)

Your AI gets dumber the longer one chat runs. It's not the model, it's the chat:
every answer gets read against everything before it, so a long chat goes vague,
repetitive, or wrong. The fix isn't a smarter model. It's a fresh chat that knows
where you left off.

This is the block to paste. Fill the brackets, paste it as the FIRST message of a
new chat, and the new session picks up exactly where the old one died.

====================================================================
THE BLOCK  (copy everything between the lines)
====================================================================

You are picking up work in progress. Read this brief before doing anything.

GOAL
[What I'm trying to get done, in a sentence or two. The finish line, not the task list.]

CURRENT STATE
[Where things stand right now. What exists, what works, what's decided. Paste the
real thing, the draft, the code, the plan, instead of describing it.]

WHAT CHANGED
[What happened since this started. Decisions made, direction changes, anything that
turned out different than expected.]

WHAT FAILED
[What we already tried that didn't work, and why if you know it. Don't suggest these
again.]

NEXT STEP
[The one thing to do first. Start here.]

====================================================================

WHEN TO REACH FOR IT
- The answers start slipping (vague, repetitive, or wrong). That's the rot.
- You're switching to a different task in the same project. New task, new chat.
- You walked away frustrated. Come back to a fresh chat, don't scroll up.
Rule of thumb: serious work gets a fresh chat early and often. Don't wait until
it's obviously broken.

THREE THINGS THAT MAKE IT WORK
1. Write it at the end of the OLD chat, not from memory. Before you close the dying
   chat, tell it: "Summarize this work as a handoff brief: goal, current state, what
   changed, what failed, next step." Fix anything it got wrong. It fills the block
   better than you will an hour later.
2. Paste real material, not descriptions. "The draft is pretty good" tells the new
   chat nothing. Paste the actual draft, code, or plan.
3. One brief, one goal. Two projects is two fresh chats with two briefs. Mixing them
   is how the rot starts again.

WHY IT WORKS (the receipts)
Researchers call it "context rot." Chroma tested 18 top models and accuracy dropped
as the input grew, at every step, not just near the limit. Anthropic's own Claude
Code reports even the newest model (Opus 4.8, a million-token window) starts slipping
around 40% full and flags you to start fresh by ~48%. Newer models raise the ceiling.
They don't remove the floor.

--------------------------------------------------------------------
This is how I run every working session with AI, every day.
Want your whole business wired like this? Free call, no pitch: autojate.com/book
AutoJate * autojate.com
--------------------------------------------------------------------