AILoadout
PLATFORM GUIDE · CHATGPT

Use a Loadout
with ChatGPT

Attach the `.loadout.md` file to a new chat, or open it and paste the complete Markdown. Then tell ChatGPT to load the file and follow it.

ทดสอบ Core flow แล้วAILoadout v0.2 draft
RUN IT

Four controlled steps

The interface differs; the safety contract stays the same.

1

Start a new chat

Keep unrelated context from changing the job.

2

Attach or paste the file

Add the `.loadout.md` file. If the extension is rejected, open it and paste the complete Markdown.

3

Load the contract

Say: “Load this Loadout, collect inputs first, and follow its approval gate and output contract.”

4

Check Done means

Judge the result against the declared outcomes, warnings and completion criteria—not presentation alone.

START COMMAND

Tell the client what must not drift

Paste this after attaching or pasting the Loadout.

Load this Loadout and follow it exactly.
1. Summarize Purpose, Risk, prerequisites and unavailable tools.
2. Ask only for missing inputs before doing the Steps.
3. Never skip Never, approval or Done means.
4. Use the declared output format; fall back to structured Markdown.
CAPABILITY

What is actually supported

Status separates the portable core from account-dependent capabilities.

01

Core Loadout

Prompt, rule, workflow and structured Markdown

Tested
02

File

ChatGPT supports common text documents; paste the contents if `.md` is rejected

Conditional
03

MCP / Apps

Only capabilities enabled for the account and workspace can run

Account-dependent
04

Visual

Charts or tables when available; structured Markdown otherwise

Runtime-adaptive
LIMITS

Know when to stop

A correct blocked result is safer than pretending a missing capability exists.

  • Do not assume every connector exists on every plan.
  • For a long file, explicitly preserve Never and Done means.
  • External actions must show the payload and wait for approval.
PRIMARY SOURCES

Product facts, not assumptions

Capabilities can change; check these sources and the tested date.

Core flow tested by AILoadout on 23 Jul 2026; connected capabilities remain account- and surface-dependent.