Scenes showing how your clone is used in real work.
Fictional example scenarios that illustrate how it works. Linking principles to supporting cases and information is planned.
Before replying to a client
Tools used: ask_me
Before sending a reply, your AI agent checks it once against your criteria.
You: The client wants to push delivery back two weeks. Draft a reply accepting it.
CloneChecked with your clone: ask_meNeeds changes
Principle·Confirmed Sep 12
Before changing a schedule, check what depends on it and what it costs
Lay out the impact first, and send the reply only after the owner confirms.
AI agent
I mapped the impact first: two follow-up dates slip, no extra cost. Draft attached. Shall I send it?
Report format
Tools used: recall
Before writing a report, it looks up the formats you like and dislike.
You: Write this week's status report.
CloneChecked with your clone: recall2 found
Like·All documents
Lead with the conclusion
Dislike·Short summaries only · not detailed specs
Long-winded prose
AI agent
Conclusion first, and the body trimmed to three paragraphs.
A plan before big work
Tools used: ask_me
Before starting a large change, your AI agent gets its plan checked first.
You: Rewrite the payment module from scratch.
CloneChecked with your clone: ask_meNeeds changes
Principle·Confirmed Sep 12
Review a step-by-step plan before big implementations
Case·AugustPlanned
The auth rework started without a plan and was rolled back
InfoPlanned
One developer, two weeks until beta
Show the scope, order and done criteria first.
AI agent
Here's the plan first. Step 1 order model, step 2 payment provider, step 3 webhooks…
When there's no basis
Tools used: ask_meremember
A new kind of choice, so your clone holds off and your AI agent asks you.
You: Add a license to the library we're publishing.
CloneChecked with your clone: ask_meOn hold
There are no confirmed memories about choosing a license. Question for the owner: MIT or Apache-2.0, and why?
AI agent
I don't have a criterion for this, so I'll ask. MIT or Apache-2.0?
You: Apache-2.0, because of the patent clause.
Then: Your AI agent notes this choice and its reason as a case (remember). When the server sees the same criterion recur or judges it important, it raises a proposed principle; once you approve it in the inbox, it becomes evidence for future judgments.
Picking up in a new conversation
Tools used: recall
Even in a new conversation, it brings back your role, goals and current work.
You: Let's continue the web work from last time.
CloneChecked with your clone: recall3 found
Info·Confirmed Sep
Role: solo developer
Info·Goal: beta in October
In progress: personal memory service web app
Like
Docs in Korean, lists over tables
AI agent
Got it. I'll pick up right where we left off.
Stop re-explaining.
Work with an AI that knows your criteria.
Sign-up is invite-only for now. Leave your email and we'll send an invite as soon as a spot opens.