Brand memory · Restaurant & Hospitality
Brand voice AI for restaurants
The Personal brain is one brand memory — your voice guide, offers, FAQs, past posts and the things you never say — that every other agent reads before it drafts a hook, a script or a reply to diners.
The problem
Every new freelancer has to learn how a restaurant like yours talks.
Your voice lives in your head, a few old posts and maybe a doc nobody reads. So every new freelancer, agency or AI tool gets re-briefed — and still writes something that isn't quite you.
For restaurants the stakes are specific: one draft that gets allergen answers the kitchen hasn't confirmed, and menu or price details that have changed wrong costs more than the time saved. The brand memory is where those lines are written down once.
Tuesday's special, from the person who made it
We only make this one when the fish is right, not on a schedule. Tonight it's right. Table for two, or ask for it to go.
Signal · A tracked competitor switched to kitchen-first reels last week.
How it works
What the Personal brain agent does, step by step.
Restaurants on Instagram and TikTok. Every step ends in a draft, not an action.
- 01
A 30-minute brand interview
We ask how you talk to diners, what you offer, what you're asked most and what you'd never say.
- 02
Learn from your posts
The brain reads your past captions and replies to pick up tone, phrasing and sign-offs.
- 03
Write down the hard lines
Rules about allergen answers the kitchen hasn't confirmed, and menu or price details that have changed are stored explicitly, and every draft is checked against them.
- 04
Update from approvals
When you edit a draft before approving it, the brain proposes an update to the memory — which you also approve.
What you get
Drafts you can use, with the reasons attached.
Part of the Personal brain side of Oryxia, reading from the same brand memory as the other six agents.
- A voice guide written from warm, specific about the food and never over-polished
- Your offers, prices and FAQs in one place every agent reads
- An explicit do-not-say list that drafts are checked against
- A change log showing what the brain learned and when
You own the memory — and every change to it.
The brain never rewrites itself silently. Suggested updates to your voice or offers wait for your approval like any other draft.
- 1Edit any entry directly
- 2Approve or reject learned changes
- 3Export or delete it whenever you like
A good fit if
- You've tried AI writing tools and everything came out generic
- There are things a restaurant like yours must never say, and you want them enforced
- Several people touch your account and you want one source of truth
Not a fit if
- You want a different persona on every post — the brain is built to keep one consistent voice.
- You want a delivery-platform or reservations integration — Oryxia drafts content and replies; your booking system stays yours.
FAQ
Fair questions.
01Is my brand memory used to train anyone else's drafts?
No. Your brain is scoped to your workspace. It's read by your agents only, and you can export or delete it.
02How are the “never say” rules enforced?
They're stored as explicit rules, not tone suggestions. Drafts that touch them — for restaurants, typically allergen answers the kitchen hasn't confirmed, and menu or price details that have changed — are flagged for you instead of being quietly smoothed over.
03Will it understand how a restaurant like mine talks to diners?
It starts from a 30-minute brand interview and your own past posts, aiming for warm, specific about the food and never over-polished. Your do-not-say list — for restaurants, usually allergen answers the kitchen hasn't confirmed, and menu or price details that have changed — is enforced on every draft, and you approve each one.
Related agents
See what your agents would draft first.
The free Social Audit maps your niche, competitors and hook gaps, and shows the agents working on a demo workspace.