The reason AI copy sounds generic is that nobody told it otherwise
A model with no brand context defaults to the average of everything it has read. That average is exactly the voice you have spent years trying not to have.
“🚀 Excited to announce a game-changing update that will revolutionise how teams collaborate! We’re thrilled to unveil our latest innovation. #innovation #growth #futureofwork”
“Workspaces shipped. One account, one bill, every client kept separate. It took longer than we said it would and we should have built it first.”
Six fields, and the reason each one earns its place
The single biggest lever on whether output reads as yours. It is prepended to every generation, so it governs rhythm as much as vocabulary.
Changes what gets explained and what gets assumed. The same fact written for engineers and for buyers is two different posts.
Your rules, in your words. This is where legal constraints, positioning boundaries and house style live.
The vocabulary you want reinforced, and by omission the vocabulary you have been trying to stamp out for two years.
Generated visuals inherit its palette and composition instead of drifting into whatever the model felt like today.
Real files the agent can attach, described well enough that it picks the right one for the post it just wrote.
One workspace, several voices
An agency does not have a brand voice — it has eleven of them. A founder-led company has at least two: the company page and the person. Kits are per workspace and named, so the right one gets picked per post rather than per account.
How agencies use thisBrand voice questions
- What is a brand voice AI?
- It is a stored description of how your brand writes and looks, applied automatically to every piece of AI-generated content. In PostMCP that description is a brand kit — voice, audience, guidelines, keywords, a style image and reusable assets — and it is read before the model writes a single line.
- How is a brand kit different from just prompting well?
- A good prompt works once. A brand kit works every time, for every person in the workspace, and for the AI agent running unattended at 6am. It also survives model changes — you are describing your brand, not tuning a specific model’s quirks.
- Can I have more than one brand voice?
- Yes, and most serious users do. A workspace holds multiple kits, so an agency can keep a separate voice per client, and a company can separate its corporate page voice from its founder’s personal account. Each generation names the kit it should use.
- Does the brand kit affect generated images too?
- Yes. Image generation accepts a brand kit ID, and the kit’s style image steers the visual output — palette, composition, mood. It is the difference between a set of images that look related and a set that obviously came from different prompts.
- Can my AI assistant read the brand kit over MCP?
- Yes. Listing brand kits is one of the read-only MCP tools, so Claude, ChatGPT or Cursor can fetch your voice, audience and guidelines before drafting — the same source of truth the built-in agent uses.
- Does everyone on the team share the same voice?
- Brand kits belong to the workspace, so anyone drafting there writes against the same definition. That is usually the point: consistency across a team is exactly what a documented voice is for.