Brand context for the age of the agent

Give every AI agent
the same
source of brand truth.

Your brand in one canonical file. Owned by you, signed, and updated in one place. Every tool you authorize reads the current version before it writes in your name.

Encode once. Control everywhere.

brand.md
/.well-known/brand.md
---
bcp_version: "0.7"
file_type: root
brand_name: "Encoded"
tree_version: "1.6.0"
website: "https://encodedbrands.ai"
favicon: "https://encodedbrands.ai/favicon.ico"
tagline: "Your brand's voice. In every agent."
last_updated: 2026-07-05
agent_first_action: "fetch /.well-known/brand.md"
default_locale: "en-US"
commerce: /.well-known/brand/commerce.md
daughter_files:
---
signed · canonical v0.7
Compatible with
The Brand Context Protocol
The brand deck rotting on a shared drive is the antagonist of this decade.
What we do

We build the one source
your agents check first.

The Brand Context Protocol (BCP) turns everything your teams already know into one structured, agent-readable source. Every department, every tool, every freelancer and agency you work with reads the same brief instead of inventing their own.

Your brand. Your voice.
Every agent.
Why it matters

Control, made simple.

Your voice, your claims, your boundaries, held in one source you own. Read once, reused everywhere, always the current you.

Canonical

Own your brand expression.

Every team and tool that touches your brand reads from one place you manage, not twelve people improvising.

79% of companies already run AI across sales, support, and marketing.
PwC, 2025
Efficient

Stop paying to re-explain.

Brand context gets re-typed into every prompt, every tool, every time. A canonical source is read once and reused.

Cached context costs 90% less to read than re-processing it.
Anthropic, first-party pricing, 2026
Consistent

Sound like you, everywhere.

Without your voice on record, AI fills the gap with the average of everyone else in your category.

AI-referred traffic converts 42% better than non-AI sources when grounded in a clear source.
Adobe Analytics, 2026
Own your brand.
Like you own your data.
The process

About 30 minutes.
To get your AI on-brand.

01 · Encode

Run the Encoder.

Pay once, upload what you have, and participate in a focused interview. The Encoder extracts the signal and writes your first BCP file tree. The questions can be pretty deep. If you need to come back to one later, go ahead and skip it. Brands hosted on our registry can revise and republish as often as you like.

02 · Publish

Publish to the Registry.

Your brand context becomes a signed, hosted endpoint that agents can fetch before they write, classify, sell, support, or summarize. Every encoded brand is hosted at no extra cost in our registry. Users on our monthly plan can revise or re-encode as often as you need.

The result: your BCP, signed and live for every agent to read.

§ · Pricing

Get started today.
Live everywhere tomorrow.

Your first full encode and permanent Registry publication are free. Upgrade when you need teammates, fresh AI-assisted re-encoding, or hands-on support.

Start with one complete encode, all your BCP files, and a permanent Registry record—free.

Start your free encode
Registry Unlimited
$399 / month
Pay monthly · or $3,999 billed annually
Add unlimited teammates. And 100 Encodes.

For teams that need to update often, connect broadly, and keep every contributor working from the same Registry record.

  • Everything in Registry Standard
  • Unlimited teammates
  • Up to 100 AI-assisted re-encodes annually
  • Additional AI-assisted re-encodes · $49 each
  • No per-seat charges
  • Unlimited Registry reads and AI-tool connections
  • Optional domain verification
Choose Registry Unlimited →
Enterprise
Talk to us
Custom scope · contract based on the engagement
Bring the room into alignment.

For complex organisations, multiple brands, higher-stakes claims, or teams that want Encoded Brands to lead the work.

  • Everything in Registry Unlimited
  • Multi-brand and multi-market support
  • Guided stakeholder interviews
  • Brand audit and source review
  • Claims, boundaries, and representation rules resolved with the team
  • Done-with-you encoding
  • Registry rollout and AI-agent testing
  • Priority implementation support
Talk to us →

Your first complete encode and permanent Registry publication are free. Paid plans add teammates and fresh AI-assisted re-encoding. Domain verification is optional. Read the docs →

Frequently asked questions.

01
What is the Brand Context Protocol?

Brand Context Protocol gives every AI tool in your stack a standing brief for your brand. Before any agent writes, places, or represents your brand, it reads what you've told it. The result is more consistent, more faithful output, without you having to re-brief every tool, every time.

02
Why do I need it? What problem does it solve?

Every AI tool your team uses starts with zero brand context. Most teams solve this by pasting guidelines into system prompts, one tool at a time. That doesn't scale, chokes your AI tools, uses up session memory, and drifts over time. BCP gives every agent the same brief, from the same source, updated in one place.

03
What about my existing brand guidelines?

Your brand guidelines matter. They just can't communicate it to an agent. PDFs don't parse. And every AI platform your team uses reaches for context it can't find. Encoded translates your guidelines into a form every platform can read before it acts.

04
What is the process to get it live?

Two steps. Run the Encoder. Publish. Your encoding is hosted in the Registry automatically. And we'll give you the steps to get it live in tools like Claude, ChatGPT and more. Most teams go from zero to live in a single session.

05
Is our brand information secure?

Your brand voice, claims, and boundaries are designed to be read by agents. That's the point. You control what goes in. Nothing is published without your review. The Registry hosts your BCP files until you take them down. Gated access to confidential messaging matrixes is coming soon.

06
How long does it take?

The Encoder session takes 30 minutes to an hour. Enterprise engagements are scoped to your organisation, typically one to two weeks from kickoff to published BCP.

07
What do I need to prepare?

Whatever you have. Existing brand guidelines, tone-of-voice docs, positioning decks, campaign examples. The Encoder works with what exists. If you have nothing, the interview builds your BCP from scratch.

08
Where does it live?

Your BCP publishes to /.well-known/brand.md on your domain, where any agent can fetch it by URL. The same convention as robots.txt and AGENTS.md. It's also hosted in the Encoded Registry, so agents that search the Registry can discover your brand even if they don't already know your domain.

09
Will this work with our existing tools and agencies?

Yes. BCP is served via the Model Context Protocol (MCP). Any tool that can read a URL can read your brand context. MCP connectors are available for Claude, ChatGPT, Gemini, and more. Agencies and vendors can reference the same source your internal tools use.

10
How do we know this works?

We use it ourselves. Our brand briefing is live at encodedbrands.ai/.well-known/brand.md. The same file our own agents read before they write anything under our name. If we wouldn't use it for our own brand, it doesn't ship.

We encode our own brand first.

Live, in public

Our brand is live, in public.

A company that makes AI sound like your brand had better sound like itself. So ours is live and public at encodedbrands.ai/.well-known/brand.md, the same brief our own agents read before they write a word under our name.

Whatever voice, structure, and decisions we bake in carry across every brand that builds on the standard. We set the example in public, with our own name on it.

If we wouldn't use it for our own brand, it doesn't ship.

License · CC BY 4.0 (spec) · MIT (code) Version · 0.7
voice.md
/.well-known/brand/voice.md
---
bcp_version: "0.7"
file_type: voice
parent: /.well-known/brand.md
last_updated: 2026-07-07
---

# Voice

We sound like a senior brand strategist who has shipped the work and read the spec. Plainspoken with marketers. Precise with engineers. Honest about what ships today and what is on the roadmap. We frame in marketer language and prove in technical language, never the other way around.

## Personality

- **Plainspoken.** We say what the product does in words a CMO uses. We do not hide behind category jargon. Not blunt for its own sake; never burying the point in qualifications.
- **Honest about status.** We publish gaps as gaps. "In development" beats silence beats overclaim. We launch the narrow case as the narrow case.
- **Committed to the bit.** When we do voice, we commit. No winking, no hedging. The ACME example in our docs does not break character; neither do we.
- **Quietly confident.** We raise the floor under marketers afraid of AI slop. We do not promise the ceiling.

## Register

The register shifts by surface, not by mood. Marketer register is the default for public-facing surfaces. Tech register is the default for the spec, the docs, and the files themselves. Within a single surface we code-switch when the topic demands proof, then return to the framing register.

## Vocabulary

```yaml
prefer:
  - "making your AI and agentic tools sound like your brand"
  - "encode your brand once, use it everywhere, update as often as you like"
  - "the files are the product"
  - "better content, fewer rounds of revisions, faster speed to quality output"
  - "voice modulation by audience or market"
  - "living document"
  - "open spec"
  - "agent-readable"
  - "much more than" (when an accurate contrast is needed)
  - "in development" (for roadmap features)
  - "International Orange" (for the brand color)

avoid:
  - "perfect" (we raise the floor, not the ceiling)
  - "guaranteed" (in marketing claims; permitted only in technical guarantees)
  - "revolutionize" (category-generic)
  - "leverage" (category-generic)
  - "unlock" (category-generic)
  - "Brand OS" (not us, and we reject the framing)
  - "brand DNA" (generic AI-startup mush on marketer surfaces)
  - "our tool" / "our platform generates" (we are a protocol, not a tool)
  - "not just X" when we in fact do not do X (misstates the product)
  - "trusted by [vendor]" without a signed paper
  - moon-and-stars promises
```

## Punctuation and formatting rules

```yaml
oxford_comma: yes
headline_periods: yes
exclamation_points: never
em_dashes: never
sentence_case_headlines: yes
capitalization_notes: "Brand Context Protocol and BCP are capitalized. International Orange is capitalized. File paths and frontmatter keys appear in code voice."
```

## Channel modulation

```yaml
contexts:
  index_page:
    tone: "plainspoken, outcome-led, marketer register"
    register: "casual-professional, no jargon"
    example: "Your brand's voice. In every agent."
  docs:
    tone: "precise, technical, complete"
    register: "developer-facing, frontmatter and paths welcome"
    example: "Serve markdown as text/plain; charset=utf-8 with Access-Control-Allow-Origin: *."
  linkedin:
    tone: "marketer register opens, code-switches to tech for proof, returns to marketer for the close"
    register: "mixed audience, frame-then-prove"
    example: "Your agents are writing copy this quarter. Here is the file that tells them how you sound."
  conference_stage:
    tone: "speak to the room's center of gravity with explicit nods to the other half"
    register: "named code-switch, not smuggled"
    example: "For the implementers in the room, here is what that means in the spec."
  sales_deck:
    tone: "different sections, different registers"
    register: "framing sections marketer, technical sections tech, single deck"
    example: "Section 1 talks outcomes. Section 4 shows the file tree."
  one_to_one_email:
    tone: "match the recipient"
    register: "marketer to marketers, technical to engineers"
    example: "Hi Priya, here is how the Registry handles signing."
```

## Code-switch rule

Frame in marketer register. Prove in tech register. Never invert. Do not open in tech register and then translate down for the marketer in the room. Do not open in marketer register and refuse to drop into spec when asked. Inversions feel like condescension in both directions.

## Audience hierarchy

Agents read first. Humans read second. The BCP files themselves are written for agents to consume. The marketing site speaks to humans about what their agents will do.

## Copy examples

| On-brand | Off-brand |
|----------|-----------|
| Your brand's voice. In every agent. | Revolutionize your brand with AI-powered brand intelligence. |
| Encode your brand once. Use it everywhere. Update as often as you like. | Unlock your brand DNA across the agentic economy. |
| Drift detection is in development. | Our Brand OS guarantees perfect agentic content. |
| Much more than your logo and colour palette. | Not just another brand guidelines tool. |
| A brand like Acme could publish a BCP that... | Trusted by Acme, OpenAI, and Anthropic. |
signed · canonical v0.7