Assay Everywhere

Like Grammarly, but for your AI.

Grammarly checks how you write. Assay checks what your AI says about your company. The wrong price, spelled perfectly. A claim legal never approved, in flawless English. Caught before it ships, right inside ChatGPT, Claude, and Cursor.

Connect your AI Reads your rules at connect · zero workflow change
See a live seal

Zero workflow change

The rollout that doesn't need one.

The workflow change is zero. Not small. Zero.

Your people keep working where they already work. Assay connects as an MCP server, your AI reads the house rules at connect, and the same governed answer shows up in every host, sealed.

ChatGPT

"Meridian data is deleted within 30 days of termination, in your EU or US region."

Assay seal · verify
Claude

"Meridian data is deleted within 30 days of termination, in your EU or US region."

Assay seal · verify
Cursor

"Meridian data is deleted within 30 days of termination, in your EU or US region."

Assay seal · verify
ChatGPT Claude Claude Code Cursor Any MCP host Slack · briefs rolling out

The idea engine

Good ideas usually die in the chat where they happened.

Someone has a sharp GTM thought inside a private AI chat, and it's gone by lunch. Assay notices, asks, and, only if they say yes, files it, credited to them.

Assay · noticed something

"What if we led the Meridian deck with the 30-day deletion guarantee instead of burying it in the appendix? It's the thing their security team actually asked about."

Keep it? It'll be credited to you and queued for testing.

Captured · credited to Dana R. · queued for testing
It offers You decide Logged and attributed

The best positioning ideas your company has are already being spoken, once, into a chat window. This is the net under them.

Nothing is captured without an explicit yes. The author's name rides with the idea into testing, so credit lands where it's due.

The Assay Seal

For seven hundred years, you couldn't sell gold without a hallmark.

A hallmark didn't promise the ring would make you happy. It certified the metal was what the seller said it was, and who stood behind the claim. The Assay Seal is that, for what your AI says about you.

· Assay seal ·
ClaimDeletion within 30 days
Sourcepolicy.retention@v7
Checkedgraph v214 · 14:22
Verifyexample receipt →
verify.assay.example / r / 8f2a Example receipt

This claim was checked.

"Customer data is deleted within 30 days of termination."

Verdict4/4 claims grounded · passed
Sourcepolicy.retention · v7 · signed
Checked at2026-07-04 14:22 · graph v214
Recordsthe check ran · not that the answer is right

A signed receipt

Every governed answer carries a cryptographic receipt of exactly which claims were checked, against which version of your truth.

A public verify link

Anyone who sees the Seal can open the receipt. The check is inspectable, not a word you're asked to take.

Earned pixels

The Seal appears only on a real check that passed. No check, no checkmark. An unconfigured setup plainly says unsigned.

The draft mark

Work in progress carries a draft mark, not a Seal, so a half-checked answer can never masquerade as a sealed one.

The Seal is a record of the check, never a promise the answer is right.

That distinction is the whole ethic. A hallmark certifies the metal, not the buyer's taste. The Seal certifies the claim was checked against your approved truth, and gives anyone the receipt to confirm it. When nothing was checked, it says so.

House rules + access

Your AI reads the rules at connect.

The moment a host connects, it learns what it may read, what it may write, and how to ask. Access travels with the seat, and every write is a deliberate, two-step action.

/assay-pulse /assay-context /assay-check

Slash commands

/assay-pulse for what changed, /assay-context to ground a draft, /assay-check to verify a claim. Present the moment your AI connects.

Access travels with the seat

A connection can only ever read and write what that person's seat is permitted to. Revoke the seat, revoke the reach.

Writes are two-step

Changing the source of truth is never a side effect. It's proposed, then confirmed by a permitted human, then logged.

One surface, seven agents

The whole team, through one connection.

Connect once and the team is reachable from inside your AI. Here's what each does through the MCP today, stated honestly.

AI SEO & GEO AgentDoer · get found and cited

Grounds and seals answers about your category. Live in the MCP today.

Available now
AI CMOLeader · drives the work

Surfaces what's winning and what changed via /assay-pulse.

Early access
AI Social & ContentDoer · post safely

Grounds posts in your voice and your approved truth.

Early access
AI Product MarketerDoer · collateral that's current

Drafts from live nodes so nothing ships stale.

Early access
AI Sales EnablementDoer · rep-ready answers

Answers a rep's question on today's story, sealed.

Preview
AI RevOpsDoer · governed plays

Checks outbound copy against the gate before it runs.

Preview

Status is what each agent does through the MCP today, not a roadmap. The chips mean exactly what they say.

Straight answers

The seven questions people actually ask.

Isn't this just RAG? +

RAG retrieves text and hopes the model uses it. Assay grounds the answer in your governed, approved truth, checks each claim against it, and attaches a signed receipt for the ones that pass. Retrieval is a step. Governance with a verifiable receipt is the product.

Is this surveillance of my team? +

No. Assay checks what your AI says about your company, not what your people type. The idea engine only captures something when a person explicitly consents, credited to them and logged. It offers, you decide.

Is this just another surface to learn? +

No. It runs inside the tools your people already use. The workflow change is zero, not small. Zero. Your AI reads the house rules at connect and the checks are just on.

Isn't a badge on every answer just badge spam? +

The Seal is earned pixels only. It appears on a governed answer that passed a real check, never on an empty result or an unconfigured setup, which plainly says unsigned. No check, no checkmark.

Can't it just say "verified" without checking? +

No. The Seal is a signed receipt with a public verify link. It records that a specific check ran against a specific version of your truth. It's a record of the check, never a promise the answer is right.

Is there a free tier? +

You can connect the SEO & GEO agent and start free. The MCP connection reads your approved truth and mints the Seal on governed answers. Writing back to the source of truth is a governed, two-step action reserved to seats with permission.

Does this make me EU AI Act compliant? +

No. Assay produces readiness evidence, an audit log, and the artifacts a reviewer asks for. It doesn't certify you compliant, because no software can. Compliance is your determination, made with your counsel.

Connect your AI

Two minutes, one connection.

Add Assay as an MCP server in the host you already use. It reads your approved truth, mints the Seal on governed answers, and reads the house rules at connect.

# Claude · Settings → Connectors → Add MCP server
{
  "mcpServers": {
    "assay": {
      "url": "https://mcp.assay.com/sse",
      "headers": { "Authorization": "Bearer <your-seat-token>" }
    }
  }
}
Also: Gemini · Codex · Microsoft Copilot · any MCP host
Connect your AI Start with the SEO & GEO agent, free
Get the GC kit

Prefer to see what the engines say about you first? Run the audit →

Facts on this page are wired to our Truth Graph · last verified 2026-07-04 · Verify →