Your AI
Connect the assistant endpoint you already run. You control the model, prompt and memory; Meetext routes each question with the right customer's capability access.
Customer-facing AI
Ship your AI into your customers' workspaces.
Bring your own assistant or use Meetext-hosted AI in Slack and Google Chat, with that customer's approved capabilities and permissions. No assistant needed for capability access. Microsoft Teams onboarding is temporarily in Preview.
Your AI or Meetext AI
Your product. Their approved capabilities.
A useful answer. In their workspace.
Northstar / #customer-success
JJamieWhich accounts need attention?
✳
Only this customer's approved tools.Your product
Two accounts could use a check-in.
- Orbit · low adoption
- Forma · open support issue
✓ get_account_health · read onlyYour intelligence. Their context.
Choose the intelligence
Your AI. Our AI. Or no assistant.
The same customer-scoped capabilities and permissions support each mode. An assistant is a choice, not a prerequisite.
Meetext-hosted AI
Start without building an assistant. Meetext hosts a model using that customer's approved tools, with personal data masking, spend limits and pause controls.
No assistant
Expose approved capabilities through the destination's supported interface. Keep deployment, authorization, validation and monitoring without adding a hosted assistant.
The assistant is the easy half.
Most teams selling AI into enterprises already have one working. It answers well in a demo, against their own data, in an account they control. Then the first customer asks for it inside their Slack, and the work that follows has nothing to do with the model.
That work is the same for every customer after the first, which is exactly the kind of work that should be a dependency rather than a quarter.
What you would otherwise build
An app in every chat tool
A Slack app, a Teams bot registration, a Google Chat app. Each with its own manifest, its own event shapes, its own way of threading a reply and its own review process.
Knowing whose workspace this is
A message arrives with a workspace id and nothing else. Turning that into the right customer, with the right credentials, is the part that must never be wrong once, because being wrong means answering one customer from another's data.
Per-customer access to your own product
Your assistant needs to reach your systems as that customer, with that customer's permissions, limited to what they bought. Not as you, and not as everybody.
Consent, tokens and the day they expire
An enterprise admin approves the install. The grant belongs to them, refreshes on their schedule and gets revoked on their timetable. Somebody has to run that lifecycle per customer, forever.
A security review, per customer
Every enterprise buyer asks what your AI can reach inside their systems before it is allowed in. Answering that with a document somebody wrote by hand does not survive the second customer.
Streaming that does not look broken
A model takes twenty seconds. Twenty seconds of silence reads as broken, one message per token is unreadable, and every provider rate limits edits. There is a right answer and it is not obvious.
Bring your AI. Keep your voice.
When you bring your own assistant, Meetext carries the question and reply while your endpoint controls the intelligence. Hosting an assistant with Meetext is a separate choice; either way, access stays scoped to the customer.
The model
Your endpoint chooses and runs the model.
The prompt
Your assistant, your instructions, your behaviour.
The name
Your app identity on vendor-registered destinations. Google Chat uses the Meetext Marketplace app.
The conversation
We send a question and a thread reference. Never history.
What your assistant is handed
Not just the words. Every question arrives with that customer's own connection to your product, so your assistant can look things up and act for them through their credentials, limited to the version they installed and the capabilities they are entitled to.
That boundary is not advisory. It is the same per-customer endpoint their own AI tools would use, with the same isolation a security review asks about first.
One assistant, grounded in each customer's environment
Slack and Google Chat connect every question to the right customer, deployment version and approved MCP tools. Microsoft Teams onboarding is temporarily in Preview.
Where it can land
Questions arrive from Slack, Microsoft Teams and Google Chat. The deployment behind them models Asana, Atlassian, ChatGPT, Claude, Cursor, Google Chat, HubSpot, Linear, Notion, Salesforce, ServiceNow, Slack, VS Code and Zendesk, so the assistant and the rest of the installation are the same object with the same version and the same entitlements.
Questions
Whose AI is it?
Choose your own assistant endpoint, a model Meetext hosts, or no assistant. Your endpoint controls its model, prompt and memory. Meetext-hosted AI uses the customer's approved capabilities and entitlements, with masking and budget controls. The Meetext Agent that operates deployments is separate from either customer-facing assistant choice.
Do you store the conversation?
The vendor assistant bridge processes the current question and sends a stable thread reference rather than conversation history; your assistant keeps its own memory. Saved conversations with the Meetext Agent in the dashboard or customer portal are a separate feature, not part of that bridge.
How does my assistant get at my product's data for a specific customer?
Every question arrives with that customer's own endpoint and token attached, which is the same pair the customer's own AI tools would use. Your assistant calls your systems through it. What it can reach is bounded by the version that customer installed and by what they are entitled to, so it cannot call something you have not approved and cannot see another customer's data.
What if my assistant is down, or slow, or fails halfway?
The person asking is told something rather than left waiting. A reply that fails partway keeps whatever arrived and adds the reason. Your own error text goes to your event log where you can act on it, and never into your customer's channel, because a stack trace from your server appearing in their Slack is its own incident.
Can I try it before registering apps with Slack and Microsoft?
Yes. There is a Try it control on the product page that sends a question down the real path and shows you the reply instead of posting it into a channel, with the latency, whether the answer actually streamed, and which customer's capabilities it was given. That is how you find a broken endpoint, rather than by watching a customer find it.
Does this replace the MCP endpoint?
No, it sits alongside it. A customer whose staff use their own AI tools connect those to the MCP endpoint. A customer who would rather ask in Slack gets the assistant. Both are the same deployment, the same version and the same entitlements, so nothing has to be decided twice.
AIAnd one for your team
The Meetext Agent runs the deployments for you
Your assistant answers your customers. The Meetext Agent works for your own team: ask it to add a customer, check who needs attention or email a customer's admin, and it does it with your permissions, asking before any change.
Meet the agent- “Which customers need attention right now?”
- “Email Vercel that we are waiting on their admin.”
- “Cap Nike's assistant at $50 a month.”
Your next customer is waiting.You build the product.
You build the product.
We take it from here.
Connect a source, approve what ships and send your customer an install link. 2 customer environments free. No card required.