For agencies

Ship a client chatbot without building RAG for every retainer

Agencies already rewrite FAQs and hop between client inboxes. Point each bot at that client's site and PDFs, embed one script, and keep tenant data isolated. Growth includes 3 chatbots; Business includes 10 — one login for the studio.

  • Multi-bot accounts
  • Tenant-isolated retrieval
  • 7-day money-back on paid

Agency reality

You cannot staff a 24/7 inbox for every site you launched last quarter

Retainers cover design and campaigns. They rarely cover answering “what is your return window?” on ten different brands at 11pm. Clients still expect the site chatbot to know *their* policies, not a generic script you copy-paste.

Building a custom RAG stack per client kills margin. Sharing one knowledge base across clients is worse: it mixes answers and breaks trust. You need isolated bots with the same playbook.

  • Each client needs their own crawl, FAQs, and widget branding
  • Handoff should land on the client's support team, not your Slack
  • Plan limits are on the studio account — you add bots as retainers grow

How it works

Stand up a client bot in an afternoon, not a sprint

  1. Create a chatbot per client

    Your account can hold multiple bots (plan-dependent). Each bot is a tenant: its documents, conversations, and widget key stay scoped to that client.

  2. Ingest their content, not yours

    Crawl their public pages, upload SOPs and PDFs, add exact-match FAQs. Retrieval never searches another client's corpus.

  3. Embed and hand off

    Paste the widget script on their site. Connect WhatsApp or Instagram when their plan allows. Their agents take over with the full thread when the bot should not decide.

Built for studios

What agencies actually need from a chatbot product

•

Several bots under one billing account

Growth allows 3 chatbots; Business allows 10. You are not paying a new workspace tax for every landing page you shipped.

•

Isolated knowledge per client

Queries are tenant-scoped. Client A never answers from Client B's return policy.

•

Per-bot appearance and embed key

Colours, greeting, and widget key are per chatbot so each site looks like the client's brand, not a template dump.

•

Handoff with context

When the answer is not in the docs, the conversation goes to humans with the thread intact — your client's team, not a generic queue.

•

Analytics per bot

Volume and missed questions stay per client, so you can show value in the monthly report without mixing properties.

•

Honest about white-label

Remove our badge on Growth and above. Full white-label and SSO are Enterprise — we do not pretend otherwise on this page.

Compare

Agency chatbot vs one shared GPT vs building it yourself

Tenant-isolated knowledge

Reply
YesYes
One ChatGPT for all clients
No
Custom RAG per retainer
If you build it

Website widget + WhatsApp

Reply
YesYes
One ChatGPT for all clients
Not a site embed
Custom RAG per retainer
Weeks each

Time to first client live

Reply
~15 minutes
One ChatGPT for all clients
Prompt tinkering
Custom RAG per retainer
Months

You operate the ML stack

Reply
We do
One ChatGPT for all clients
OpenAI does
Custom RAG per retainer
YesYes

FAQ

Agencies asking before they try it

You can remove our badge on Growth and above. Full white-label (your product name, SSO, dedicated infra) is an Enterprise conversation — contact sales.

Get started

Add a client bot without adding a chatbot engineer

Create the bot, ingest their docs, paste the script. Keep each client's answers isolated.