Choose the service your agent provides before choosing every possible channel.
Customer channels
Multichannel AI agent with one place for its rules
Build a multichannel AI agent whose knowledge and behavior live in Prostir. Configure each supported delivery path for the people who need it.
For the usual MCP path, model-token cost to the Agent creator is $0: the customer's AI client supplies the model under that customer's subscription and limits.
Available
What is getting in the way
Maintaining separate copies of instructions makes it harder to know which answer or process each customer receives.
What changes
An owned agent with consistent source configuration and individually verified client or channel connections.
Customer channels
How Prostir gets you there
Describe one common job
Choose the service your agent provides before choosing every possible channel.
Connect the paths you need
Authorize the supported clients, widget or channels separately. Respect the setup and limits of each.
Verify each experience
Test identity, access, sources and actions in every intended destination before inviting users.
Available
What you can verify
- Shipped channel kinds are Telegram, Slack, email, WhatsApp, Instagram, Messenger, Microsoft Teams, and the web widget.
- Inbound messages run through the selected published Agent and return on the same configured surface.
- Every channel remains gated by publication, feature and plan state, a valid model selection, enabled credentials, and provider-specific requirements.
A good fit if
- Your customers already contact you through two or more currently supported surfaces.
- You want one owner-controlled Agent and knowledge boundary behind those conversations.
Not the right fit if
- You need every provider feature, unsupported identity method, or arbitrary messaging network.
- You need channel-native checkout or subscriptions that have not been proven for that exact Store and channel.
Questions before you decide
Does turning on Channels make every provider work automatically?
No. Each surface needs its own supported credential and settings, while the Agent also needs a valid channel model, publication state, feature access, and any required credits.
Can customers keep the same private memory everywhere?
Only when the channel can establish an allowed customer identity and grant. Unsupported proof methods remain gated; anonymous or cross-Agent shared memory is not implied.
Who pays for model tokens, and what do they cost the Agent creator?
For the usual MCP path, model-token cost to the Agent creator is $0. When a customer uses the Agent through a supported MCP connector in ChatGPT or Claude, the model runs in that customer's AI environment under the customer's subscription and limits. The creator pays for the Prostir plan, not those model tokens. AI Credits are needed only when the creator separately chooses a Prostir-hosted model run, such as a supported channel or widget. BYOK is optional and bills the creator's own provider account. Paid external tools remain separate.
Explore related options
Available
One service. A familiar way to reach it.
Keeping answers consistent gets harder with every channel. Start with one agent and verify the chat or channel your customers actually use. Start your 7-day Creator trial, no card needed.