Tell Builder which questions the agent should answer and when a client should contact you.
Private client delivery
Client-facing AI agent for help between conversations
Build a client-facing AI agent that helps approved clients with a defined task. Keep your shared method in Prostir and grant access without handing over the configuration.
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
Clients need answers after a call, while your working instructions and source material need controlled access.
What changes
A client-facing service with exact access rules and boundaries around what each person can use.
Private client delivery
How Prostir gets you there
Describe the client job
Tell Builder which questions the agent should answer and when a client should contact you.
Set the boundaries
Add approved knowledge, choose allowed actions and configure access for the intended people or domains.
Try the client experience
Verify sign-in and supported-client access with an authorized test user before sending the connection instructions.
Available
What you can verify
- New Agents are private by default and begin with OAuth protection rather than anonymous access.
- OAuth policy uses exact verified emails or normalized exact domains and rejects suffix-style matching.
- API keys are Agent-scoped, named, expiring, revocable, rotatable, shown once, and stored hashed.
A good fit if
- You deliver an Agent to named clients, companies, or approved integrations.
- You need the customer to use the Agent without editing its core configuration.
Not the right fit if
- You want an untracked public link to count as private access.
- You need several coworkers to edit shared Tasks, Files, Data, and Knowledge; that is a Company use case.
Questions before you decide
Can I allow a whole client company?
Yes, with a normalized exact-domain OAuth grant when that policy is appropriate. Similar-looking domains, suffixes, and unverified email claims do not qualify.
Can a client change the Agent?
No. A standalone Agent remains author-controlled. Clients can use their explicitly owned personal context, but they cannot mutate the shared instructions, tools, Skills, or Agent Knowledge.
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
A client agent with a clear boundary.
It sounds like your clients need easier answers while their information stays under control. Build one private agent, test its access with the intended client and review the result together. Start your 7-day Creator trial, no card needed.