Builds customer-facing chat agents in Python that follow your policies, approved wording and tool rules, for CX teams who want support bots on their own code and models.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- Canned Responses
Use Parlant to add approved wording examples: ‹what you need›
- Tool and Message Review
Use Parlant to check actions: ‹what you need›
- Simulated Tests
Use Parlant to run simulated test conversations: ‹what you need›
Install the CLI
pip install parlant
Setup guide: parlant.io/docs/quickstart/installation
Call the API
Auth An API key from Emcie
Setup guide: parlant.io/docs/quickstart/installation
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- APICLI
- Auth
- API Key
- Skills
- 5
Skills
Policies
Defines plain-language policies that the engine brings into a conversation only when they apply, with the tools each may use.
Canned Responses
Adds approved wording examples that the agent adapts to each conversation when a policy calls for exact phrasing.
Tool and Message Review
Checks actions such as refunds before they run and reviews replies before they are sent to the customer.
Human Handoff
Hands a live conversation from the agent to your human team in the same chat widget on your website or app.
Simulated Tests
Runs simulated test conversations with personas and links each reply to the policies and tool calls behind it.
