Better than prompts
Parlant gives you structured control to change every aspect of your agents’ behavior—instantly, because while few of us can script out entire interactions from scratch, we still know something is off when we see it. Great interactions evolve with time, and you need a rapid feedback loop to react and iterate, without worrying about breaking other behavioral configurations.
Supervised and conformant
It’s hard to let go and trust an AI, especially if it tends to get "creative." Parlant helps you stay sane by monitoring and double-checking every agent response to ensure that it consistently adheres to your configurations, resulting in correct and conformant responses. It also filters out inappropriate and malicious user inputs from ever reaching your agents, making it a good fit for sensitive use cases that require compliance.
Guided API integrations
Reliable integrations need more than just giving agents access to your APIs, because APIs are hardly ever self-explanatory. Parlant’s vendor-agnostic, turbo-charged tool-calls implementation lets you show agents the why, the when, and the how of using your APIs. Better yet, you can give different instructions on how to use the same tool in different scenarios for different goals.
import { ParlantClient } from 'parlant-client';const client = new ParlantClient({ environment: SERVER_ADDRESS });const agent = await client.agents.create({name: "Scooby",description: "Technical support specialist",});