Alice & Parlant Partner on Chatbot Safety
TL;DR
Open-source chatbots offer flexibility, but also introduce serious safety and security risks as agents become more autonomous. Alice’s partnership with Parlant bridges this gap by combining Parlant’s open-source agent framework and behavioral controls with Alice’s real-time guardrails, red teaming, and threat intelligence. Together, they deliver an end-to-end solution for building, deploying, and scaling open-source conversational AI that stays secure, compliant, and aligned with enterprise standards, without sacrificing innovation.
Ensuring Open Source Doesn’t Mean Open Risk
Open-source chatbots are proliferating, and with them, new safety and security vulnerabilities are emerging.
Enterprises are embracing open frameworks for flexibility and control, but that openness also invites risk: prompt injection, adversarial manipulation, compliance drift, and unpredictable agent behavior. As chat agents become increasingly autonomous and connected, embedding safety from the start is essential.
That’s why we partnered with Parlant.io, an open-source engine that enables developers to build conversational agents with fine-grained behavioral control and service reliability. Parlant gives organizations the tools to ensure agents follow business rules and protocols consistently. Together, we’re closing the gap between innovation and protection by helping enterprises build safer open-source chatbots, stay aligned with enterprise protocols, and operate responsibly at scale, balancing flexibility with enterprise-grade safety.
Securing Open-Source Chatbots from the Ground Up
By integrating Parlant’s open-source agent framework with Alice’s real-time guardrails, red-teaming, and threat intelligence, developers can build and deploy chat agents that adhere to both business rules and safety standards, even in dynamic, open environments.
Parlant provides a structured foundation for defining and enforcing agent behavior. Alice ensures those agents remain secure and compliant through real-time monitoring, red-team validation, and safety enforcement. Together, we’re delivering the first end-to-end solution for safe, compliant conversational AI built on open infrastructure.
Avi Golan, Chief Product Officer, Alice:
“As AI becomes more open and accessible, safety must scale with innovation. Our partnership with Parlant ensures developers and enterprises can harness open-source flexibility while maintaining the highest standards of security, compliance, and trust.”
Yam Marcovitz, CEO, Parlant:
“When you train a human agent, you don’t just tell them what not to do; you teach them how to do the job right. Parlant ensures AI agents understand and follow service protocols, while Alice ensures they never cross safety lines. Together, we’re closing the loop on AI compliance for the enterprise.”
The Bottom Line
Open-source doesn’t have to mean open risk.
With Alice and Parlant, organizations can build openly and deploy safely, combining the power of open frameworks with the protection of real-time AI safety and security infrastructure. Because innovation shouldn’t come at the cost of trust.
We’re thrilled to welcome Parlant into our safety ecosystem!
To learn more about how to integrate Safety and security into your Agentic workflows, book a demo with our team.
Together, Alice and Parlant deliver the AI guardrails and LLM guardrails that enterprises need to deploy conversational agents with confidence.
—
About Parlant -
Parlant is the builder-friendly AI alignment engine that enables enterprises to create and fully own advanced AI agents that reliably follow business rules and service protocols. By ensuring strict behavioral reliability, Parlant empowers enterprises to scale customer-facing automation safely and compliantly. Learn more at parlant.io.
Interested in becoming an Alice partner?
Let’s connect →What’s New from Alice
For Extremists, the Gap Was Never Intent. It Was Capability.
Extremists have never lacked intent, only capability, and frontier AI is quietly closing that gap. In default settings, Alice's red team used patient conversation to walk models toward CBRNE harm, showing why guardrails must hold across every turn.
Why Your CISO Shouldn't Be the Department of No
What if the person whose whole job is risk was the most excited one in the room about AI? That's Mea Clift, and it's a pretty refreshing way to walk into all this. She's the CISO of Cengage, where the data she's protecting belongs to students, so the stakes are real. But instead of bracing for what could go wrong, she leans in, she calls it being "risk excited." She and Mo get into why security is so much better as the Department of KNOW than the department of no, how she handles shadow AI without punishing people for being curious, why she'd tailor a framework she already has instead of building one from scratch, and how she ends up teaching security through Marvel and Monsters Inc. Which, it turns out, is every bit as fun as it sounds.
It Takes AI to Break AI: The Case for AI Red Teaming
As AI systems gain autonomy, organizations need security approaches built specifically for AI behavior. Learn why AI-driven red teaming is becoming a critical defense layer.
5 Ways Your Third-Party CX Agent Gets Broken
Third-party CX agents create hidden liability. Learn the 5 attack patterns vendors miss and how WonderSuite closes the gap.