News
Research Report
Business Leaders CX Report: What’s Working and What’s Not in AI-Driven CX
The Gist
- New toolkit: PolyAI launched its Agent Development Kit (ADK), designed to let enterprise developers build and manage AI customer service agents using standard software development tools and workflows.
- Speed claims: The company says early customers cut development time from weeks to hours, though specific customer names were not disclosed.
- Platform play: The ADK complements PolyAI's existing no-code Agent Studio, positioning the company as a full-spectrum platform for both technical and non-technical CX teams.
Enterprise CX development teams have long faced a frustrating tradeoff: adopt purpose-built AI platforms that lock them into rigid interfaces, or cobble together custom solutions outside the tools they actually use.
PolyAI is making a case that neither compromise is necessary.
The London-based conversational AI vendor this week launched its Agent Development Kit (ADK), a developer-first toolkit designed to let engineering teams build, deploy and iterate on AI-powered customer service agents using their existing languages, IDEs and version control workflows — rather than working inside a constrained vendor UI.
Table of Contents
- What the PolyAI ADK Does
- Customer Claims and Internal Metrics
- Where It Fits in PolyAI's Platform Strategy
What the PolyAI ADK Does
The ADK positions itself as an AI-native development environment for contact center and CX automation work. According to the company, developers can use coding assistants — including tools like Cursor or Claude Code — to generate and refine production-grade agent logic directly against PolyAI's platform and codebase. Inputs can include diagrams, spreadsheets or APIs, and the resulting agents can be managed with standard enterprise software practices: version control, code reviews and collaborative development workflows.
The company argues the current state of CX AI development is the problem it's solving.
"Most AI platforms for CX force developers to work inside a UI, cut off from the way real software gets built," said Shawn Wen, co-founder and CTO at PolyAI. "With the ADK, we're changing that. Developers can now build AI agents with the same tools, workflows and flexibility they use to build any other critical system."
Beyond initial build, PolyAI says the ADK supports continuous improvement loops. By connecting to monitoring tools and automated QA pipelines, agents can identify performance gaps and self-improve over time — a shift the company frames as moving from static automation to adaptive systems.
Related Article: 4 AI Shifts That Will Separate CX Leaders in 2026
Customer Claims and Internal Metrics
PolyAI cited two early enterprise deployments to illustrate the speed gains the ADK delivers, though it did not name either customer. The company reports that one of the world's largest utility companies built complex flows in hours rather than the multiple weeks previously required, and that one of the UK's largest banks processed hundreds of FAQs in minutes rather than hours of manual work.
On the internal side, Wen said more than 60% of PolyAI's own engineering work is now done autonomously through ADK-powered workflows, with developers in a review-and-guidance role. The company is now extending that same capability to customers.
PolyAI said the ADK's reusable production patterns are informed by more than 500,000 hours of real-world deployment work across its enterprise customer base, which includes Marriott, Caesars Entertainment, PG&E and UniCredit.
Where It Fits in PolyAI's Platform Strategy
The ADK is a complement to, not a replacement for, PolyAI's existing Agent Studio, which the company describes as a no-code and low-code environment for non-technical users. The company frames the combined offering as a spectrum: technical teams get code-first flexibility through the ADK; business and operations teams continue to work through the lower-friction Studio interface.
Webinar
Apr
27
Where Contact Center AI Is Actually Headed
A straight read on where the contact center platform market is going and what it means for your next technology decision.
Register
Webinar
May
12
How Marketing Teams Can Take Control of the Web Experience
See how Veo and Kvalifik put marketing in the driver's seat, shipping faster and growing qualified bookings by 150%.
Register
Webinar
May
14
Two Audiences, One WordPress. Is Yours Ready?
The practical steps to making your WordPress portfolio ready for both human visitors and AI agents.
Register
Webinar
May
19
From Content Sprawl to Competitive Advantage: A Knowledge Operations Roadmap
How automation, AI and a centralized content platform turn knowledge fragmentation into a scalable competitive advantage.
Register
Webinar
May
20
From AI Investment to CX Results: What Enterprise Leaders Need to Know
Move beyond experiments. See how top enterprises scale AI for CX results.
Register
Webinar
On demand
AI for Your DXP: Connect What You Have, Transform How You Work
Most AI strategies stop at the platform—but work happens elsewhere. Bring intelligence into Teams, email, tickets and CRM.
Watch Now
That dual-track approach is increasingly common in enterprise AI platforms, where vendors are trying to serve both IT and business stakeholders without building two separate products. Whether PolyAI's execution delivers on both fronts — or stretches the platform too thin — remains a question for customers working at scale.
The Agent Development Kit is now generally available.
Have a tip to share with our editorial team? Drop us a line: