Meet Wren, the agent behind your agents. Now in Dialog Studio.

Read the announcement
Podcast - Episode 103

Can you build a custom AI agent in 10 minutes?

About the show

Hosted by Nikola Mrkšić, Co-founder and CEO of PolyAI, the Deep Learning with PolyAI podcast is the window into AI for CX leaders. We cut through hype in customer experience, support, and contact center AI — helping decision-makers understand what really matters.

Summary

In this episode of Deep Learning with PolyAI, Frank Ferro sits down with Ruari Phipps, Senior Forward Deployed AI Engineer at PolyAI, to show — live — what's possible when developers get direct access to a voice agent platform. The conversation is part discussion, part demo: Ruari builds a working hotel AI agent from a single PDF spec, pushes it to a branch, runs automated tests, and merges it for deployment in under ten minutes.

This episode answers the question: what happens when you don't need to choose between speed and control?

Together, Frank and Ruari cover:

  • Why developers were constrained before tools like the Agent Development Kit were introduced
  • What changes when you pair ADK with tools like Claude Code or Cursor for building and iteration
  • How AI coding tools enable parallel testing: running ten simulated conversations at once instead of manually typing through each one
  • What the live demo shows about going from zero to 80% with AI coding tools — and where human tuning still matters
  • How PolyAI's years of best practices are embedded directly in the ADK's documentation and scaffolding, so developers aren't starting from nothing
  • What building flows, entities, and functions looked like before — and how much faster things move now

Frank and Ruari produce an agent that handles knowledge base Q&A and a multi-step booking flow, plus is ready to deploy across voice, chat, and SMS — all from a blank project and a one-page spec. It's a clear illustration of how far we've come, and how quickly we can build.

Key takeaways

  • The ADK unlocks what the platform kept sandboxed: Before, everything had to happen through the platform — custom scripts, external data sources, and bespoke integrations were impossible. The ADK is a Git-like CLI with pull, push, branching, and merge, bringing a real software development lifecycle to agent building without changes hitting live until they're tested and merged.
  • AI coding tools take you from zero to 80%: Paired with Claude Code or Cursor, boilerplate like knowledge base topics spins up in minutes — work that used to take a day. Human tuning takes it the rest of the way, jumping in to fix the hiccups an initial version always has.
  • Parallel simulated testing is the hidden unlock: Coding agents spin up multiple versions of themselves to run ten test conversations at once, across chat and simulated voice, using dynamic wordings that push the agent harder than static test scripts — catching edge cases a single human QA-er never would.
  • Best practices are baked into the scaffolding: PolyAI's years of deployment experience live in the ADK's documentation, templates, and validation, so developers — and the coding agents they use — aren't starting from nothing. A flow that would have taken an hour of manual configuration comes together, validated, in about two minutes.