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

Read the announcement
Podcast - Episode 108

What happens if your AI agents get 1% better every day?

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

An agent that improves every day compounds into a very different agent within months. That's the bet behind Wren. For a few years, the story in AI has been agents that do the work; Wren is the next step, an agent whose job is to improve other agents. PolyAI's new release watches how your customer-facing agents perform in real conversations, finds what's working and what isn't, and helps your team act on it, from a small refinement to a significant fix.

In this episode of Deep Learning with PolyAI, Nikola Mrkšić talks with Arkadiusz Kwapiszewski, PolyAI's Head of Agent OS and one of the people behind Wren, about why this is a real change in how enterprises build and improve their agents. The core idea is that agents should learn from real production interactions. The signal that matters is what happens on live calls with real people, and it beats any amount of extra training data.

They also get into who actually uses it. Wren has put agent development in the hands of people well beyond engineering, and inside PolyAI, 95% of production changes now ship through it. Arkadiusz makes the case for cutting out the middleman: whoever holds the context, a builder or even an executive, can make the change themselves, watch it get validated against real data, and move on.

Wren is also how PolyAI builds PolyAI now, which tells you where Arkadiusz thinks the whole industry is heading.

Watch the full episode to hear how an agent that improves other agents changes the way enterprises build.

Key takeaways

  • From a “deist” coding agent to an interventionist one: The first iteration of Wren built your agent from specs and backed off; now it stays engaged — reviewing every production call, surfacing a morning list of recommendations, and implementing fixes you approve with a click. It's an adaptive loop where the agent gets roughly 1% better every day, and one customer saw booking conversions rise 30% just by working through the list.
  • Real call data is the antidote to AI slop: Production conversations act as a regularization function no human could provide — you can't review enough calls yourself (about 50 a day is the human ceiling). Every recommendation links the real calls behind it, replicates the issue in simulated conversations, shows the fix working, and keeps monitoring after you approve, so trust is built incrementally.
  • Whoever holds the context should make the change: Human-to-human handoffs are the real bottleneck, so Wren cuts out the middleman — builders, call center managers, even executives ship changes directly, and roles flatten into part-engineer, part-product. Around ten customers now exchange 2,000+ messages a month with Wren, 95% of PolyAI's own production pushes go through it, and cheap experiments on 1–5% of calls replace internal debate.
  • Self-healing is not self-improvement: Fixing friction — bugs, gaps, frustration — is detectable and can run largely autonomously, while self-improvement is KPI-driven: redesigning flows and experiments against North Star metrics like booking rate, with humans engaged only for business rules and missing content. Like Waymo, autonomy grows as trust does — Nikola bets someone goes “Uber auto mode” within months.