From dead ends to clear paths: How I redesigned a chatbot fallback for BMO Assist—Catherine Bryce Skip to main content
Catherine Bryce
Experience Designer | IA, Governance & Content Systems

From dead ends to clear paths: How I redesigned a chatbot fallback for BMO Assist

The challenge: Help users succeed on their first try

BMO launched a new chatbot, BMO Assist, to support everyday banking. With 760,000+ users and 1M+ sessions, traffic was strong. But half of those chats ended in failure.

When the bot wasn't confident, it said: "I'm sorry, I didn't understand that." That left customers stranded without guidance or next steps.

BMO Assist chatbot showing a generic fallback reply
A poor user experience. The chatbot couldn't match a response even if it were close.

The problem: fallback was a poor user experience

While the long-term plan was to improve intent recognition through training, I proposed a content-led solution that could help immediately:

"What if fallback wasn't the end of the conversation, but, instead, helped them drive forward?"

That's how the fall-forward model was born.

The goal: prioritizing outcomes over AI accuracy

We set clear targets to shift focus from precision to progress:

  • Raise the response success rate from 45% to at least 80%.
  • Reduce exits after fallback.
  • Improve positive feedback.
  • Define success in terms of customers completing tasks, not just the AI guessing right.

My approach: turn fallback into fall-forward

I owned the content strategy for a new model that gave customers choices instead of dead ends.

Create options, not apologies

Short acknowledgement → "Try one of these" → 2–4 clear CTAs → safe escalation.

Design a scalable CTA system (300+ options)

  • Verb + noun → "Lock card"
  • Noun only → "Account balance"
  • Question → "Why am I receiving alerts?"

Work across functions

  • With PM: set new KPIs.
  • With design: tested fit within UI.
  • With engineer/QA: spec'd behaviour and edge cases.
Old experience flow: fallback response leads to contact us New experience flow: full fall-forward response suggests relevant CTAs

Real examples

BMO Assist offering suggested options after a low-confidence match BMO Assist fall-forward response with clear next steps BMO Assist guiding a customer to update contact information

The results? Users didn't just stop at fallback. They moved forward.

Within the first week of launching the Fall-Forward Model, the chatbot's response success rate jumped from 45% to 86.5%—nearly doubling its effectiveness overnight.

13,150
Fall-forward responses invoked in the 1st week
90%
Increase in correct responses
43%
Responses contributed to total thumbs up

Why it matters: building trust in a new channel

For many people, BMO Assist was their first time trying digital self-serve with the bank. A poor fallback would have eroded confidence quickly. By replacing a dead end with clear choices, we made the channel feel more reliable and worth coming back to.

Read the full case study on UX Content Collective.

← All projects Next: IVR lean UX workshop →