top of page

Argos Assistant

The goal was to make a quick and easy  voice-led user experience that really made the Argos tone of voice really come out in the voice experience. We wanted the Argos Assistant to be fluid and uncomplicated, whether you were using it at home or on the go. The skill is able to learn via NLP, as well as perform Error handling, Validation and Response.




UX / UI Lead


Alex Ayres | Louise Webber | Chris Crispin |  Kat West | Zubar Miah

GH - 320 - sstates_x2.png


This project centred around the following:

  • Developing a Voice UX tone of voice, and user experience for Argos’ first foray into Conversational Commerce.

  • With over 10% of UK consumers owning a smart home device (with continued growth), we see an opportunity for Voice to add value in the Argos shopping journey.

  • For MVP we wanted to focus on a core slice of our Argos offering:  finding & reserving the right product quickly and easily in order to learn quickly about the technology and appetite.

GH - 320 - sstates_x2.png


Creating the new Argos Assistant required close collaboration between different teams, specifically Google AI, our in-house engineering team and the UX team. Using our current AI and NLP learning bots, it was proving to be difficult to recreate, a playful, sparky natural language for the assistant.

It was important to bring everyone on the journey and show the value of applying design thinking to create a solution that solved the user problem while also being technically feasible. We spent a lot of time talking to users, stakeholders and members our store teams to ensure we had a clear view of all pain points and needs for this specific project. We tested different iterations of the solution ahead of launch. This helped us refine the final solution and prove our hypothesis.

  • Argos was an early adopter and with that comes growing pains.

  • We were the first partners with Google - Google informed a lot of design requirements, making it hard for the Argos brand to shine through.

  • Googles platform had lots of bugs and we needed incorporate a lot of work around to get a working version. The system was changing underneath us as we designed and coded - testing a few days later, and suddenly we realised that the behaviours had changed. Google was optimising in parallel to us, which made it really tricky.

  • Argos does not have the underlying services to support a lot of the new features we want to launch within Argos Assistant. Harder to quickly deliver personalised experiences.

  • Constrained by a very restrictive CMS that does not allow us to build pages aimed for editorial use, so getting the page to look modern and tech, was a challenge using very limited developed components and lots of restrictions.


Iterating with scale:

  • We spent a lot of time talking to users, stakeholders and members of our store teams to ensure we had a clear view of customer struggles & pain points and needs for this specific project.

  • We tested different iterations of the solution ahead of launch. This helped us refine the final solution and prove our hypothesis on our established customer problem statements. We tested the Argos Google Action with real consumers in a contained, ring fenced environment.

  • Over several weeks we launched an internal Argos audit. Employees from all departments reported back issues and feature gaps which were then prioritised for resolution. 



I learned many valuable lessons during this process. I will not to just start coding with not a lot of structure or direction, tangle data or kickoff.  For Day 2, I will encourage the team to think more about the essence of conversational design and how we can optimise and explore the channel further, while working with our partners at Google to understand the underlying tech and it’s limitations better. I think it will behoove us to bring other key stakeholders onboard earlier and develop a proof of concept and language which closer aligns to the Argos brand.



  • Continue to answer customer queries and meet with customer intent by optimising our content to match.

  • Optimise our help services to accommodate Voice Search, which is 2x as keyword search. Make sure we are catering to those Voice customers who have a higher intent and are searching in question form.


  • Explore scalable solutions that enable us to respond to intent across a variety of channels and touch points. Looking at serving on customers from a platform agnostic POV, not just on Google Home devices. 

Reducing contact

  • Intelligent query handling to free up our customer contact agents to help customers when it really matters.

  • Integrating Bots within our Live Chat and social messaging AP

bottom of page