Tenancies and Chatbots in Chicago and Scotland

Chatbots have an obvious potential in the delivery of legal information. You ask a question and the bot, given varying degrees of  identity, answers. One of the latest entrants in the access to justice field is Rentervention. It is a joint project of three organisations: Illinois Legal Aid Online, an imaginative user of technology, the Lawyers Trust Fund of Illinois, the state’s collector and distributor of interest on trust accounts, and the Lawyers Committee for Better Housing. Reasonably enough, it only answers tenancy queries in Chicago but it also provides a model for international comparison – particularly because it is very like a project developed by Scottish Shelter.

In 2017, Scottish Shelter (the national campaign for the homeless) responded to a Scottish government initiative to use technology. This started life, explains Chatbots Magazine, as ‘Sheldon’ .. a conversational bot that sits in messenger platforms acting as an intermediary between the user and Shelter Staff. Allowing for the automation of administrative and repetitive tasks. Sheldon responds to users queries with advice and information on their rights as a private tenant. While also actively collecting the users information in a conversational manner, building a case file on the user that can be passed on to a Shelter staff member if further action is required.’

Sheldon proved the concept and then mutated into Alisa. It is now deployed by Scottish Shelter to answer questions about new rules for private renting. More ambitious plans to use natural language programming and to introduce a wider scope are in progress. But, the original intention was deliberately to start cautiously. One commentator, e-consultancy, observed, ’One of the biggest obstacles brands face when creating chatbots is limitations in technology. While NLP (natural language processing) theoretically offers users a richer and more interactive experience – one that mimics human interaction – this often takes a long time to come to fruition (as the bot learns natural speech patterns over time).These kinds of bots can also go awry, either failing to answer basic queries or worse – speaking in offensive language. Microsoft’s Taybot is the most famous example of this.’

Conrad Rossouw of Scottish Shelter is pretty clear about the role of bots like Alisa: ‘I don’t think that a chatbot can replace a real person, especially when providing essential advice but it can certainly help answer some of the basic questions your users might have, freeing up time for your advisers to answer more urgent queries.With this in mind, Ailsa tries to answer the question but if she doesn’t know the answer she does one of three things: Checks if we have a live chat operator available if so provide the link to chat; If a live chat person isn’t available, she’ll check if our helpline is open and provide the number if it is; If no live help is available, she’ll direct users to our Advice pages.’

Rentervention is much along the same lines, though less tied to one housing organisation. You can test it out from anywhere in the world but you need to be able to produce a Chicago zipcode. I can report that the system rejects codes for local courts but you can get round that by consulting a chicago real estate website to get the code of actual rented accommodation. You get basic information in the familiar interactive form. It is not very visual. The chat is accompanied by a picture of a little red robot but there is little personalisation. The Chicago project has clearly stayed clear of Scottish Shelter’s Sheldon/Alisa or, even more individualised, Mencap’s Aeren who announces herself with ‘My name’s Aeren. I love reading and acting. I went to mainstream school, got all my GCSE’s and then did a BTEC in Performing Arts. Let’s chat!’. 

It is unclear if those behind Rentervention knew about the Scottish Shelter project. I would doubt that they did: it has not received much publicity outside its own country. But, the existence of two very similar chatbots opens up the possibilities of direct trans-national comparison and the ability to pool learnings across different jurisdictions, something that can only expand as similar organisations in similar but different jurisdictions explore what can be done.

Leave a Reply