March 17th, 2026
Improved
Ever wondered whether your escalation guidance is being used and how often?
Or how many of your escalations are a result of your guidance?
Well, wonder no more!
We've just released escalation usage.
You can see it by going to Improve > Guidance > Handover, and Escalation.
You'll be able to see what percentage of your escalations come from your escalation guidance overall and by individual types of guidance in the last 30 days.
This will allow you to improve the specificity of your guidance and ensure that you can get it really dialled in.
Go and take a look at yours today.
March 9th, 2026
Our self-learning articles have been live for just a few weeks but we’re already improving them based on your feedback.
Now when your weekly changes are made you’ll:
Get an email letting your know which articles have been updated
When you go into the self-learning section of your Dashboard (Improve > Self-learning), and click into an article you’ll see the additions and deletions in green and red.
You can learn more about self-learning here and keep the feedback coming!
March 5th, 2026
Improved
Want to collect an email address from a lead or customer in Zendesk when they escalate a conversation?
Now you can with our email collection Task for Zendesk Messaging.
When the lead or customer triggers an escalation in any form, you can set your AI agent to collect details (email, phone number, whatever you want) that will be added directly into Zendesk so no details are lost.
If you're interested in setting this up for your agent, get in touch with us via our chat.
March 2nd, 2026
Improved
How do you rate your AI agent’s performance and track it over time?
Now when you are testing your AI agent in the Dashboard you can score your AI agent.
Score the agent on:
Whether you’d send the response to a customer
An overall score for the response
What can be improved
Any additional comments
You can then track these as you make updates to your agent.
To use the new QA scoring go to Dashboard > Improve > Test then click on any of your test questions to start scoring.
February 9th, 2026
New
Your AI agent can now constantly improve, learning from your human agent replies, automatically.
Self-learning is the ability for your AI agent to learn from your human agent conversations, ensuring that you don't have to manually update its knowledge on an ongoing basis.
And, importantly, tell us how they could be better!
February 3rd, 2026
Improved
On top of our recent launch of Tasks, you can now use AI to create your tasks, instead of having to fill in all the fields individually.
Just describe in plain English what you want the task to do, hit “Generate Task” and watch the AI populate all the relevant fields.
It’ll even tell you when if a Tool would be necessary for the Task to work.
To try it out, log into your Dashboard and head to “Tasks & Tools”, then click “+New”.
January 29th, 2026
New
Don't already have help docs/a help center? No problem, we can help you generate one automatically from your historic tickets.
There are lots of reasons you may want to train on your past/historic tickets:
December 12th, 2025
Improved
We have now made our Tasks feature available to everyone.
This means you can build complex multi-step processes for your AI agent to follow.
You can read about how you can use Tasks here, and get some inspiration for how you can use them here.
To test them out today, just login to your Dashboard and go to "Tasks & Tools".
November 20th, 2025
Improved
Occasionally with AI you don't always get an answer you expect, with our improved Inspect feature you can better understand your new AI agent's responses.
Just click Inspect answer then ask your question to better understand the answer.
November 17th, 2025
It’s been a little while coming (and a good amount of work!) but I am happy to announce we have now obtained our SOC-2 Type II certification!
SOC 2 Type II is an independent audit that shows a company is following strict security and privacy practices to protect customer data.
While a Type I report checks that the right controls exist, a Type II report goes further by verifying that those controls were actually working effectively over a period of time.
Hopefully this should help us to:
Build trust: Proving to you (our customers and partners) that we handle your data securely.
Reduce risk: Ensuring we have strong processes around security, availability, and data handling.
Operate maturely: Demonstrating consistent, well-run, industry-recognized internal security practices.
If you would like access to our Trust Center or SOC-2 report, just get in touch with us via our chat.