
Last week my wife and I headed out to Luray, Virginia to relax for a few days without our kids. We stayed in a cabin at the Shadown Mountain Escape which is located right outside of Shenandoah National Park. We hiked the Appalachian Trail each day, read a lot, watched a lot of movies, and generally just tried to relax and unwind. It was lovely. If you ever wind up going, tell Karen and Ralph that I said hi.
What I’m working on at Help Scout
I finally got access to GPT-3 a few days ago and have been playing around with it and brainstorming applications at Help Scout and beyond. Specifically I wanted to see what kind of responses it would generate to support emails customers had sent us.
Here’s a real conversation I received today in the Preceden inbox:
Hello,
I upgraded my Preceden account this month, but it turns out its not a tool I will be using. My project management system can create a grantt chart and that is sufficient for my company’s needs. I would like to request a refund.
Thank you, Edna
Plugging that into the script I set up for this (which I seeded with some examples of real responses in Help Scout):
Hello Edna,
I’m sorry to hear that you won’t be using Preceden. I’ve refunded the account for the remaining days of the month.
If you have any other questions, please don’t hesitate to contact us.
Not bad right?
Thing is, it doesn’t have any idea what it’s talking about. For example, Preceden charges yearly and I give full refunds (not prorated) so the response about the partial refund for the month isn’t accurate.
Still, pretty interesting.
What I’m working on at Preceden
A worthwhile investment I made a few years back was creating this list of timeline maker tools. It is IMHO the most comprehensive list out there and over time it has come to rank well for search terms like “timeline software”. Because Preceden is at the top of the list of course so it winds up driving a decent amount of leads and sales.
This week I added two new tools, Kronoli and ChronoFlo, bringing the total to 35 tools.
What I’m working on at Timeglider
I recently decided to shut down Timeglider, a competitor timeline maker tool that I acquired last year.
After I cancelled the active subscriptions, I emailed those people as well as anyone who had used it in the last year to inform them about the closure and how to migrate their timelines to Preceden if they wanted.
But what about everyone else who had used it prior to that? All time, Timeglider had about 500k sign ups. Emailing everyone though seems unnecessary because many of those never did anything in the app. Limiting it to those that had created at least 11 events got the number down to 100k.
I imported their detailed (email, sign up date, timeline names) into a database in Preceden and then set up a rake task to email a bunch each day to inform them about the closure (I chose a rake task because signing up and trying to use like Mailchimp to email 100k people with a new account seemed like a bad idea). Here’s an example email:
Hi Elijah,
You’re receiving this email because you signed up for Timeglider in 2018 and still have 2 timelines on the site.
My name is Matt and I purchased Timeglider from its prior owner last summer. There aren’t a lot of people using it these days so I’ve made the tough decision to shut Timeglider down at the end of November. This will allow me to focus my efforts on Preceden, my primary timeline maker tool.
Here’s a list of your timelines:
* French Revolution timeline
You have a few options:
* If you don’t care about your timelines anymore, there’s nothing you need to do
* You can download a CSV of your data so it’s not lost when the site shuts down
* You can download a CSV and import it into Preceden to continue working on your timeline
* You can use the Timeglider jQuery widget to host your timeline on another site
For instructions on all of these options and answers to common questions, check out our Timeglider Closure FAQs.
Sorry for any hassle this causes.
Please don’t hesitate to respond if you have any questions.
Matt Mazur
info@timeglider.com
I started small and ramped up the daily emails as I gained confidence that the message was solid and that Timeglider didn’t have any issues that might cause problems (it had a few).
The last of the emails went out today:

Preceden uses SendGrid to its emails, including these going out to the Timeglider users. Over the course of sending out these emails my reputation score dropped from 99% to 79% due to a fair amount of bounced emails (since many of these users signed up 10+ years ago) and a few spam reports.

Scores between 70% and 80% are categorized as “This is considered a poor reputation and you should consider taking action to identify and fix problems with your sending practices.” Fortunately since its through the 100k emails this should start to rise back up to shortly.
The responses were overwhelmingly positive with lots of people thanking me for telling them and wishing me luck on Preceden.
I haven’t set up reporting for this yet, but it did seem to drive a lot of Preceden sales too as these people moved their timelines over to Preceden.
What I’m studying
I finished DataCamp’s Introduction to Deep Learning in Python, Introduction to Deep Learning with Keras, and Advanced Deep Learning with Keras courses. The last one there was probably the most difficult course I’ve done yet. Four courses to go.
Also started reading Hands-On Machine Learning with Scikit-Learn and TensorFlow which is fantastic. For anyone interested in machine learning who doesn’t want to go through an online course, this book is a great place to start.
What I’m listening to
Chai Time Data Science, a podcast where the host, Sanyam Bhutani, interviews folks in the data science community with a focus on those who compete in Kaggle competitions. It’s got me pumped about diving into Kaggle in the coming year to level up my ML skills.
What I’m watching
Speaking of AI, I’ve been watching Raised by Wolves on HBO. If you like dystopian sci-fi movies, you’ll enjoy this show.
You can watch the entire first episode for free on YouTube:
That’s it for now my friends, thanks for reading 👋