We’ve released a new version of the PHP SDK for Fuzzy.ai. Version 0.2.0 includes:
- full API support including all Agent CRUD methods
- better error handling
- Agent, Evaluation, and Feedback objects for better object-oriented patterns
We’ve released a new version of the PHP SDK for Fuzzy.ai. Version 0.2.0 includes:
Some of our Google Sheets Add-on beta users have been using it to do some really interesting stuff. One of my favorites is the company that is using it to identify their best customers by creating custom user scores using Fuzzy.ai and user data from Intercom.
Here’s how you can build something similar:
First, export user data from Intercom (Instructions here) and upload it to a new Google Sheet. It should look something like this:
Given all of the data available in Intercom, you can really easily do a lot here. To get started, let’s narrow it down to a few columns:
With these columns, we can easily get a few useful facts about each customer:
You can add columns and use an easy formula in Google Sheets to calculate the number of days between today and the Signed up and Last seen dates:
And an if/then statement to show whether or not the user is on a paid plan:
=if(P2 = "free", 0, 1)
The result is a sheet like this:
(To help you get started quickly, here’s a copy of this spreadsheet. Just go to the File > Make a Copy menu to make a copy of it in your own Google account.)
If you don’t already have a Fuzzy.ai account, you can sign up here to try it for free.
Next, let’s decide on a few rules to start things off. These are a pretty obvious place to start:
Let’s also say that rules 2,3 and 4 are much stronger signals than rule 1, so we can give rule 1 a lower weight.
Here’s what those rules might look like in Fuzzy.ai:
Take note of your Fuzzy.ai API key and the Agent ID of the agent you created above. You’ll need them for the next step.
If you haven’t already made a copy of the sample spreadsheet above, you can do that here.
Once the add-on is installed, go back to the Add-ons menu > Fuzzy.ai > Settings and enter your API key and Agent ID.
With the Fuzzy.ai Google Sheets add-on, you can use the function =FUZZYAI() to send data to Fuzzy.ai and display the result. It expects inputs in the following format:
=FUZZYAI(<name of input 1>, <value of input 1>, <name of input 2>, <value of input 2>, etc)
So for this example, paste this formula into cell B2 (in the User Score column):
=FUZZYAI("daysSinceSignup", D2, "daysSinceLastSeen", F2, "webSessions", G2, "paidPlan", I2)
A score should appear in that column. Just copy and paste that formula into B3 -> B10 to get the rest of the scores.
And with that, you should have a working version of this example! Try changing some of the data in the spreadsheet to see how it affects the score.
The goal here, of course, is to show a pretty simple example of how to do this. We’ve seen users do similar things to create lead scoring, do churn risk analysis, and much more.
Some of our users have built agents to do this type of user score and then send that score back to Intercom daily as custom user attributes.
We’re excited to announce the release of a Fuzzy.ai add-on for Google Sheets. With this add-on, you can test your Fuzzy.ai agents directly in Google Sheets without having to do any integration with code.
To get started, follow this link or go to the Fuzzy.ai listing on the Google Sheets Add-on Marketplace and install the add-on.
Once it’s installed, go to Add-ons > Fuzzy.ai > Settings and put in your API key and the ID of the Fuzzy.ai agent you’d like to use.
Once you’ve entered your API Key and Agent ID, you can make a call to Fuzzy.ai using this formula:
=FUZZYAI("<name of first input>", <location of first input value>, "<name of second input>", <location of second input value>, etc...)
=FUZZYAI("Number of shares", A2, "Number of likes", B2, "Age in minutes", C2)
This add-on is a quick and easy way to start using Fuzzy.ai without any code at all. Try it out and let us know what you think!
(Bonus for developers: If you’re curious to learn more about how the add-on works, check out the project on GitHub and file issues for any comments/feedback.)
A common application of Fuzzy.ai is in powering custom recommendation engines. For many companies, generic solutions don’t offer enough flexibility (or require too much work manually setting up links between all of the different products in the catalog), and building a custom recommendation engine from scratch requires way too much time and effort.
To show how easily it can be done, we’ve put together an open source Product Recommendation plugin for Drupal Commerce stores that lets anyone spin up their own product recommendation engine with Fuzzy.ai.
When a user is looking at a product page on an online store, the goal of this recommendation agent is to identify the other products in the catalog that might be relevant.
The way Fuzzy.ai differs from other machine learning platforms is that we let developers encode their own knowledge about how a system should work as a set of rules. The Fuzzy.ai API uses those rules to provide recommendations. Over time, as feedback is sent to Fuzzy.ai on how well the rules performed, the API learns and improves automatically.
In our sample recommendation agent, we identified a few rules that might show affinity between the current product and each of the other products in the catalog:
Here’s what those rules look like when created within Fuzzy.ai:
Keep in mind that these were purposely chosen because they can work generically for many online stores. Specific stores may have other rules that make sense, for example, a clothing store may want to show products for the same season and so might add rules like:
If you want to try it for yourself, sign up for a Fuzzy.ai account and follow the instructions in the Drupal Commerce Recommendation Engine plugin on GitHub.
This project is meant as a starting point. Every developer will likely have their own modifications to make to the rules and integration in their ecommerce platform.
In an upcoming blog post, we’ll talk about how to add feedback into this recommendation engine so that it can learn based on actual customer behavior over time.
One of our favorite quick demos of Fuzzy.ai’s capabilities is to show how easy it is to take your own Twitter feed, score each of the Tweets, and surface the most relevant ones. It’s one of the first new agent templates we built for the platform and it’s a lot of fun to try out.
To show how easy it can be, we put together a Ruby on Rails project to help you get started and get more acquainted with Fuzzy.ai. You can find that project on GitHub.
Getting your Tweet Relevance agent set up will take just a couple of minutes. Once you’ve signed up for a free Fuzzy.ai account, go to your Dashboard and take note of the API key shown on the top left-hand corner of the page. You’ll need it later.
Next step is to create your Tweet Relevance agent. There are two ways to do this. The easiest way is to use this link and just click on Create.
Alternatively, you can create it manually by logging into your dashboard, clicking on the ADD AN AGENT button. From there, select the TWEET RELEVANCE template:
That will automatically create a Tweet Relevance agent like the one below:
This initial template starts off with just 3 rules that should be pretty easy to understand:
Take note of your agent ID, which is found just above the TWEET RELEVANCE title on this page. Later in this post we suggest a few things you can add to this, but this is a good starting point.
Next step is to clone our Tweet Relevance Ruby on Rails on GitHub, and follow the installation instructions in the README.md file, from there you’ll be guided through the next steps of setting up the app.
Once you’ve got things set up, your app will show you the tweets that are most relevant based on the rules we defined earlier. Each tweet will be scored like this:
Now that you’ve got this simple app working, what else can you do? If you want to play around with the app and Fuzzy.ai, here are some other things you could try:
One of the benefits of having Fuzzy.ai on Product Hunt last week was getting a lot of additional eyeballs on our SDKs for different programming language. We got a lot of feedback on the Python library on github, so there’s now a new version of the fuzzy.ai package in pypi.
This version brings the Python SDK up to the same level of functionality as other SDKs, and provides support for Python 2 and 3, a better unit testing framework, and some other software engineering improvements.
Please kick the tires if you’re a Python developer. Issues to Github!
Fuzzy.ai was featured on Product Hunt last week, both on the site and in the email newsletter. We were happy to get a huge response from the community — a ton of comments and upvotes. We’re now in the top 10 API products of all time and top 20 AI products. Exciting stuff!
If you’re a member of the Product Hunt community, please make sure to check out the conversation there.