This post outlines how to integrate a state-of-the-art machine learning model into a Slack bot to generate a summary of articles shared by their URL — a.k.a “tldr” (too long, didn’t read). To round up the rest of the tech stack, I’ll cover how to set up Cortex (Machine learning model deployment platform), Serverless Framework (AWS Lambda), and AWS Simple Queue Service (SQS). The end result looks like this:
I use a service called Tiller that automatically pulls and consolidates transaction data from different accounts into Google Sheets. It helps me track spend and plan for budget. Unfortunately, incoming transactions have to be manually labeled into categories.
The prospect of free hotel stays in Vegas prompted me to automate some random mobile game
Last July we met with a family friend to watch their sons compete at a karate tournament in Las Vegas. During one of our dinners, I learned that they’re staying for free at the Aria, which at that time was busy with hotel guests and clocked in close to $400+/night! They got to stay for free thanks to a mobile game that rewards you “coins” that can be redeemed for real hotel stays around the strip.
Needless to say, I was intrigued and asked…
About 5 years ago, I wrote a post on a list of 50+ machine learning APIs. It got a fair amount of likes and shares at that time*. As a software developer, APIs provided a safety net from where I can interact with ML without having to understand how it works.
Nowadays I can’t go from my morning coffee to lunch without hearing at least two people in a cafe talk about AI, neural networks, epoch, TensorFlow, training your model, ML-powered <insert any word here>, etc. At work I discreetly Google terms to keep up with the growing list of…
Last week at Fusion 2018 we announced the Concur Expense and Travel for Slack. For those who have been following our progress, you might recall that we started this journey more than a year and a half ago with a design sprint with the Slack team.
In that session we hashed out ideas for what a Concur bot might look like. Most of the features we launched last week had their roots there.
Between then and today, we did several tweaks and iterations. The following is a short list of things that have contributed (and continue to shape!) …
The Concur Labs and Hipmunk team are in the Washington State Convention Center this week for SAP Concur Fusion 2018. Fusion is our annual conference that brings together clients, partners, and staff to connect, collaborate, and inspire.
Yesterday, March 14th, we announced the result of our longtime partnership with Slack. We launched beta versions of our bots, namely Concur Expense on Slack and Concur Travel on Slack (private early access). Fusion attendees were among the first to see and try the bots in our booths.
The goal of putting these experiments in front of users is to gather feedback which…
When I was a kid, my mom kept a stack of cookbooks. Once in a while I’d browse those books, even if I didn’t know nuts about cooking. The pictures of mouth-watering food kept me going back to those pages. Oh yeah..
Occasionally I'd stumble on cookbooks that didn’t have pictures. Needless to say, I never read them.
As a Developer Advocate for Mashape, I get to attend, join, sponsor, and judge developer hackathons. One after another, I’ve seen great teams lose to equally awesome teams. It leaves a bad taste in my mouth. I know that we run these contests to pick the best of the best. But sometimes, it’s difficult to draw the line. How many times have you told yourself, “That other team was obviously better than the winner.”
There’s another way of saying this — “Hey they could have won in that other hackathon!”
I think as developers, we have the responsibility to carefully…