HumanFirst & Cohere QuickStart Guide To start using the HumanFirst [https://www.humanfirst.ai] / Cohere [https://www.cohere.ai] integration you will need a Cohere [https://cohere.ai] API key...in order to get your
Follow-Up Interview With Cobus The following is a redacted interview between Greg (CEO @ HumanFirst [https://www.humanfirst.ai]) and Cobus Greyling (www.cobusgreyling.me [http://www.cobusgreyling.me/]); in this interview, we dig deep
Practical semantic search and clustering Semantic similarity is quickly becoming a mainstream technique for working with natural language data; embedding new examples into a latent space uncovers the relationship between them. PineCone.io [pinecone.io]
Interview with Cobus Greyling [Greg] HumanFirst is a big fan of yours Cobus :) I've personally been reading your blog [cobusgreyling.medium.com] for the last two years, and have learned a lot about everything
Intent Disambiguation We’re moving away from first-generation chatbots and into the world of complex conversational AI strategies as a means of interacting and delivering on multi-faceted customer requests. This means that
Articles Continuous AI Improvement With the emergence of platforms democratizing conversational AI, there’s a smaller hurdle to get a basic NLU model up and running. The real work starts when your conversational AI
Articles Why It’s Time to Move Beyond Sentiment Analysis The customer landscape is no longer represented by a one-dialogue offering. When customers share their feedback with you, they expect you to listen and act. That’s why many businesses
Articles The Importance of High-Quality Training Data In the new AI/NLU paradigm, businesses realize that complex algorithms will no longer sustain their competitive advantage. The advantage lies in the ability to curate and utilize high-quality training
Articles Buying vs. Building enterprise-ready solutions The decision to build proprietary solutions or buy ready-made software is important for companies investing in a long-term digital vision and roadmap. This is particularly true when it comes to
Are we focusing too much on the labeling problem? Programatic labeling has been a hot area of development in the last 2 years, with Snorkel Flow [https://snorkel.ai/] leading the way, and other commercial [https://www.watchful.io/
Voice of the Customer Data is 🚀 Most businesses are sitting on high-quality Voice of the Customer Data , generated across a growing number of channels in the context of sales, marketing, product and operations. Examples of activities
GPT-3 in Conversational AI The first iteration of HumanFirst was a browser extension that ingested customer support live chat conversations, trained a black-box AI model that predicted what the chat agent’s next response
Help Centers are Underrated in Conversational AI. > In this article, I use the term "Help Center" to refer to all types of Help Center, Knowledge-base and FAQ solutions. Help Centers are rarely a core part of the
Labeling isn't hard if you know what to label. Companies like Scale.ai [scale.com] (recently valued at $7B+ dollars [https://fortune.com/2021/04/13/scale-ai-valuation-new-funding-fundraising-data-labeling-company-startups-vc/#:~:text=Scale%20AI%2C%20a%20San%20Francisco,in%20the%20latest%20investment%20round.
Conversational AI should start with search. > Let’s take an airline example: “I want to change my flight from the 3rd to the 4th”. This is one of the 1000+ requests that an airline might hear
Walking before running in conversational AI. Conversational AI is often equated with chatbots. Yet chatbots rarely do the “AI” part correctly (i.e: understanding user intents). Statements like “great conversational AI needs to move beyond dumb
Case Studies NLU at scale: 1000+ intents powering eHealth's Call Center AI and Analytics Learn how eHealth has moved from excel and .txt files to HumanFirst for management of their NLU data at scale.
Articles Building a Semantic Emoji Prediction NLU Learn one way to approach semantic Emoji prediction with cascading intents.
Articles The crux of NLU is managing the long-tail of data. > Until now, building and maintaining the training data needed to support a long-tail of intents has been a difficult problem — yet this is what is needed to go from a
Tutorials Syncing Dialogflow with HumanFirst How to import an existing Dialogflow agent to HumanFirst using our command line integration.
Tutorials Bottom-up NLU with HumanFirst Learn how to apply the tried and tested divide-and-conquer approach to labeling large datasets using HumanFirst.
Articles A bottom-up approach to NLU Bottom-up labeling applies the tried and tested divide-and-conquer approach to this problem, with great success.
Tutorials Importing Conversational Data from Rasa to HumanFirst This article explains the process of importing your conversational data from Rasa to HumanFirst.
Tutorials Labeling Data at Scale with HumanFirst Learn how to make use of HumanFirst to accelerate the labeling process of conversational data.
Tutorials How to bootstrap and continuously improve Botpress projects with HumanFirst Studio and real data In this article we’ll see how to use available datasets or your own in order to create a Botpress bot from scratch without having to come up with every single training phrase.