Virtual interviews are on the rise–60% of HR professionals now use or have used video interviews in the hiring process. Not surprisingly, the market for intelligent products that help companies better facilitate and process these virtual interviews is also expanding–leading to the rise of AI-fueled Hiring Intelligence Platforms.
Hiring Intelligence Platforms do much more than host virtual interviews. Product teams at the top platforms embed AI models to build suites of tools and features that help companies automatically transcribe interviews, automatically create important sound bites from each interview, support interview team collaboration, and boost interview equity for interviewees.
This article looks at how Hiring Intelligence Platforms can quickly build robust AI hiring tools using production-ready, state-of-the-art AI models that help users:
- Automate asynchronous and real-time transcription for interviews, supporting faster and easier candidate review.
- Generate highlights and key analysis, helping hiring managers spend less time on post-interview manual tasks and helping minimize unconscious hiring biases.
- Surface insights that can be easily searched, tagged, and categorized, supporting seamless team collaboration.
First, we’ll explore what Hiring Intelligence Platforms do before examining the top three ways that Hiring Intelligence Platforms can build AI-powered tools and features today.
What are AI hiring tools and Hiring Intelligence Platforms?
Hiring Intelligence Platforms, also referred to as Talent Intelligence Platforms, use AI hiring tools to help companies screen, interview, and hire smarter for every posted job. At their core, these platforms help companies attract and hire more qualified candidates much faster and more efficiently than traditional hiring methods.
Tools and features offered by the platforms can assess a candidate’s soft skills, analyze tone, gauge emotions, examine proficiency, and more, all with the help of AI. And Hiring Intelligence Platforms boast impressive results. The users of the Hiring Intelligence Platform Screenloop, for example, realize an average 20% reduced time to hire, 60% less candidate drop-off, 50% fewer rejected offers, and 90% less time spent on manual tasks during the hiring process.
In addition, Hiring Intelligence Platforms help companies reduce or eliminate bias in the hiring process by using “ethical AI”. According to Modern Hire, ethical AI practices can be used to automate interview scoring, increase transparency, and ensure a fair interview process for each candidate.
The next section examines how Hiring Intelligence Platforms can embed state-of-the-art AI models to build AI-powered tools and features.
AI models for Hiring Intelligence Platforms
The field of AI is moving at breakneck speed.
Production-ready AI models can help product teams at Hiring Intelligence Platforms quickly build high-ROI, future-proofed features and tools on top of interview transcription data for platform users.
The best AI transcription models and Speech-to-Text APIs, for example, transcribe asynchronous and real-time audio and video data–like virtual interviews–at near human-level accuracy. Additional AI models can automatically summarize interview responses, surface key points and highlights, analyze responses, and facilitate team collaboration at scale.
Now, let’s look more closely at the three biggest impacts AI models can have for product teams at Hiring Intelligence Platforms looking to build with AI:
1. Automate Interview Transcription
AI transcription models can automatically transcribe video interviews as interviews occur in real-time or after the fact at high accuracy. When looking to incorporate AI transcription into a platform, consider accuracy and transcript readability. Today’s top AI transcription models should demonstrate high accuracy, or low Word Error Rate (WER).
But just as important–if not more so–is transcript readability.
What is transcript readability? Many AI transcription models output transcriptions that, though technically accurate, are missing sentence and paragraph structure, basic punctuation and casing, and speaker labels. This makes the transcripts difficult to read through, lessening the utility of the transcription.
See this shortened transcript of an interview–sans formatting– as an example:
When i'm gone for a while but hes always supportive so that always
takes a lot of stress off and lets me play and its a lot easier sure
wow well back to your college and pro career i know you are a usc
player and im sure that was an amazing team experience but a lot of
college players dont go on to go pro even though theyre incredible
players and the college level is very high its a shame that there isnt
much more interest in college tennis but how do you talk about mindset
shift from choosing tennis as a career versus like business or coding
or something you know and then making that decision from usc to just go
pro one of my goals when I was little was to always play professional i
think maybe some people just want to go to college or get a scholarship
and then end there but i knew i always wanted to continue my tennisThankfully, top AI transcription models apply Automatic Casing and Punctuation and Paragraph Detection to automatically add these missing features, making transcripts much more readable at a glance. Speaker Diarization also increases transcript readability by automatically adding speaker labels to a transcript–a very important addition to interview transcripts.
Now, here’s what the same transcript would look like with these features added:
<Speaker A> When I'm gone for a while, but he's always supportive, so
that always takes a lot of stress off and lets me play, and it's a lot
easier.
<Speaker B> Sure. Wow. Well, back to your college and pro career. I
know you are a USC player and I'm sure that was an amazing team
experience but a lot of college players don't go on to go pro, even
though they're incredible players and the college level is very high.
It's a shame that there isn't much more interest in college tennis. But
how do you talk about mindset shift from choosing tennis as a career
versus, like, business or coding or something, you know, and then
making that decision from USC to just go pro?
<Speaker A> One of my goals when I was little was to always play
professional. I think maybe some people just want to go to college or
get a scholarship and then end there, but I knew I always wanted to
continue my tennis.It’s significantly easier to read, right?
Automatic interview transcription helps hiring managers spend less time on manual interview tasks, like response review.
Sometimes, companies using a Hiring Intelligence Platform will need to make the interview transcript anonymous, perhaps to support a more ethical or unbiased interview process. To support this anonymity, platforms can use PII Redaction models to automatically remove or redact Personally Identifiable Information (PII) such as a candidate’s name. Platforms may even want to help companies remove other attributes of potential bias, such as age, gender, location, etc. A PII Redaction model would replace each specified PII with a # instead.
This table demonstrates the PII types that can often be redacted:
2. Generate Highlights and Key Analysis
In addition to providing an accurate, highly readable transcript, AI models can help product teams at Hiring Intelligence Platforms build tools that generate highlights and key analysis for users. This could include tools that can help users automatically search transcripts for relevant skills or experience, create highlight reels of key talking points, or analyze a candidate’s overall behavior to determine the best fit for the available role.
There are a few AI models that operate both individually and collectively to produce this sophisticated analysis.
First, AI Text Summarization models create short summaries or soundbites for each section of the interview. In addition, some AI Summarization models let users customize the way the summaries are displayed and are trained on data relevant to a specific use case. For example, AssemblyAI’s Conversational Summarization model was trained on highly relevant conversational data, making it best to use for any multi-person conversation. AssemblyAI also has an Informative Summarization model, which is best for files with a single speaker, and a Catchy Summarization model, which is best for creating video, podcast, or other media titles.
In addition, summaries processed by the AssemblyAI API can be returned as the following summary types:
gist– 3-10 word summaryheadline– 1-2 sentence (20 word) summaryparagraph– 3-5 sentence (30-100 word) summarybullets- bulleted list of paragraph summaries (max. 6 bullets)bullets_verbose– bulleted list of paragraph summaries (no limit)
With AI Summarization, Hiring Intelligence Platforms can build tools that help hiring managers more easily review candidate responses to key interview questions or even create video snippets of responses based on interview time stamps in the transcription text.
Next, Entity Detection models, also referred to as Named Entity Recognition models, can be used to identify and classify important recurring information in an interview transcript. For example, French is an entity that would be classified as a language.
With Entity Detection, companies can build tools that automatically pull named entities from interviews such as Names, Locations, Occupations, Addresses, and more. Then, the tools can use this information to help users to help categorize, tag, and search interviews.
Here is an example list of entities that can commonly be detected in a text:
Topic Detection models work similarly to Entity Detection. Topic Detection models identify and label important or recurring topics in a transcription text. For example, some Topic Detection models ascribe topics according to the standardized IAB Taxonomy:
With Entity Detection and Topic Detection models, Hiring Intelligence Platforms can build tools that help hiring managers find mentions of relevant skills and experience or other topics of interest. Tools built with Entity Detection or Topic Detection can help users perform analysis across interviews as well–of the same candidate or across different ones–to find trends or flag recurring topics for further follow-up.
Finally, Sentiment Analysis models can be used to identify and label speech segments as positive, negative, or neutral. Hiring Intelligence Platforms can build tools or features with Sentiment Analysis models that track a candidate’s emotional response toward a particular job attribute or interview question, helping give hiring managers even deeper insights into candidate behaviors.
Together, these AI models can help product teams build powerful tools that unlock valuable data about candidates and interviews.
3. Categorize, Tag, and Search Insights
In addition to helping build tools that let users identify trends, surface highlights, and support key analysis, Hiring Intelligence Platforms can use AI models to create tools that let users categorize, tag, and search candidate interviews.
For example, platforms could use this data to build a feature that generates indexable categories that users can then use to tag or search, similar to how users use hashtags on platforms like Twitter.
These “auto” or “smart” tags can be used for internal collaboration or for automatically attaching notes to indexed sections of interviews. Smart tags also make searching through and screening responses much faster and more efficient for hiring managers. Once a key tag is indicated, hiring managers can even share the tagged video content for review with other key members of a hiring committee, without having to sift through the entire video response.
The Summarization, Entity Detection, and Topic Detection models discussed above work together to create this smart tagging system feature. Entity Detection and Topic Detection models, for example, can be used to build tools that help users identify common themes in interview responses.
Then, the tool can use this data to generate smart tags that make these themes searchable. Summarization models could then be used to auto-generate short contextual summaries to attach to the appropriate tag.
These AI models all combine to help product teams at Hiring Intelligence Platforms build tools and features that offer a seamless hiring experience for candidates and hiring committees, helping companies boost ROI and secure key market share.
Explore an example of AI models in action in this sample conversationCompetitive Hiring Intelligence Platforms
Hiring Intelligence Platforms must invest in production-ready, state-of-the-art AI models to build powerful, high-ROI tools for users that capitalize on today’s AI breakthroughs.
AI models such as AI transcription, Summarization, Topic Detection, Entity Detection, and Sentiment Analysis can help product teams build AI-powered tools and features that automatically generate accurate, readable transcripts, create highlights and analysis, and build smart tags for key segments of interviews.
The time to build with AI is now.
