Candidate Compare

Inspiration

With the number of candidates rising in the industry in comparison to the job positions, conducting interviews and deciding on candidates carefully has become a critical task. Along with this ratio imbalance, there are an increasing number of candidates that are forging their experience to gain an unfair advantage over others.

What it does

The project provides AI interview solution which conducts a human-like interview and deploy AI agents in the backend to verify the authenticity of the candidate.

How we built it

The project was building NextJS as frontend, and NodeJS as backend. The AI service was provided by Hume, along with Single Store as the backend database. We also used Fetch AI to deploy the AI agents that verify the authenticity.

Challenges we ran into

Some challenges we ran into were related to integrating Hume into our frontend. Managing the conversation data and inferring it to provide feedback was also tricky.

Accomplishments that we're proud of

Being able to build a working MVP within 2 days of hacking. Integrating hume AI and being able to persist and maintain conversation transcripts that was later used to make inference.

What we learned

We learned about using and integrating AI agents to help us with important tasks. Having used Hume AI also provided us with insights on different emotions captured by the AI service that can be used in a lot of downstream tasks.

What's next for Candidate Compare

We plan on expanding the scope of our candidate information verification to include more thorough checks. We also plan to partner with a couple of early stage adopters to use Candidate Compare and benefit from reduced hiring loads.