HackStack

Project Info

Candidate Compare

Devpost

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 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

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.

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • Next.jsIn code
  • PythonIn code
  • ReactIn code
  • Tailwind CSSIn code
  • TypeScriptIn code
  • Vercel AI SDKIn code
  • Node.jsClaimed

7 of 8 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

214 KB

Source files

46

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars