Custom agent · Built in-house
Collect anonymous worker feedback by voice and summarize it for owners
US community lender Pacific Community Ventures runs AIKKA, a voice survey tool built on Claude, to gather open-ended feedback from small business workers and pass anonymized themes back to owners who have no HR team.
What they did
Workers who opt in answer open questions by speaking for up to five minutes in their own language on a phone. Each response is transcribed and Claude, via the API, tags it for sentiment, emotion and theme, feeding a dashboard that updates as answers arrive. The team packages anonymized results into feedback for the business owners.
How it went
The organization says one nationwide survey reached close to 300 workers, versus 12 in a comparable focus group, and its qualitative research now runs at about ten times the previous scale.
Worth knowing
Accuracy has only been confirmed in English, Spanish, Hindi and Punjabi, and data scientists still spot-check the tagging. The tool is run by a lender for its clients, not by each employer directly.
Try it with Custom agent
Here are anonymized transcripts of employee answers to <your survey questions>: <transcript file>. Tag each answer for sentiment, main theme and any sign the person may leave, keeping mixed feelings rather than averaging them. Then write a one-page summary for <owner or manager> with the top themes, a few short paraphrased examples, and three practical actions. Remove anything that could identify a person.
We wrote this prompt from the case. Replace the parts in angle brackets with your own details.
What this label means: Vendor says
The maker describes it on its own site or launch post. It shows what the product is meant to do, with no independent result.
Real cases of AI agents at work, from every major agent, each linked to where it was first reported. Rewritten in our own words, most with a prompt you can try. These are not Wize customers.