Human resources

The power of experience: capturing 30 years of knowledge.

How a global manufacturing company built a knowledge capture application on Forra that transcribes expert video interviews, identifies each speaker, and turns operational knowledge into searchable, structured records.

KEY RESULTS

< 15 min

per interview processed

0

knowledge gaps since launch

Day 1

measurable results from deployment

“Meeting transcription significantly reduces the time spent on note-taking, analysis, and even the production of supporting documentation. What used to take hours now happens in minutes, and with even greater accuracy.”

Learning Advisor

The challenge

Decades of expertise, walking out the door.

The company faced a critical risk: decades of operational expertise lived in the heads of experienced workers nearing retirement. When a senior technician left, the knowledge went with them. Video interviews were recorded but never processed. Files sat on shared drives, unsearchable and unused. There was no systematic way to capture, structure, or transmit what the organization had built over 30 years.

The solution

A knowledge capture application, built on Forra.

The team built a knowledge capture application on Forra that processes video and audio interview recordings automatically. Files go through segmentation and speaker diarization to identify who is talking at each moment. AWS Transcribe and OpenAI Whisper are used in combination for best accuracy across French and English content.
Solution screenshot 1
Solution screenshot 2

Each transcript is automatically annotated and structured by topic. The knowledge is stored in shared memory and searchable by any authorized team member. New hires can query years of expert interviews directly. Every recording and transcript stays inside the organization’s own infrastructure.

The outcomes

Measurable results from day one.

  • Expert interviews processed and searchable in under 15 minutes, down from days of manual transcription.
  • Speaker identification across multiple voices per session, with annotated transcripts ready for review.
  • Years of expert knowledge captured and made searchable in the first months of deployment.
  • Zero knowledge lost to employee transitions since the application went live.

Related stories

More teams shipping with Forra.

Your knowledge base isn’t the problem.<br>How it is searched or used,&nbsp;is.

Your knowledge base isn’t the problem.
How it is searched or used, is.

Purpose-built AI agents replace a generic assistant, achieving 87.5% accuracy on a validated benchmark versus 12% for Microsoft Copilot.

View project
The answer existed. It was buried in 15 hours of searching.

The answer existed. It was buried in 15 hours of searching.

AI research agent searches four scientific libraries simultaneously and delivers a complete, sourced report in minutes instead of hours.

View project
The expert in their pocket,<br>on every client floor.

The expert in their pocket,
on every client floor.

How a global manufacturing company built a technical support tool on Forra that lets technicians troubleshoot any robot issue on-site, in seconds, with the exact source and location in the documentation to back it up.

View project