Back office ops · Production

Fellow integrates Recall.ai for meeting recording and transcription, shipping in a week instead of months

The problem

Fellow needed meeting recording, transcription, and speaker diarization for their productivity platform but estimated that building internally would require three full-time engineers plus an SRE for approximately three months, plus significant ongoing maintenance including potential 24/7 on-call coverage.

Workflow diagram · grounded in source
1
Bot joins meeting to capture data
trigger
“having a bot that joins meetings to capture the data we wanted”
2
Record and transcribe calls
ai_action
“Fellow uses Recall.ai to record, save, and transcribe scheduled and ad hoc calls on Zoom, Microsoft Teams, and Google Meet”
3
Speaker diarization
ai_action
“It matches up the speakers to their names, transforms the transcript with the data it has about speakers, and sends that to us directly so we don't need to worry about any of the diarization process”
Reported outcome

Fellow implemented Recall.ai within a week rather than the estimated three months, avoided an engineering effort equivalent to four people for several months, and freed the team to focus on core product features.

Reported metrics
implementation time with Recall.aiwithin a week
Estimated internal build time (counterfactual)three months
Engineers required for internal build (counterfactual)three full-time engineers and an SRE
Engineering effort avoidedfour people for several months doing what Recall does for us in a couple of weeks
Reported stack
Recall.aiZoomMicrosoft TeamsGoogle Meet
Source
https://www.recall.ai/customers/fellow
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Fellow implemented Recall.ai within a week rather than the estimated three months, avoided an engineering effort equivalent to four people for several months, and freed the team to focus on core product features.

What tools did this team use?

Recall.ai, Zoom, Microsoft Teams, Google Meet.

What results were reported?

implementation time with Recall.ai: within a week; Estimated internal build time (counterfactual): three months; Engineers required for internal build (counterfactual): three full-time engineers and an SRE; Engineering effort avoided: four people for several months doing what Recall does for us in a couple of weeks (source-reported, not independently verified).

How is this back office ops AI workflow structured?

Bot joins meeting to capture data → Record and transcribe calls → Speaker diarization.

Related back office ops cases