Sales call transcript analyzer

Every hour this workflow reads the tab of call transcripts in your Google Sheet, finds the calls that have not been analyzed yet, and for each one asks Claude to read the transcript and write a full breakdown: a summary of the call, how warm the deal is, what the prospect said about pain, budget, timeline, decision process and stakeholders, the buying signals and red flags, a numbered action plan with an owner and a date on every step, the questions to settle before the next call, and a follow-up email draft. The analysis is emailed to the address you choose, and the row is marked so it is never analyzed twice.

The sheet The tab needs these four column headers in row 1, and Status has to be the first column:

Status | Call Date | Prospect | Transcript

Status is the only column the workflow writes, and it writes nothing else on the row. That is why it has to be column A: a one-column write lands on A alone, so a row can be marked done without any chance of touching the transcript beside it. Leave Status blank on a new call; the workflow fills it in with "Analyzed <date> - sent to <address>" once the email is out. Prospect is the company or person the call was with and Call Date is when it happened; both are used to title the email and to give Claude context, and either may be blank.

Before the first run, edit the settings at the top of the workflow: - spreadsheetUrl: the sheet holding the transcripts. It ships blank and the run stops with a message until you fill it in. - sheetName: the tab inside it. Defaults to "Transcripts". - recipientEmail: where every analysis is sent - a rep, a manager or a shared inbox. Also ships blank. - maxPerRun: how many transcripts one run may analyze. Defaults to 5, which paces a backlog out over a few hours instead of sending forty emails at once on the first run. - minTranscriptChars: how long a transcript has to be before it is worth analyzing. Defaults to 300 characters, which skips rows whose recording has not been transcribed yet.

How a row is picked up A row is worked when Status is blank and the transcript is long enough. A row whose transcript has not arrived yet is left alone with Status still blank, so it is picked up on a later hour with nothing to reset. Status is written last, after the email is sent, so a failure part-way through leaves the row untouched and the next run retries it. If the email goes out but the row cannot be marked, the run stops and names the row to mark by hand, so the same analysis is not sent again every hour. If Claude returns nothing usable, the row is marked "Needs review" instead and no email goes out.

What it costs and what it needs Connections: Google Sheets (reading the transcripts and marking rows), Anthropic (the analysis) and Gmail (delivery). One Claude call per new transcript, so cost tracks how many calls your team runs. Long transcripts are the expensive part; a two-hour call is a few cents.

Worth knowing Everything Claude writes here is for your own team, never the prospect: the follow-up email at the end of each analysis is a draft for a person to review and send themselves. Claude is told to write "Not stated on this call" rather than infer anything the transcript does not cover, so a thin analysis is a signal that the call was thin. The analysis is written as plain text, which is what Gmail sends here, so it reads the same in every mail client.

To change the pace, edit the trigger; hourly suits a team whose transcripts land through the day. To send each rep their own calls instead of everything to one address, use the "Turn sales calls into action plans" template, which reads a Rep Email column from the sheet.