Summarize Sales Calls and Update CRM
Submit a call recording URL and the agent transcribes it, extracts deal details.
What it does
Submit a call recording URL to instantly get transcribed notes with extracted deal status, action items, and objections. You receive an automated summary that updates your shared Google Doc so the whole sales team stays aligned without manual follow-up.
Step by step
- Configure n8n HTTP nodes to send POST requests to WayinVideo and Google Docs APIs
- Set up a wait node in n8n to poll for transcription completion status
- Define the JSON schema structure for extracting deal status, action items, and objections
Where the LLM does the work
- Craft system prompts that instruct OpenAI to identify specific sales metrics from unstructured transcripts
- Refine extraction logic to handle ambiguous language or incomplete sentences in call recordings
- Format the extracted data into a clean text block suitable for appending to Google Docs
Tools that fit
WayinVideo API Audio transcription and speaker identification
OpenAI Chat Model LLM Extracting structured CRM data from transcripts
The agent brief
Everything your agent needs, including the gotchas. Copy it and go.
You are helping me build the following AI agent workflow. ## Goal Summarize Sales Calls and Update CRM: Submit a call recording URL and the agent transcribes it, extracts deal details. ## Specification - What it does: Submit a call recording URL to instantly get transcribed notes with extracted deal status, action items, and objections. You receive an automated summary that updates your shared Google Doc so the whole sales team stays aligned without manual follow-up. - Trigger: Triggered by an event (Manual · on form submission) - Autonomy: Fully hands-off - Expected setup effort: under an hour - Tools/services involved: - n8n: Workflow automation platform - WayinVideo: Audio transcription and speaker identification - OpenAI Chat Model: Extracting structured CRM data from transcripts - Google Docs: Storing and appending CRM reports ## Known pitfalls, handle each one explicitly in your implementation No documented pitfalls for this recipe. Apply your own review before going live. ## Reference implementation https://n8n.io/workflows/14588 (workflow template) Fetch and inspect this before building. If it matches my stack, adapt it; if not, rebuild the pattern with my tools. ## Process requirements 1. Before building: ask me which of the listed tools I actually use and what my platform is (n8n / Make / code / other). Do not assume. 2. Adapt the pattern to my answers; do not force the reference stack. 3. Address every pitfall above; tell me how you handled each. 4. Provide a test plan I can run before letting this touch real data. 5. Ask before any step that sends messages, modifies data, or spends money. Source: https://usecasesforagents.com/use-case/summarize-sales-calls-and-update-crm/ via usecasesforagents.com
Frequently asked questions
Can I use a different Automation Platform than n8n?
Yes. n8n is only the example automation platform in this recipe. The same flow works with Home Assistant. Swap the automation platform connection and keep the rest of the setup as written.
Want this running in your business?
This is what I do. I design and build AI agents like this one, and keep them running. If you want it set up for your team instead of doing it yourself, get in touch.
Who it's for
Built for sales teams who want the prep work done before they pick up the phone.