Csm Summary - AI Meeting Recap Model
Meeting Recap
by Neurometric🤝 Customer Success
CSM-Summary is a task-specific model that sends a "here is what we discussed" email immediately after a sync call.
Csm Summary is designed for Customer Success workflows where speed, consistency, and control matter more than generic creativity. Instead of relying on a broad model to guess intent each time, this task-specific SLM is optimized for meeting recap and predictable output quality. That makes it easier to adopt in production pipelines where teams need reliable formatting, lower latency, and reduced hallucination risk.
Most teams integrate CRM records, internal docs, and workflow tools to automate repetitive language-heavy tasks with predictable outputs. This makes deployment practical for sales ops, customer success, legal, and operations teams that need answers grounded in their own data. Because the model is small and focused, teams can run it with efficient infrastructure while still meeting quality targets for the use case.
Compared with general-purpose models, focused SLMs like this one typically deliver better precision for narrow tasks, lower cost per request, and easier governance. You can start with the free tier, test the model against your business data, and scale usage through Neurometric APIs or ClawPack workflows when performance meets your benchmark.
Model: Qwen/Qwen3-4B-Instruct-2507
This task-specific SLM uses Qwen/Qwen3-4B-Instruct-2507 with a specialized system prompt. The model weights are identical to the base Qwen model — the task specialization comes from the system prompt and has been validated through our testing pipeline. Need better accuracy? We can fine-tune the model on your data for your specific use case.
Quickstart
Copy-paste code to use CSM-Summary in your project
from openai import OpenAI
client = OpenAI(
base_url="https://api.neurometric.ai/v1",
api_key="YOUR_API_KEY"
)
resp = client.chat.completions.create(
model="neurometric/csm-summary",
messages=[
{"role": "user",
"content": "{\n \"call_context\": {\n \"tone\": \"friendly, action-oriented\",\n \"attendees\": [\n \"Maya Patel\",\n \"Sam Rivera\"\n ],\n \"recipient\": \"Maya Patel\",\n \"sender_name\": \"Sam Rivera\",\n \"..."}
]
)
print(resp.choices[0].message.content)Test Results
Example Input
Call Context: Tone: friendly, action-oriented Attendees: - Maya Patel - Sam Rivera Recipient: Maya Patel Sender Name: Sam Rivera Action Items: - Due: 2026-03-20; Task: Confirm webhook retry policy with vendor and document in spec; Owner: Sam - Due: 2026-03-21; Task: Provide sample payloads + event list for billing webhooks; Owner: Maya - Due: 2026-03-25; Task: Draft support runbook for launch week; Owner: Sam Subject Hint: Notes & next steps from our billing integration sync Decisions Made: - Target staging integration complete by March 28 - Use idempotency keys on all charge/create endpoints Topics Discussed: - Integration timeline for the new billing provider - Open questions on webhook retries and idempotency keys - Support handoff plan for the first 2 weeks post-launch Call Datetime Iso: 2026-03-17T14:30:00-07:00
Expected Output
Subject: Notes & next steps from our billing integration sync
Hi Maya,
Thanks for the sync earlier. Here’s a quick recap of what we discussed:
Discussion highlights:
Integration timeline for the new billing provider
Open questions on webhook retries and idempotency keys
Support handoff plan for the first 2 weeks post-launch
Decisions:
Target staging integration complete by March 28
Use idempotency keys on all charge/create endpoints
Next steps / action items:
Confirm webhook retry policy with vendor and document in spec (Owner: Sam, Due: 2026-03-20)
Provide sample payloads + event list for billing webhooks (Owner: Maya, Due: 2026-03-21)
Draft support runbook for launch week (Owner: Sam, Due: 2026-03-25)
If I missed anything, feel free to reply and I’ll update the notes.
Best,
Sam Rivera
Actual Model Response
Subject: Notes & next steps from our billing integration sync
Hi Maya,
Thanks for joining our sync today — it was great to chat about the billing integration roadmap! Here’s a quick recap of what we discussed and what’s next:
🔹 Integration Timeline We’ve set a target for staging integration to be complete by March 28. Let’s keep the momentum going to hit that deadline.
🔹 Webhook Retries & Idempotency We’ve decided to use idempotency keys on all charge and create endpoints to prevent duplicate processing. I’ll follow up with the vendor to confirm the retry policy and document it in the spec by March 20.
🔹 Support Handoff Plan To ensure a smooth launch, Sam and I will draft a support runbook for the first two weeks post-launch. Maya, please provide sample payloads and the full list of billing webhook events by March 21 so we can build a clear reference.
✅ Action Items (with owners & due dates): - 📝 Confirm webhook retry policy with vendor and document in spec → Sam, due March 20 - 📄 Provide sample payloads + event list for billing webhooks → Maya, due March 21 - 📚 Draft support runbook for launch week → Sam, due March 25
Let me know if anything needs adjusting — I’m happy to connect again if we hit any roadblocks. Looking forward to a smooth launch!
Best, Sam Rivera
Test this model
Sign in to run your own test cases against this model.
Capabilities
Related models
Frequently asked questions
Does Csm Summary work with CRM systems?
Yes. Csm Summary is built to work with CRM systems, internal docs, and CSV/JSON pipelines. Most teams connect existing APIs or scheduled exports and map records into prompt-ready JSON.
What data format does this model accept?
You can send plain text or structured JSON. For meeting recap, teams usually pass normalized records with field names, context notes, and output constraints.
Why use a task-specific SLM for meeting recap?
Task-specific SLMs are tuned for one business outcome, so they are often more consistent and cost-efficient than general models for repetitive production workflows.
Try This Model
Send a message to try the model
Use via API
FreeView API settings and get a free key. Sign up when you want more keys or billing access.
Need better performance?
We can fine-tune this model on your data for higher accuracy on your specific use case.