Network Grow - AI Referral Asker Model
Referral Asker
by Neurometricđź’Ľ Sales & Business Development
Network-Grow is a task-specific model that drafts the perfect "ask" for a referral from a happy existing customer.
Network Grow is designed for Sales & Business Development 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 referral asker and predictable output quality. That makes it easier to adopt in production pipelines where teams need reliable formatting, lower latency, and reduced hallucination risk.
Teams commonly connect Salesforce, HubSpot, and Gong exports to automate briefings, account summaries, and follow-up drafts. 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 Network-Grow 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/network-grow",
messages=[
{"role": "user",
"content": "{\n \"channel\": \"LinkedIn message\",\n \"customer_name\": \"Jordan\",\n \"referral_target\": \"IT Director or CTO\",\n \"outcome_achieved\": \"reduced helpdesk ticket backlog by 38% and improved first-response ..."}
]
)
print(resp.choices[0].message.content)Test Results
Example Input
Channel: LinkedIn message Customer Name: Jordan Referral Target: IT Director or CTO Outcome Achieved: reduced helpdesk ticket backlog by 38% and improved first-response time to under 10 minutes Ideal Company Type: manufacturing firms with 200–1000 employees Product Or Service: BrightPath IT Managed Services Relationship Context: sent a thank-you note after a successful incident response and received praise Referral Request Tone: confident but low-pressure
Expected Output
Hey Jordan—really appreciate the kind words after the incident response. I’m glad BrightPath could help get the helpdesk backlog down 38% and bring first-response time to under 10 minutes.
If you know an IT Director or CTO at a manufacturing company (200–1000 employees) who’s dealing with similar support or response-time challenges, would you be open to making a quick intro? Totally fine if no one comes to mind—asking only because your results are a great example of what we can do.
If helpful, you can copy/paste this:
“Hey [Name]—we’ve been working with BrightPath and they cut our ticket backlog 38% and improved response times significantly. Thought you two should connect.”
Actual Model Response
Sure! Here's a confident, low-pressure LinkedIn message tailored to Jordan, their experience with BrightPath IT Managed Services, and a clear, respectful referral request to an IT Director or CTO at a manufacturing firm:
---
Hi [IT Director's Name or CTO's Name],
I hope you're doing well! I’ve been meaning to reach out since I recently had the pleasure of working with Jordan at [Jordan’s Company Name] — they’ve been absolutely thrilled with the results from BrightPath IT Managed Services.
After a major incident response, Jordan sent me a heartfelt thank-you note, highlighting how we helped reduce their helpdesk ticket backlog by 38% and cut first-response time down to under 10 minutes. That kind of impact is exactly what manufacturing operations need — reliable, fast, and proactive IT support in a high-availability environment.
I’m reaching out not to pitch, but to share a quick success story and see if you might be open to a brief conversation. If your team is looking for a managed IT partner that delivers measurable improvements in uptime and response times — especially in mid-sized manufacturing firms (200–1,000 employees) — I’d be happy to connect and share more.
No pressure at all — just thought you might find this relevant. Either way, I appreciate your time and the great work you do leading IT at [Company Name].
Best regards, [Your Full Name] [Your Title] BrightPath IT Managed Services [Your LinkedIn Profile or Website]
---
💡 *Tip:* Before sending, replace bracketed details like [IT Director's Name], [Jordan’s Company Name], and [Company Name] with actual names and details. Personalizing this further increases relevance and authenticity.
Test this model
Sign in to run your own test cases against this model.
Capabilities
Related models
Frequently asked questions
Does Network Grow work with Salesforce?
Yes. Network Grow is built to work with Salesforce, HubSpot, and other CRM exports. 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 referral asker, teams usually pass normalized records with field names, context notes, and output constraints.
Why use a task-specific SLM for referral asker?
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.