A ChatGPT agent that scores every inbound lead against your ICP.
It reads each form fill or enriched contact from your CRM, scores it against the criteria you define, and writes a one-line context note your AE sees before they pick up the phone.
32 leads scored. Here's the top-ranked one queued for outreach:
How does OpenAI ChatGPT work for lead qualification?
OpenAI ChatGPT works for lead qualification by acting as the reasoning model behind a DeskFerry agent that scores every inbound form fill and enriched contact against the rubric your team actually uses — not a generic ICP template.
- 01
Trigger fires
The agent reads the lead record in your CRM (HubSpot, Salesforce, Pipedrive, Attio, or Close), pulls enrichment from Clay, Apollo, ZoomInfo, or LinkedIn Sales Navigator, and assigns a score together with the reasoning the AE will see before picking up the phone.
- 02
Score every new @ChatGPT inbound lead in @HubSpot against our ICP
The rubric is calibrated from six to twelve months of your past closed-won and closed-lost deals, then editable in plain English at any time.
- 03
Push the top 10% to @Salesforce with a one-line rep brief
High-confidence leads route to the right AE instantly; ambiguous ones queue for a human review with the missing signal called out.
- 04
You approve
Every score is logged and reversible, so the agent improves with each correction.
How you tell it what to do
Built in plain English.
You write the rule the way you'd describe it to a teammate. The agent reads the rule, breaks it into the actions it'll take, and confirms the apps it'll touch — before it does anything.
- 1Score every new @ChatGPT inbound lead in @HubSpot against our ICP
- 2Push the top 10% to @Salesforce with a one-line rep brief
Already wired in
ChatGPT is built into DeskFerry.
No API key, no model setup, no glue code. Connect the apps your team already uses and lead qualification runs on them.
ChatGPT runs inside DeskFerry on our keys.
- HubSpotConnect
- SalesforceConnect
Runs on your data, in your apps.
Nothing to deploy. Nothing to maintain.
Actions
What OpenAI (ChatGPT) + DeskFerry can do
Real OpenAI (ChatGPT) actions your AI agent can perform automatically — no manual work required.
Create Assistant
Tool to create a new assistant with specified parameters. use after finalizing model, tools, and instructions.
Create Message
Tool to create a new message in a specific thread. use when adding messages to an existing conversation after confirming the thread id.
Create Thread
Tool to create a new thread. use when initializing a conversation with optional starter messages.
Delete assistant
Tool to delete a specific assistant by its id. use when you need to remove an assistant after confirming its id.
Delete file
Tool to delete a file. use when you need to remove an uploaded file by its id after confirming the target.
List files
Tool to retrieve a list of files. use when you need to view all files uploaded to your organization.
List fine-tunes
Tool to list your organization's fine-tuning jobs. use when you need to review all fine-tune runs.
List models
Tool to list available models. use when you need to discover which models you can call. use after confirming your api key is valid.
List run steps
Tool to retrieve all steps of a specific run. use when you need to inspect each step's details after initiating a run.
Modify thread
Tool to modify an existing thread's metadata. use after obtaining the thread id when you need to update metadata.
Northwave + DeskFerry · 15 min next week?
ChatGPT flagged your account as a 92/100 ICP fit — Series B SaaS, 80 FTE, hiring two ops roles this quarter.
Personalized using LinkedIn activity from the last 30 days.
Human in the loop
Approve before it sends.
Every draft lands in a review queue. You approve, edit, or reject — the agent never acts on its own unless you explicitly turn that on for a workflow you trust.
Governance
Every action, with the reasoning attached.
Each step the agent takes is logged with what it did, why it did it, and which app it touched. Audit-ready, so security and compliance can sign off without backfilling.
- Marco11:42 AM
Approved the draft to jordan.lee@northwave.io.
- Agent11:41 AM
Drafted the email and queued it for review.
Reason: High-confidence personalization but recipient is C-level — escalating per policy.
- Agent11:40 AM
Pulled LinkedIn activity and HubSpot deal context.
- Agent11:40 AM
Triggered: Score every new @ChatGPT inbound lead in @HubSpot against our ICP, then push the
- Agent11:38 AM
Confirmed sender domain DKIM is healthy.
How it works
Get started in three steps
Step 01
Connect OpenAI (ChatGPT)
Authorize OpenAI (ChatGPT) in your DeskFerry dashboard. The secure connection takes less than 60 seconds.
Step 02
Configure Your AI Agent
Set up triggers, actions, and conditions specific to how your team uses OpenAI (ChatGPT).
Step 03
Deploy & Monitor Results
Your AI agent goes live immediately. Track tasks automated, time saved, and accuracy metrics in real-time.
Start automating Lead Qualification for OpenAI (ChatGPT)
7-day free trial. Works with the tools you already use.
FAQ
Frequently asked questions
What does ChatGPT actually decide here — does it score the lead, or does it act on the score?
It scores the lead and proposes the next action (route to AE, drop into nurture, disqualify with reason). The action is configurable: auto-execute for high-confidence cases, ask a human for review on the rest.
Where does the scoring criteria come from?
From your past closed-won and closed-lost deals. The agent reads 6–12 months of CRM history, asks you to confirm the patterns it finds, and uses that as the rubric. You can edit it any time.
What CRMs does this work with?
HubSpot, Salesforce, Pipedrive, Attio, and Close out of the box. Custom CRMs work via REST or our 1,500+ app library.
How do I know the scores are right?
Every score comes with the reasoning the agent used. You can spot-check, accept, or override — and the agent learns from each correction. After ~50 reviewed leads it usually plateaus at the level your best SDR would score them.
What's the setup time on a typical 50-rep team?
Half a day. Most of it is mapping your existing fields and confirming the agent's first-pass rubric. No engineering required.
Explore more