Skip to main content
Some lead providers do not POST to an endpoint — they email you. Settings → Email Parsing connects a Gmail mailbox, filters what comes in, and has AI read the matching emails and create leads from them.
The Email Parsing screen with the Activity and Settings tabs
Two tabs: Activity (what has been processed) and Settings (the connection, the filters and the prompt).

​
1. Connect Gmail

On the Settings tab, under Gmail connection, click Connect with Google and choose the mailbox that receives the lead emails.
Leave the broad consent checkbox enabled. The page says it plainly:
We need read-only access to your Gmail inbox to monitor incoming emails and turn matches into leads. On the next screen, please leave the “Read, compose, send, and permanently delete all your email from Gmail” consent checkbox enabled (we only use the read permission). Without it, parsing will not work.
Google does not offer a narrower scope that still lets BeRocker read the mailbox. Untick it and the connection completes but nothing is ever parsed — you will see Permission required.
Once connected, the card’s tag reads Connected (or Needs reauthorization / Error / Disconnected), Connected as shows which account is linked and when it last synced, Test connection checks it still works, and Disconnect revokes access. If read access was not granted the button becomes Reconnect Gmail.
Use a dedicated mailbox such as leads@yourdomain.com and forward provider emails to it. Pointing this at a personal inbox means the parser sifts through everything you receive.

​
2. Set up filters

A filter decides which emails get parsed. Until you add one you will see “No filters yet. Add one to start parsing matching emails.” Click Add filter (the dialog is titled New filter). Each filter has: Each rule is a field, an operator and a value:
An email that matches no filter is recorded as No filter matched and nothing is created. That is on purpose — it is how you keep the rest of your mail out.

​
A filter that works

Start narrow:
  • From contains @leadprovider.com
  • AND Subject contains New Lead
then widen only if you find real leads being missed.

​
3. Set the AI prompt

This prompt is sent to OpenAI together with the cleaned email body. The AI is asked to return strict JSON with the lead fields (first_name, last_name, phone, email, vehicles, addresses, etc.). Every save is recorded as a new version you can roll back to.
Current prompt (preview) shows what is in use. If it says No prompt configured, nothing will be extracted yet — click Edit prompt. The Email parsing prompt editor has three tabs — Edit (the prompt, an optional What did you change? note, Revert to current and Save), Summary, and Version history, where each version carries a What changed (AI) summary and your editor note, and Restore rolls back to it. A change that makes parsing worse can always be undone.

​
4. Turn on automatic processing

Process incoming emails automatically is the master switch. Leave it off while you tune your filters, then turn it on. Next to it, Create parsed leads in status decides what a parsed email becomes:
  • New — a regular New lead that goes through your normal quoting flow, just like any other incoming inquiry.
  • Order — treated as an already-booked shipment: the lead is placed in the Order stage, the chat is handed to a broker and automated outreach is turned off.
Change the prompt in small steps and watch the Activity tab afterwards. A prompt that reads well can still extract the wrong ZIP code.

​
The Activity tab

Every email the parser has seen, with: Received · Subject · Filter · Status · Failure reason · Lead Search subject, sender, body…, filter by Status (Received, Processing, Parsed, Lead created, Failed, Reply / inquiry), narrow by date range, and Refresh.

​
Statuses

Status tags are shown in lower case, exactly as below: Open a row and the detail drawer shows From, To, whether it was Forwarded or a Reply, an Email preview (Cleaned content (sent to AI) and Original email), Attachments with download links, the Filter match, the Prompt used, the Parsed JSON, the OpenAI response and a Lifecycle log — so when a lead comes out wrong you can see exactly which step went wrong.

​
Troubleshooting

Lead sources

The API way of receiving leads.

Profile

Your personal Gmail connection.

Notifications

Alerts for parse successes and failures.

Shipments

Where the created leads land.