This is a submission for the Postmark Challenge: Inbox Innovators.
What I Built
InboxOps is a powerful AI-augmented operations platform...
For further actions, you may consider blocking this person and/or reporting abuse
FYI the link to demo is not working: inboxops.render.com
The link had a silly typo i didn't knew it was .onrender.com.
The Submission is updated with Link!
good :) now I can access it. Any way I can test it? maybe sending email with some fake employer request?
Yes, the Email address is:
The schema to send an Employee or HR Leave application is suggested:
Subject: xyzabc
Body: Start Date, End Date
The body can contain anything!
thanks! jsut sent email and saw it in inbox, but not in other parts of dashboard, should I make some action to trigger it go through the flow?
Yes, the Ticket was not getting created, the whole workflow was at a standstill due to Postmark not recognizing the email address.
I made some changes in the backend routing code, it should work just fine now!
now i see it in other tabs, but it is not supposed to send me any resolution of issue right? at this stage i guess it is not implemented yet? potentially if certain flows are set up it will be able to resolve certain use cases?
You're absolutely right! At this stage, InboxOps focuses on intelligently parsing, classifying, summarizing, and dashboarding inbound emails using Postmark + LLMs.
While it doesn't send automatic resolutions yet, it's architected to make that possible. The foundation is in place:
The next step (on roadmap) is to help create APIs for the Internal team systems that can directly attach replies to which response by email automation using Postmark Outbound Email Stream is to be done.
I think to make this submission stronger, you can make simple emulation of response. Like on receive of webhook to process as you already do + simulation of real work done:
Also ALERT 🔴🔴🔴 you might want to check your repo for leaked gemini and postmark tokens.
Thanks a lot for the guidance, I will work on this to update Inboxops!
Super impressive how you’ve combined Postmark parsing with LLMs to automate and unify so many workflows. Curious, how did you approach prompt chaining for reliable intent and summary extraction across really different email types?
Yes when it came to extracting intent, summary, tags, and criticality from different email types Orders, HR, Customer Enquiries support, Approvals I used structured prompt chaining.
The Postmark Inbound Email JSON is passed to LLM to return in a structured JSON format:
{
"intent": "support",
"summary": "Customer reports duplicate charge and requests refund.",
"criticality": "high",
"tags": ["refund", "billing", "duplicate"]
}
This solved me the consistent storage of data. Entirely the workflows cannot just rely on LLM. To improve reliability across types: Order Emails, Approvals, HR, Customer Enquiries Support Requests Issues Tickets, I did:
been cool seeing steady progress - it adds up. you think the roadmap or just showing up every day keeps stuff moving the most?