Remix.run Logo
Show HN: Drafting AI – Human-in-the-loop AI automation for ops teams' email(getdrafting.com)
24 points by jpochtar 8 hours ago | 3 comments

Hi HN, I'm Jared from Drafting AI (https://getdrafting.com/). We're a Chrome extension that helps operations and customer support teams work through their inboxes more efficiently. Here's a quick demo video: https://www.youtube.com/watch?v=PCDqAMaYx2Q

We believe AI can be deployed more widely when you mitigate hallucinations through human-in-the-loop review. This led to two decisions:

1. A Chrome Extension is ideal for presenting actions in third-party apps for human review. When AI suggests issuing a refund via Shopify, what better way to show it than through Shopify's own refund interface?

2. AI should "draft" responses but not submit them. For instance, it’ll open Shopify admin and fill in refund details, but won't click "submit." This gives the user full control to approve, modify, or discard the AI's suggestions.

We believe this "drafting" UX of pre-filling form fields will become standard for AI. It feels like GitHub Copilot's autocomplete UX, but for forms.

You can add Drafting (https://getdrafting.com/) to your internal tools today to speed up email-based workflows. It's perfect for any process that follows the pattern of: 1) read email, 2) use internal tool to handle it, 3) reply to email.

For an example, consider a customer support rep for an e-commerce. A customer emails about poor product quality. The CS team has configured Drafting AI to process refunds through Shopify for serious quality complaints. The rep opens the email in Gmail or Front and clicks the Drafting AI button. A window appears with Shopify's refund form already filled out, plus a reply draft ready in their email. After reviewing both, they approve and send.

We’ve seen that without Drafting AI, a rep can spend 5 minutes just writing the reply email; half their time on a 10 minute ticket. With Drafting AI, reviewing and approving takes seconds.

Other use cases include: freight and logistics ops (TMS) coordinating with carriers, travel agents making trip adjustments (GDS), and HR teams processing payroll and benefits requests (HRIS). These and other job roles can sometimes be thought of as using a person as a bridge between email and internal tools.

As a Chrome extension, we integrate with all your existing internal tools as long as they’re web-based, whether they’re SaaS (Shopify, Salesforce), nocode/lowcode (Retool, Airtable), or custom apps (React, Rails, Django)

Try it at https://getdrafting.com/ or reply here with questions! I'm happy to personally onboard the first 20 teams that reach out.

jpochtar 7 hours ago | parent | next [-]

I started thinking about this while leading an internal Ops platform at a previous operations-intensive tech company. As we automated Ops work, I found the bottleneck to shifting left was was defining the processes our Ops team followed. Eng entered late: first, we'd throw Ops resources at a new challenge; then gradually systematize it; wait for PM attention; document the process; and finally engage engineering. This was necessary since systematized bad processes meant scaled mishandling of issues and engineering rework.

Drafting AI offers a different path: teams begin automating processes organically as they discover them, growing toward full automation as understanding deepens. Human review catches edge cases, handles ambiguous situations, and gives an incremental path towards full automation without rework.

Hopefully this lets internal tools teams shift automation further left.

parthi 7 hours ago | parent | prev | next [-]

I think it's right for this to sit at the browser layer to have a human in the loop.

paras_athina 7 hours ago | parent | prev [-]

Enterprises these days have built their own 2 layer guardrail system to work around with Hallucinations and its really effective. I found this blog with proper experimentation on real life use case of Doordash: https://dub.sh/how-doordash-mitigates-hallucinations