My man here has serious pull at @aftersell (obviously, as head of product)
We've received some awesome feedback over the past few weeks - some positive, some negative, all 100% helpful
- Subs upgrades are crushing on LTV
- Aftersell Cart: hot off the press from @dppatel_
- Templates: we hear you, @russell_kwokk is sharing gold
- Write access for MCP is coming
What else??
An AI agent has been fixing bugs at @aftersell for 6 months.
It costs us $400/mo.
Meet Watson👇
We audited all of our engineering tickets last year and 35% weren't code bugs. They were config questions, duplicates of bugs we already knew about, confusing UI, etc.
And then the real bugs? The fixes are always easy but investigation was always the inefficient part.
Watson now finds and squashes bugs and has started to implement features fully autonomously. Here's how it works:
1) Triage - is this worth looking into?
Watson classifies every ticket before it digs in - is it a config issue, known issue, does it need more info? Output is structured data so downstream stages branch off of a real contract instead of parsing what a model is saying. Helps a lot with latency, cost, and performance.
2) Investigate - what happened?
This is the core of why we built Watson - it'll reconstruct the entire event timeline, read the codebase, pull cloud logging, etc. And we built this all directly on top of the Claude Platform Client SDK so we can have full control over prompt caching, per-tool call caps, cost accounting, etc. It's a super powerful way to control cost - on a "warm run" - 98% of inputs are from the cache.
3) Implement - write to the codebase
Watson directly writes to the repo, makes a PR, etc. It also monitors and reviews PR comments from reviewers. This is the simplest part - writing the code is so simple when you've gotten all of the context from triaging and investigation.
4) Memory - self improving loop (MUST HAVE)
Watson has a persistent memory mounted via GCS Fuse. Every time Watson is invoked it brings back findings and artifacts. We're layering it into episodic (past investigations), semantic (distilled patterns and playbooks), and reflective (what investigation strategies actually work on this codebase).
Watson integrates into everything we have - all internal chats, support systems, Linear, Github, etc. It's constantly improving and every single Linear ticket we have gets looked at by Watson.
Our first run was ~$50 and now it costs us $3.87 per ticket all in.
Comment below if you want me to write up a guide for how to build your own Watson.
We spent $131,239 getting our 60 person team in one place for 3 days.
By the next Monday, we’d already ROI’d it.
Our team is split across Toronto, Vancouver, Calgary and NYC...
So we packed in a lot:
→ Reviewed the last 6 months
→ Set our Big 3 goals for H2
→ Revealed a new product
→ Ran client fireside chats
→ Hosted a Twitter-Maxxing workshop
→ Watched @VarunKundra go head-to-head with @BEBuchanan in a mock sales pitch
The week after, there was less back and forth.
People knew what mattered and what they owned.
The team is locked in.
We’re on pace for our best week ever.
Bring your team together.
You won’t regret it!
Everyone said it'd take forever. We rebuilt @UpCartApp from scratch in @aftersell. One set of Strategies for cart + post-purchase 👀
It's live in alpha, and just won my team @ROKT's High Impact Award. 🏆
Follow for BTS dev content 💻
Want early access? Join our waitlist 👇
Every year we spend a TON of $$$s getting the @Aftersell team together for an offsite
70 cracked people in one location
Three of my biggest takeaways:
1. Building is more fun in person, with people you like and respect
No shade to working remote but man the energy slaps
2. Win one week at a time
How we show up next week determines our trajectory for the next six
3. Agency + ownership > everything else
I'm looking for the person who cares more than everybody else
Offisites... smart? Or just an excuse to party? 😅 LMK
@jforjacob 100%
We vibecoded something because we *had* to - it was costing us $50K p.a. and it was terrible
But I would ditch what we built and buy it again in a heartbeat if it was actually good
The CS team @aftersell has been crushing it lately
Would be a huge win heading into the weekend if we could make this happen
P.S.
If you had a bad experience in any way, DM me and I'll make it right
We’re 2 reviews away from 900
Our CS team has been GRINDING nonstop to get us there.
If you use @Aftersell…
A quick review on the Shopify App Store would mean a lot 🙏
I’m transferring this exact funnel (from our demo store) into the first 20 brands that comment.
why it converts: you catch people right after they paid and hand them money back to switch to a sub.
one-time buyer in, subscriber out.
The best subscription upsell might just be... an upgraded plan.
Introducing Subscription Upgrades.
Turn a monthly subscriber into a quarterly subscriber, right after checkout.
One click for them.
More cash upfront. Higher LTV for you.
@maxwellcopy Guessing they cap the refund at a certain monetary value and offer the same value to anybody who writes in for a free entry to get around lottery laws