01
Drafts inside the help desk
Every new message gets a ready-to-send reply plus a private note showing what was checked and where.
All case studies
From 9 hours to 4 minutes.
How an AI support agent replaced a departing hire.
A no-code website builder was three weeks from losing the only engineer who could handle technical support. Sixth Gear replaced that role with an AI agent in 10 working days, cutting first-reply time from 9 hours to under 4 minutes and shipping three bug fixes as tested pull requests in the first month.
Results · first 30 daysBefore → after Sixth Gear
3m 40s
Median first reply
vs 9 h 12 min before1 in 20
Tickets needing a developer
vs 1 in 4 before5.5 h
To resolve technical tickets
vs 2.3 days before$68k
Saved a year vs. a new hire
vs $70k+ replacement cost01 / The pain points
Three weeks to lose the only engineer who knew support.
Every technical ticket ran through one person, and he was leaving.
- 01
One person held all the technical knowledge.
A single engineer handled every ticket that needed the code or the account data. He was leaving in three weeks, with no handover plan.
- 02
Customers waited too long.
Median first reply was 9 hours on weekdays and 26 hours over weekends, in a product where a broken site is urgent.
- 03
Technical tickets stalled.
One in four of ~60 monthly conversations needed a developer, and those took 2.3 days on average to resolve.
- 04
The founder was doing support.
He spent 6.5 hours a week answering tickets instead of building the product.
- 05
Answers drifted from the product.
The help docs lagged behind the code, and 14% of replies had to be corrected in a follow-up message.
- 06
Churn was spotted after the fact.
Cancellations surfaced in the billing dashboard days later, with no view of why or who was next.
- 07
Hiring wasn’t a real option.
A replacement would cost over $70,000 a year and take two to three months to ramp up on the codebase.
02 / What we built
One agent that answers, investigates and fixes.
Scoped to the support ticket, while the client’s team keeps the final say.
02
Account-aware answers
Read-only access to the customer’s account, billing, product analytics, logs and live DNS, so replies reflect their real plan, sites and charges.
03
Answers checked against the code
When the knowledge base and production code disagree, the agent holds the reply and flags it.
04
Debugging to the line of code
The agent rebuilds the customer’s site in a sealed sandbox, reproduces the fault and traces its cause.
05
Fixes as draft pull requests
A PR opens only when the failing reproduction passes after the change. Merging stays with the team.
06
Weekly customer pulse
A Monday summary of new signups, cancellations, likely churn reasons and at-risk accounts.
It runs on a hardened private server with read-only credentials, and every lookup is limited to the one customer in the conversation.
03 / Results after 30 days
Support carried on without a gap.
Pain pointBeforeAfter 30 daysImprovement
Median time to first reply9 h 12 min3 min 40 s
Weekend first reply26 h4 min 10 s
Tickets needing a developer1 in 41 in 20
Time to resolve technical tickets2.3 days5.5 hours
Founder hours on support per week6.51.2
Replies needing a correction14%2%
$912 kept
The weekly pulse flagged five at-risk subscribers in its first month. Four stayed after outreach, keeping $912 in annual revenue.
~$68k / yr
Saved against a new hire, who would have cost over $70,000 a year and taken two to three months to ramp up.
3 fixes
Bug fixes shipped as tested pull requests in the first month, ready for the client’s team to review and merge.
I expected a chatbot. What we got behaves like a careful engineer: it checks the account, reads the code and shows its working. I haven’t opened the support inbox on a weekend since it went live.
Your turn