Home/Blog/Case studies
Case studies

Case study: Document.com cut response time from 11 hours to 6 minutes

Document.com runs an automated state-document generator. Speed is competitive moat. They consolidated four tools into Message and saved $1,400 a month on the way.

MP
Mara Patel
Customer engineer · April 4, 2026 · 9 min read

Document.com generates state-compliant business documents on demand: incorporations, operating agreements, NDA templates. Their customers are time-pressured. The platform sold itself on speed, but the support response time was 11 hours. That gap cost them sales and reviews. Here is how they closed it.

The 11-hour median

We were paying $1,800 a month for tools that gave us an 11-hour reply time. That math was unbeatable. So we left.

Document.com's old stack was four tools: Intercom for chat ($99/seat for Advanced, 3 seats = $297), Zendesk for tickets ($55/seat for Suite Team, 3 seats = $165), Aircall for phone ($30/seat = $90), and Notion for the KB. The median first-response time across channels was 11 hours and 22 minutes. The 95th percentile was 38 hours.

The migration

I ran the migration. We imported 14 months of Intercom conversations and 9 months of Zendesk tickets into a single Message workspace in 6 hours. The team's saved replies, macros, and routing rules I recreated by hand over the course of a week with Mara on a video call. Mara from Document.com (different Mara) wrote down every routing rule in plain English first, which made it a 20-minute exercise per rule.

Day one of production

The widget went live on a Wednesday at 4pm. We were watching the metrics in real time. By Thursday morning, the AI was answering 31% of incoming questions without a human. By the end of the first week, 58%.

Week 4: the response-time crash

Median first-response time dropped to 6 minutes inside three weeks. Two things drove it. (1) The AI handled the easy 73% of conversations within 10 seconds. (2) Human agents could now focus on the hard 27% instead of triaging email queues. AI deflection plateaued at 73% after week 6 and has held steady since.

Where they spend the savings

Document.com's tooling bill went from $1,800 to $19 a month. They put the $20k a year into a part-time CX hire who reviews the AI's escalation log and writes new KB articles based on patterns. The KB grew from 24 articles to 67 in three months. Deflection ticked up to 76% as a result.

#case-study#saas
MP
Written by Mara Patel · Customer engineer
Customer engineer. Most-cited byline in our help center. I write about the hands-on migrations.

Try Message free for 14 days.

Unlimited agents, flat monthly price. No credit card to start.

Start free trial