You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: apps/blog/content/blog/claude-generated-50-websites-overnight-prisma-compute/index.mdx
+23-7Lines changed: 23 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -16,25 +16,30 @@ tags:
16
16
- "case-study"
17
17
---
18
18
19
-
Ali Fatemi left an AI outreach system running overnight.
19
+
[Ali Fatemi](https://www.linkedin.com/in/ali-fatemi-94566a163/) runs a boutique software agency and builds AI-agent workflows for client acquisition and delivery.
20
+
21
+
In one experiment, he gave Claude the Prisma docs and CLI, then left an outreach workflow running overnight.
20
22
21
23
By morning, Claude had generated roughly 50 websites for spas in Vancouver.
22
24
23
-
Each site was part of a larger workflow: find businesses in a target market, check whether their website exists or needs work, research the business, generate a custom site, ask Ali for approval, deploy it, and prepare an outreach email with the live URL.
25
+
Each site was part of a larger loop: find businesses in a target market, check whether their website exists or needs work, research the business, generate a custom site, ask Ali for approval, deploy it, and prepare an outreach email with the live URL.
24
26
25
27
The interesting part is not just that AI can generate the sites. It is that the agent can move from generated code to a working URL without Ali turning deployment into a separate project.
26
28
27
29
Prisma Compute gave Ali's agent a deployment path it could actually operate: docs, CLI commands, terminal output, and a working URL.
It has been working pretty great. Claude almost one-shot this solution.
31
36
</Quotes>
32
37
33
38
That is the story: AI can make software feel cheap to create, but generated code only becomes useful when it can run somewhere. For this workflow, Ali said getting to a working URL felt easier than Railway.
34
39
35
40
## What Ali is building
36
41
37
-
Ali runs a boutique software agency and has been experimenting with AI agents as a new way to build and sell software. His current project is an outreach system for agencies and service businesses.
42
+
The project is an outreach system for agencies and service businesses.
38
43
39
44
Instead of sending a generic cold email, the system creates something useful first.
40
45
@@ -48,6 +53,8 @@ The flow looks like this:
48
53
- deploy the site
49
54
- write the outreach email with the live URL
50
55
56
+

57
+
51
58
Ali described the message as something closer to: "I noticed your business does not have a great website. I created this free version for you. Check it out."
52
59
53
60
The product is still early, but the workflow already changes the economics of outreach. If AI can create a useful asset before the first email, the outreach can start with proof instead of a promise.
@@ -64,7 +71,10 @@ Ali gave Claude the [Prisma docs](https://www.prisma.io/docs/compute), asked it
64
71
65
72
For Ali, the important part was not a dashboard tour. It was that the agent could use the CLI, deploy the app, and get a working URL.
0 commit comments