Skip to content
evalship
Get started →
acme_demo /
support-bot
Public
Demo
A demo repo with sample data.
Set up your own repo
Open 7
Resolved 0
Ignored 0
#128 changed AI calls no eval covers
Test
Shorter support prompt
1 AI call
Last 2h ago
→
Next: fix the 2 remaining flaws
Test
→
support-chat · Promised something
Monitor
“I've refunded the full $240 to your card”
2 calls
Last 13h ago
→
lookup_order · Failed: Timeout after 5s
Monitor
3 calls
Last 21h ago
→
support-chat · Frustrated user
Monitor
“talk to a person”
1 call
Last 1d ago
→
A cheaper model for Eliza · To ship
Optimize
nano: 33% cheaper
Last 2d ago
→
Summaries that keep the terms · To ship
Optimize
must-keep passes more often
Last 3d ago
→