The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
One ordinary shift, replayed through an n8n order intake, lost 14 of 120 orders.
The replay had the interruptions that really happen, like a site restart and an e-mail limit. The old workflow lost EUR 2,504 of revenue and failed ten times without telling anyone, while the dashboard still looked fine. The repaired one lost none, and every remaining failure reaches a person in Slack. 45 automated checks confirm the numbers.
The ceramics studio is invented for the demo.
https://flowlab-dev.github.io/work/automation-repair/
How would you know today if your workflow dropped an order last night?
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Build log. I published my first n8n node.
1pm, the idea: put Jev, TypeSafe's decision model, inside n8n.
Jev does not write text. It reads a field and answers your question with a probability
for every option.
First thing, check whether it already existed. It did: six public packages. I read the
code of all six and noted what none of them did. I found a gap. Nobody measures the
confidence threshold. They all ask you to pick a number between 0 and 1 and hope.
That gap became the third operation in my node, calibration. You give it labeled
examples, it returns accuracy and coverage at every threshold and recommends one. In my
test, 0.5 let one wrong answer through and 0.7 let none.
Before writing the node, I ran a batch of tests on the model. Three things I learned:
• the same call repeated returns different probabilities, and no decision above 0.95
changed between runs
• 24 items in one request give the same answers as 1 item per request, at half the cost
• 28k tokens of unrelated text in the state changed nothing. 2k tokens of text that looked
like one of the options turned two answers wrong
23 unit tests, one live run against the API, three workflows executed inside n8n. By night
my first contribution to the n8n community was live.
Over the next few days I will show it applied: lead triage, extraction checks, content
filtering.
#n8n #automation #ai #jev
