customer_support · finance · workflow

Brigit improves customer satisfaction 15% and achieves 40% ticket resolution with Ada AI agent

Brigit faced rising conversation volumes and email support remained manual-intensive, making it impossible to meet the 2.5-hour customer response expectation without massively scaling headcount.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Inbound email or chat arrives
Inbound emails account for around 30% of the monthly support conversation volume.
Tools used
Ada
Outcome

The Ada AI agent outperformed the scripted chatbot, achieving a 15% improvement in customer satisfaction and 40% ticket resolution, with over 6K users emailing the AI agent within two months of launch.

Results
Time savedaround 30%
Volume15%
Running since2022
Source

https://www.ada.cx/case-study/brigit

How we source this →

Grounding & classification
Source type: vendor customer story
31 fields verified against source quotes.
ai agentchatbotcontent generationconversational aisupport agentchat transcriptemailsupport tickethuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedfinancial servicesautomation ratecustomer satisfactiondeflection rateemployee productivityresponse time reductionvendor customer storycustomer supportticket triageautonomous resolutionintake to triage