Skip to main content
usedby

75–80%

CSAT score of the Rasa-powered agent

As published on rasa.com. Captured by usedby on Oct 8, 2026.

What happened

JetBrains uses Rasa to run a single AI support agent that recognizes customer intent across its product catalog, answers routine questions from its internal knowledge base, and escalates other cases to the right human team with context already captured. It replaces a fragmented set of separate contact forms and is deployed on-premise on JetBrains' own infrastructure.

Summary written by usedby from the source page, in English. The figures are those of Rasa and JetBrains, not ours.

  • 3,000“processing roughly 3,000 conversations per month”

JetBrains' Rasa-powered agent is now live across the key entry points of their support ecosystem, processing roughly 3,000 conversations per month and sustaining a CSAT score of 75–80% — numbers that put the agent on par with their human support team in terms of customer satisfaction.

From the page. rasa.com, captured Oct 8, 2026

We wanted something that's not just a deflection tool

Letic, JetBrains. Source, captured Oct 8, 2026

What the story claims, and what we checked

We compared the story with its live page on Oct 8, 2026.

  • The figure: 75–80%CheckedThe figure is on the page; its label is our wording.
  • The passage quoted aboveCheckedCopied word for word from the page, near the name of JetBrains.
  • JetBrains uses RasaCheckedConfirmed line. Latest check across sources: Oct 8, 2026.
  • The result itselfNot checkedWe quote it; we did not measure it.

Same company, same tool or same industry.

JetBrains uses Weights & BiasesAnother tool at JetBrains10%“T-Mobile's virtual assistant has reached 10% of Messaging customers”T-Mobile uses Rasa. Another customer of Rasa50%of production time savedMiro uses Runway. Same industry: DevTools & Infrastructure