How it works
FCR is calculated as:
FCR = (Issues resolved on first contact / Total issues) x 100
Measuring FCR accurately requires defining "resolved", typically a combination of:
- No follow-up ticket from the same customer on the same issue within 72 hours
- Customer confirmation of resolution (positive feedback)
- Agent marks issue as resolved (less reliable as a standalone signal)
FCR is considered the most important support metric because it directly measures whether customers actually got their problem solved. A team with fast response times but low FCR is responding quickly without actually helping.
Why it matters
FCR is closely tied to customer satisfaction: a customer who has to come back is a customer who was not helped. Every repeat contact adds agent time and customer frustration. AI chatbots improve FCR by accessing comprehensive knowledge bases and providing complete answers rather than partial ones.
How Chatsy uses it
Chatsy improves FCR through comprehensive RAG retrieval that surfaces complete, accurate answers on the first interaction. When the AI lacks sufficient information to fully resolve an issue, it escalates to a human agent with complete context rather than providing a partial answer that would generate a follow-up contact.
Chatsy
What else should I know about First Contact Resolution (FCR)?
It is closely tied to customer satisfaction because it shows whether the problem was actually solved
Key takeawaysTest this in your own agent
Add your help content, ask the questions on this page, and check every answer before you publish.
Start freeChatsy
Example scenarios
- 01
AI chatbot achieving high FCR
A SaaS company measures FCR for AI chatbot interactions by tracking whether customers return with the same issue within 72 hours. The AI achieves 85% FCR on supported topics, matching human agent performance, because RAG retrieves comprehensive answers rather than partial information.
- 02
FCR failure analysis
A team discovers that their FCR for "integration setup" questions is only 45%. Investigation reveals the knowledge base article covers only the basic setup, not common error scenarios. After expanding the article with troubleshooting steps, FCR increases to 78% on the same topic.
- 03
Human-AI collaboration for FCR
For complex billing disputes, the AI cannot fully resolve the issue (30% FCR). But by pre-gathering account details, identifying the specific charges in question, and presenting options to the agent, the human agent achieves 92% FCR on escalated billing issues, higher than the 75% FCR without AI pre-work.
Key takeaways
- FCR measures the percentage of issues fully resolved on the first interaction without follow-ups
- It is closely tied to customer satisfaction because it shows whether the problem was actually solved
- Track FCR by topic to see which answers send customers back
- Repeat contacts add agent time and customer frustration on top of the original interaction
- AI chatbots improve FCR by providing comprehensive, RAG-grounded answers rather than partial responses