What is first contact resolution?

First contact resolution (FCR), explained

FCR asks whether the customer had to come back. If someone asks where their order is, gets an accurate answer and never contacts you about it again, that is a first contact resolution. If they are told to email another address, transferred, or return two days later because the answer was wrong, it is not.

There are two common ways to measure it. The first asks the customer after the interaction whether their issue was resolved. The second looks at behaviour: did the same customer contact you about the same topic within a set window, such as seven days? The behavioural method catches cases where a customer thought the answer was fine until it turned out not to be.

FCR is sensitive to how contacts are defined. Decide whether a transfer between the bot and a human in the same chat counts as one contact or two, and apply it consistently.

Improving FCR usually means giving the first responder, human or AI, what they need to finish the job: accurate content, access to order data, and authority for common exceptions.

How to measure it

Define a repeat-contact window (for example, same customer and topic within 7 days) and whether a bot-to-human handoff in one conversation counts as one contact.

Common mistake

How SuperBot relates

SuperBot helps the first conversation finish the job: it answers from your own content, looks up orders read-only after verifying the customer's email, and when it hands off, your team sees the full transcript instead of starting over.

• Human handoff rules that keep an AI agent from annoying customers
• AI chatbot evaluation checklist

Frequently asked questions

Related terms

• Resolution rateResolution rate is the percentage of customer conversations or tickets that end with the customer's issue solved. For AI support, it usually means conversations the bot resolved without a human. Because vendors define “resolved” differently, the number is only meaningful when you know the definition behind it and check it against repeat contacts and satisfaction.
• Average handle time (AHT)Average handle time (AHT) is the average amount of time an agent spends on one customer interaction from start to finish, including talking or typing, any hold time, and the follow-up work after the conversation ends. Contact centres use it for staffing and cost planning, but pushing it down too hard can hurt resolution and satisfaction.
• Human handoff (escalation)Human handoff is the point where an automated system such as a chatbot passes a conversation to a person, ideally with the full conversation history and context attached. Good handoff rules trigger on low confidence, sensitive topics, explicit requests for a human or signs of frustration, and tell the customer what happens next and how long it will take.
• Order status lookup (WISMO)Order status lookup is answering a customer's “where is my order?” question, known in ecommerce as WISMO, by retrieving the order's real status and tracking details from the store. It is one of the most frequent ecommerce support questions, which makes it a strong candidate for automation, provided the lookup verifies the customer's identity first.
• Customer effort score (CES)Customer effort score (CES) measures how easy it was for a customer to get an issue resolved or complete a task, usually by asking them to rate a statement such as “The company made it easy to handle my issue” on a numbered agreement scale. Lower effort is associated with stronger loyalty, which is why support teams track it.