Skip to main content

[Extension] How to Measure Your Chatbot's Resolution Rate and Quality on Blip with the Waizer Extension

  • Updated

  1. Introduction

  2. How to Monitor Chatbot Quality

  3. Best Practices

  4. Support

 

Brief Description: Track your chatbot’s performance score, resolution rate, error rate, overflow, and sentiment on Blip all in one dashboard, week by week.

 

Introduction

Anyone who operates a bot daily faces the same question: Is the bot solving the contact’s problem or just pushing the conversation to overflow? Without objective measurement, the evaluation becomes guesswork, tied to isolated complaints or the perception of whoever is closest to the support.

Waizer fills this gap with a Dashboard that assigns a performance score to each conversation and gathers operational indicators into a single view. From this, you can compare the bot’s health over time without relying on satisfaction surveys, which most users ignore after interacting with a bot. Did a new flow go live and the error rate increased? Did the score drop after a change in overflow? The answers are on the panel, without querying logs or requesting reports from the technical team.

Before You Start

Before analyzing the data, check if:

  • The Waizer extension is installed and active on the bot. Activate Waizer in the Blip Store.

  • The bot already has conversations recorded during the period you want to analyze.

  • You have access to the Waizer Dashboard.

 

How to Monitor Chatbot Quality

  1. Open Waizer on the desired bot and click Dashboard. The panel loads the indicators for the selected period.

Tela inicial do Waizer com o Dashboard de análise do chatbot aberto

  1. Use the date filter at the top of the panel to set the period. Adjust the interval whenever you want to compare one week with the previous one.

  2. Monitor the main indicators on the top cards:

  • Total Contacts: volume of contacts served during the period.

  • Error Rate: percentage of conversations where the bot failed.

  • Resolution Rate: percentage of conversations the bot successfully resolved.

  • Overflow Rate: percentage of conversations forwarded to human support.

  • Predominant Sentiment: how contacts felt during conversations in the period.

Each card shows a comparison with the previous period, so you can immediately see if the indicator improved or worsened.

Cartões de indicadores do Dashboard do Waizer mostrando total de contatos, taxa de erro, índice de resolução, taxa de transbordo e sentimento predominante

  1. Check the Performance Score, a rating from 0 to 100 that summarizes the chatbot’s overall performance based on operational, experience, quality, and impact metrics. The range indicates the assessment: Excellent (80 to 100), Good (60 to 79), and Needs Improvement (0 to 59). The card also shows how much the score increased or decreased compared to the previous period.

  2. Click View Full Report to open the performance report for the period, with analysis of indicators, strengths, main opportunities, and a plan of next steps. Use Export Report to generate a PDF version for sharing or presenting.

 

Best Practices

  • Monitor the indicators weekly to spot trends before they become problems.

  • Compare data before and after each flow adjustment.

  • Treat drops in the Performance Score or spikes in the Error Rate as signals to investigate the flow.

  • Cross-reference the Overflow Rate with topics to find demands worth automating.

  • Read the Predominant Sentiment alongside the Resolution Rate: a conversation can be resolved yet still leave the contact dissatisfied.

 

Support

If you have any questions or issues with the extension, contact us at support@wiv.com.br.

 

Need more help? Explore our content at Blip Academy or Blip Community, watch tutorials on our YouTube channel, or get your questions answered in our support channel 😃
 

Related articles