Observability Dashboard

Observability Dashboard vous permet d'analyser les capacités AI utilisées par Copilot, Autopilot Knowledge et Autopilot (Omilia). Le tableau de bord fournit des informations complètes sur la performance de réponse générative, vous permettant d'identifier les axes d'amélioration et d'optimiser vos opérations.

Les données dans Observability Dashboard sont conservées pendant un an. Cette période DE conservation peut évoluer à l'avenir en fonction des mises à jour du produit.

Copilot

Le Observability Dashboard pour Copilot fournit des informations sur les Métriques de performance de AI Agents (Cognigy) for Process Automation (Task Assist), les réponses génératives, les Requêtes Copilot for Agents et Automated Summary (AutoSummary).

  1. Cliquez sur le sélecteur d'application , accédez à Data & Analytics, puis sélectionnez Actions.

  2. Sur Actions, cliquez sur Observability Dashboard.

    Par défaut, le tableau de bord Copilot s'affiche. Il comprend les graphiques suivants :

  3. Si nécessaire, mettez à jour la Période du tableau de bord et sélectionnez le type d'interaction dans Canal. Choisissez d'afficher les détails des interactions Voix , des interactions Chat , ou de Toutes.

  4. Cliquez sur Exécuter la requête. Les trois graphiques sont mis à jour pour refléter les dates et les canaux souhaités.

AI Agents (Cognigy) for Process Automation (Task Assist) Métriques de performance

La vue AI Agents (Cognigy) for Process Automation (Task Assist) Métriques de performance fournit une analyse détaillée de l'exécution des tâches, y compris l'activité assistée par AI et manuelle, l'état d'exécution, les résultats et les tendances de performance. Utilisez cette vue pour explorer la progression des tâches à travers différentes étapes, évaluer l'adoption de l'AI et identifier des opportunités d'améliorer l'efficacité de l'exécution.

  1. Cliquez sur l'étiquette AI Agents (Cognigy) for Process Automation (Task Assist) Métriques de performance de l'en-tête du graphique pour explorer les statistiques en détail.

  2. Les AI Agents (Cognigy) for Process Automation (Task Assist) cartes KPI fournissent une vue synthétique des données affichées dans le graphique AI Agents (Cognigy) for Process Automation (Task Assist) Métriques de performance. Utilisez ces cartes pour évaluer rapidement AI l'adoption, le volume d'exécution et la performance générale sans analyser l'intégralité du flux de tâches.

    1. État de Task Assist : Indique comment les tâches sont distribuées en fonction de la manière dont elles ont été traitées.

      • assistée par ai : Nombre total de tâches pour lesquelles l'IA a fourni une assistance.

      • Manuel : Nombre total de tâches terminées sans l'aide de AI.
        Utilisez cette carte pour comprendre le niveau d'adoption de l'IA.

    2. État de l'exécution : indique la progression des tâches après leur lancement.

      • Exécution assistée par l'AI : Nombre de tâches pour lesquelles les suggestions d'IA ont été acceptées et exécutées.

      • Exécution manuelle : Nombre de tâches exécutées manuellement.

      • Rejeté : Nombre de tâches pour lesquelles les suggestions AI n'ont pas été acceptées.
        Utilisez cette fiche pour évaluer la fréquence d'utilisation des suggestions ai par rapport à leur rejet.

    3. Résultat d'exécution : Affiche le résultat final des tâches exécutées.

      Réussite : Nombre de tâches complétées avec succès.

      Échoué : Nombre de tâches qui n'ont pas abouti.
      Utilisez cette carte pour évaluer l'efficacité de l'exécution générale.

  3. Le graphique AI Agents (Cognigy) for Process Automation (Task Assist)Métriques de performance montre comment les tâches passent de la disponibilité à l'exécution et au résultat final. Utilisez ce graphique pour comprendre comment l'assistance AI influe sur l'exécution des tâches et les taux de réussite. Chaque valeur du graphique est représentée sous forme de nœud, et les connexions entre les nœuds montrent comment les tâches passent d'une étape à l'autre. Les nœuds sont décrits comme suit :

    1. Disponible : Le nombre total de tâches qui auraient pu être exécutées pendant la période sélectionnée. Il s'agit du nœud de départ dans le graphique. Toutes les tâches partent de ce point et passent dans un type d'exécution.

    2. Type d'exécution : les Tâches à partir de Disponible sont réparties dans les catégories suivantes :

      • AI-assisted: Tâches pour lesquelles l'AI a suggéré ou aidé l'action.

      • Manuel : Tâches effectuées sans l'assistance de AI.
        Ces catégories indiquent la manière dont les tâches sont traitées au départ.

    3. État d'exécution : Cette étape indique si les tâches ont été exécutées et comment. Les Tâches de chaque type d'exécution passent à un état d'exécution :

      • De AI-assisté :

        • Exécution assistée par AI : suggestions ai qui ont été acceptées et exécutées.

        • Rejeté : AI suggestions qui n'ont pas été acceptées.

      • À partir de Manuel :

        • Exécution manuelle : Tâches exécutées manuellement.

  4. Le graphique Total Execution Metrics Over Time indique comment les Exécutions assistées par AI et les exécutions manuelles varient sur la période sélectionnée, ce qui vous aide à comprendre les tendances d'adoption et d'utilisation de l'IA. Chaque ligne représente un type d'exécution (violet pour les exécutions assistées par IA et gris pour les exécutions manuelles), et chaque point du graphique indique la répartition des exécutions à un moment précis. Cela vous permet de comparer la proportion ou le volume des exécutions assistées par IA par rapport aux exécutions manuelles au fil du temps, ce qui facilite l'identification des modèles, des changements de comportement et des variations du volume d'exécution.

  5. Le graphique Total Execution Metrics by Task montre comment les Exécutions assistées par AI et les exécutions manuelles sont distribuées entre les différentes tâches pour les filtres sélectionnés. Chaque barre représente une tâche, avec des segments indiquant le type d'exécution (violet pour l'assistance par IA et gris pour le manuel). La hauteur de chaque segment indique la proportion ou le nombre d'exécutions. Utilisez ce graphique pour comparer la manière dont les tâches sont traitées, identifier les tâches qui dépendent davantage de l'assistance par IA et détecter les tâches nécessitant une plus grande implication manuelle.

  6. Le graphique Temps d'Exécution moyen affiche la distribution des temps d'exécution pour chaque tâche, ce qui vous aide à comprendre la variabilité et l'efficacité entre les tâches. Chaque boîte représente une tâche et affiche la plage des temps d'exécution, y compris les valeurs minimum, maximum et médiane. La Position et la taille de la boîte indiquent la durée habituelle des tâches et l'ampleur de la variation existante. Utilisez ce graphique pour identifier les tâches dont les temps d'exécution sont plus longs ou incohérents, et pour repérer les opportunités d'amélioration des performances.

  7. Si nécessaire, mettez à jour la Période pour le tableau de bord, sélectionnez le type d'interaction dans Canal, puis sélectionnez la configuration ou le persona Copilot dans le Profil Copilot. Cliquez sur Exécuter la requête. Les graphiques sont mis à jour pour refléter les dates, les canaux et les profils Copilot souhaités.

  8. Vous pouvez personnaliser les données qui apparaissent dans les graphiques :

    1. Dans les graphiques Total Exécution Metrics Heures supplémentaires et Total Exécution Metrics par tâche, vous pouvez basculer entre Nombres absolus ou Pourcentage.

    2. Dans tous les graphiques, cliquez sur Maximiser pour afficher les données en plein écran.

  9. Faire défiler vers le bas pour afficher les données de performance détaillées regroupées dans un tableau. Par défaut, les données peuvent être regroupées par nom de l’action. Le tableau vous aide à analyser la manière dont les tâches spécifiques sont traitées. Pour chaque ligne regroupée, le tableau affiche des valeurs telles que :

    • Total exécuté : nombre de fois où la tâche a été exécutée.

    • AI-assisté : Nombre de fois où la tâche a été assistée par AI Agents (Cognigy) for Process Automation (Task Assist).

    • Exécution assistée par AI : Nombre de fois où l'agent a utilisé l'exécution suggérée par AI Agents (Cognigy) for Process Automation (Task Assist).

    • Exécution moyenne assistée par AI : le pourcentage moyen d'exécution assistée par IA.

    • Total Réussite : Le nombre de fois où la tâche a abouti à un résultat réussi.

    • Réussite moyenne : Le taux de réussite moyen pour cette tâche.

  10. Cliquez sur un nom d’action pour afficher les requêtes spécifiques et leurs détails, par exemple :

    1. Liste des interactions individuelles liées à l'action sélectionnée.

    2. Détails clés tels que l'ID D'INTERACTION, le texte de la requête, le nom DE L'AGENT, l'ensemble de compétences, le nom DE L'ÉQUIPE, le nom bot et l'état de l'intention.

    3. Réponses horodatées du bot pour un contexte plus approfondi sur la manière dont l'action a été exécutée.

    4. Des indicateurs de performance tels que le temps d'exécution, le nombre de réussites et le taux de réussite, aidant les utilisateurs à évaluer l'efficacité de chaque action.

  11. Pour chaque requête, vous pouvez cliquer sur le bouton Info situé à côté de l'interaction et afficher les commentaires sur la requête de l'interaction.

  12. Vous pouvez basculer le mode d'affichage de ces données. La vue par défaut s'effectue par nom de l'action. Cliquez sur Group By pour changer le regroupement de nom de l’action à Id d’interaction ou par toute autre option répertoriée dans le menu déroulant. Les données réapparaissent en fonction du nouveau regroupement.

  13. Pour télécharger toutes les données, visibles et masquées, en fonction des filtres définis dans le générateur de requêtes, consultez la section Export.

Affichage des données sur les Réponses génératives

Les réponses génératives sont des réponses générées par AI fournies au cours des interactions.

  1. Click the Generative Responses label to drill down into the statistics. Three graphs appear:

    • Over Time: Shows the percentage of answers that were used, modified, ignored, or resulted in no answer over time.

    • By Category: Displays the details by category.

    • Average KB Per Interaction: Shows the average number of knowledge base interactions per day.

  2. You can customize data that appears in the graphs:

    • In the Over Time and Category graphs, you can toggle the display of different answer statuses by clicking on the legends.

    • In the Over Time and Category graphs, click Absolute Numbers or Percentage to switch between percentages and absolute numbers.

    • In all three graphs, click Maximize to view the data in a table format.

  3. Scroll down to see the data grouped by categories. The Categories View organizes the knowledge base answers into different categories, offering a structured approach to analysis. Each category presents:

    • Agent name

    • Team

    • Skill

    • Total volume of knowledge base answers

    • Average adherence score

    • Average number of links and images provided

    • Average knowledge score (score assigned by the knowledge base)

  4. Click a category to view the related queries and their details, such as:

    • Query sent to the Knowledge Base

    • Suggested knowledge base answer

    • Agent's actual response

    • Number of links and images provided

    • Query Feedback

    • Adherence score (the similarity between suggested and actual response)

    • Offset from the beginning of the interaction

    For each query, you can:

    • Click Play Interaction to listen to the audio of the interaction (if available).

    • Click the Info button next to the query. You can view the query feedback of the interaction. In the Response details panel on the right, you can see whether the AI generated response received positive   or negative  feedback, along with any comments and tags provided.

  5. You can change how the data is grouped. The default view is by category. Click Group By to change the grouping from Category to one of the following:

    • Master Contact

    • Team

    • Skill

    • Agent Name

    The data reappears based on the new grouping.

Viewing Data About Agent Queries

app Queries displays information about the knowledge base answers generated on demand based on agent questions. It provides graphs that show the status of direct queries and adherence scores.

  1. Click the chart heading, app Queries, to drill down into the statistics. The first graph shows the percentage of responses and no responses over time. The second graph displays the details by category.

  2. You can toggle the display of different answer statuses by clicking on the legends.

  3. Click Absolute Numbers or Percentage to switch between percentages and absolute numbers.

  4. Click Maximize to view the graph in full screen.

  5. Scroll down to see the data grouped by categories. The Categories View organizes the knowledge base answers into different categories, offering a structured approach to analysis. Each category presents:

    • Total volume of responses

    • Number and average of no responses

    • Average number of links and images provided

    • Average knowledge score (score assigned by the knowledge base)

  6. Clicking on a category reveals the specific queries and their details, such as:

    • Agent query sent to the Knowledge Base

    • Response to the agent query

    • Number of links and images provided

    • Date and time of the response

    • Average knowledge score

Viewing Data About Automated Summary (AutoSummary) Queries

Automated Summary (AutoSummary) shows how auto-generated summaries perform. You can see graphs that track performance over time, with data grouped by intent and skill. Detailed tables display suggested summaries alongside actual summaries, complete with adherence scores to gauge accuracy. For more comprehensive details, you can play back specific interactions, which will give you a full picture of how summaries are generated and used in real conversations.

Auto-generated summaries are supported in the Observability Dashboard for both CXone ACD and CXone non- ACD environments.

  1. Click on the chart heading, AutoSummary, to drill down into the statistics.

    • The first graph shows the percentage of summaries that were used over time. Summaries are classified as As Is, Minor Revisions, Revised, and Ignored.

    • The second graph displays the details By Intent.

    • The third graph displays the details By Skill.

    • The fourth graph displays the details By Team.

    You can toggle the display of different answer statuses by clicking on the legends.

  2. Click Absolute Numbers or Percentage to switch between percentages and absolute numbers.

  3. Click Maximize to view the graph in full screen.

  4. Scroll down to see the data grouped by categories. The Categories View organizes summaries into different categories. Each category presents:

    • Agent Names

    • Total volume of responses

    • Number and percentage of no responses

    • Average number of links and images provided

    • Average knowledge score (score assigned by the knowledge base)

  5. Click a category to view the specific queries and their details, such as:

    • Agent query sent to the knowledge base

    • Response to the agent query

    • Overall Feedback

    • Number of links and images provided

    • Date and time of the response

    • Average knowledge score

    • Adherence Score

  6. In Automated Summary (AutoSummary), the adherence score is determined by the LLM using the following approach:

    • The LLM compares the meaning of the text rather than the exact wording.

    • If the actual summary and suggested summary text are the same in meaning, the score is high.

    • If the suggested summary contains additional details, such as minor revisions not in the actual summary then the score is medium.

    • If the suggested summary and the actual summary text have different contexts, then the score is low.

    • If the agent does not save the summary, or saves the summary without making any edits, the final summary is treated as identical to the suggested summary. Observability Dashboard updates the columns as follows:

      • Actual Summary: Same as Suggested Summary

      • Adherence Score: High

      • Comment: As Is (until a final summary is received)

    • If a final summary is received within 90 days and it differs from the originally suggested summary, Observability Dashboard updates the record as follows:

      • Actual Summary: Updated actual summary from Automated Summary (AutoSummary)

      • Adherence Score: Recalculated based on the difference between the suggested and actual summaries

      • Comment: Updated from As Is to Minor Revisions or Revised, depending on the level of change

        Currently, Observability Dashboard does not support tracking multiple sequential edits to the same Automated Summary (AutoSummary).

  7. Click the Info button next to the query. You can view the overall feedback of the interaction. In the Response details panel on the right, you can see whether the interaction received positive   or negative  feedback, along with any comments and tags provided.

As a CX leader, Mark wants to use the Observability Dashboard to identify knowledge gaps in the knowledge base. He notices that many knowledge base suggestions are being modified or ignored. Mark clicks on Generative Responses to view data by category. He focuses on categories with low average adherence scores, indicating misalignment between suggestions and actual responses. By expanding low-scoring categories like Billing and Payments, Mark sees low adherence to queries about payment plans and refund policies, suggesting knowledge gaps in those areas.

Through the Observability Dashboard, Mark can pinpoint topics needing knowledge base enhancements. He can then work with the knowledge base team to address these gaps, improving the quality of suggestions for better customer interactions.

Business Impact View

The Business Impact view is a dynamic panel within the Copilot dashboard that provides a consolidated view of key performance metrics influenced by agent activity. It offers visual insights into operational trends such as After Call Work (ACWClosed état qui permet à un agent de remplir les exigences de travail après avoir terminé une interaction.) and Average Handle Time (AHTClosed Le Temps de traitement moyen est la durée moyenne qu’un agent consacre au traitement d’une interaction.) agent performance indicators. By expanding this menu, you can analyze monthly trends, apply filters to focus on specific teams, skills, or agents, and compare performance averages across selected categories. The date range and filter options in the Business Impact view are independent of those in the Observability Dashboard.

  1. To open the Business Impact menu, click the upward-facing arrow located at the bottom of the Copilot dashboard. This expands the bottom panel and shows detailed performance metrics:

  2. At the top of the dashboard, update the Dashboard date range to define the period for which you want to view ACW and AHT data. You can select from preset options like Last 2 days, Last 7 days, Current month, or set a custom range. By default, the date range is the same range defined in the Copilot dashboard. Once selected, the graph automatically updates to show the average ACW and AHT duration for each month within that range.

  3. Use the Filter By options to narrow down the data based on Teams, Skills, or Agent Name. You can select up to 5 values per filter type. For example, choose 5 teams, 5 skills, or 5 agent names. Apply filters to compare performance across different groups or individuals.

  4. To remove a filter category from the ACW and AHT graph, click the X icon next to the selected team, skill, or agent name. Once removed, the graph updates automatically to exclude that category from the visualization.

  5. In the dashboard, the metrics All Skills Avg., All Teams Avg., and All Agent Names Avg. appear dynamically based on the filters you apply. When you filter by Skills, the graph displays the All Skills Avg. line to show the average ACW and AHT duration across the selected skill groups. Similarly, filtering by Teams or Agent Name will show All Teams Avg. or All Agent Names Avg. respectively.

  6. Interpreting the graphs:

    • Upward Trend: Indicates an increase in time. For ACW, agents are spending more time on post-call tasks. For AHT, calls are taking longer to handle.

    • Downward Trend: Indicates a decrease in time. For ACW, agents are completing post-call work faster. For AHT, calls are being handled more efficiently.

    • Sudden Spikes or Drops: May signal changes in workload, process, or tool usage. These should be reviewed to understand the cause.

Viewing the ACW Data

The ACW (After Call Work) graph helps track how much time agents spend on post-call tasks each month, showing the average duration across all calls. ACW refers to the time an agent spends completing tasks after ending a customer call—such as writing notes, updating systems, or tagging the interaction. The average ACW duration is calculated by dividing the total ACW time by the number of calls handled during the selected period:

Average ACW= Total ACW time / Number of calls

This graph allows you to compare performance across teams, skills, and individual agents, identify patterns or unusual changes in workload, and make informed decisions. Additionally, it helps indicate whether there is an increase or decrease in ACW for a specific team, skill, or agent over time. For example, a rising line may indicate growing post-call workload, while a downward trend may suggest improved efficiency or process changes.

The ACW graph is presented as a line graph, where the X-axis represents time in monthly intervals based on the selected date range, and the Y-axis shows the average ACW duration, typically measured in seconds or minutes. Each data point on the graph reflects the average ACW for that specific month. The graph includes interactive features such as hover-to-view exact values, dynamic updates based on applied filters and date range, and legends that display the selected filters for easy reference.

Viewing the AHT Data

The AHT (Average Handle Time) graph helps track how much time agents spend handling customer interactions each month, showing the average duration across all calls. AHT includes the entire interaction time—such as talk time, hold time, and After Call Work (ACW). The average AHT duration is calculated by dividing the total handle time by the number of calls handled during the selected period:

Average AHT=Total Handle Time / Number of Calls

This graph allows you to compare performance between teams, skills, and individual agents, identify patterns or unusual changes in interaction duration. Trends in the AHT graph can help identify increases or decreases in AHT for specific teams, skills, or agents over time. For example, a rising line may indicate longer customer interactions due to complexity or inefficiencies, while a downward trend may suggest streamlined processes, improved agent performance, or better system support.

The AHT graph is presented as a line graph, where the X-axis represents time in monthly intervals based on the selected date range, and the Y-axis shows the average AHT duration, typically measured in seconds or minutes. Each data point on the graph reflects the average AHT for that specific month. The graph includes interactive features such as hover-to-view exact values, dynamic updates based on applied filters and date range, and legends that display the selected filters for easy reference.

The Observability Dashboard supports new Copilot features for Engagement Hub, allowing you to monitor feature performance across different client types.

  • For CXone ACD clients: You see data for auto-generated summaries, team details, and skill information.

  • For non-CXone ACD clients: Team and skill data is not available, and related features are hidden.

  • For tenants using both ACD and non- ACD applications: The dashboard displays only ACD-related data.

Autopilot Knowledge

The Observability Dashboard for Autopilot Knowledge shows data about how well your automated system handles customer questions. You'll see a graph that displays performance trends over time. This lets you track changes daily, weekly, or monthly.

  1. Click the app selector and select Actions.

  2. On Actions, click Observability Dashboard.

  3. Click the Autopilot Knowledge tab. Set the desired Date Range for the dashboard, and click Run Query. It displays three charts:

Viewing Data About Overall Effectiveness

This graph displays a high-level summary of the Autopilot Knowledge chatbot's performance and status.

  1. Click the Overall Effectiveness graph heading to drill down into the statistics. Four graphs appear:

    • Engaged: Displays the number of visitors who engaged with the chatbot, helping you understand the engagement trends over time.

    • Contained: Displays the percentage and count of chatbot users who completed their conversation without needing escalation to a live agent. With this metric, you can assess how effectively the chatbot resolves queries independently.

    • Elevated: Displays the percentage and count of chatbot users who escalated their conversation to a live agent, highlighting cases that required human intervention. With this metric, you can monitor how often the chatbot hands off conversations to human agents.

    • Abandoned: Displays the percentage and count of chatbot users who abandoned an ongoing conversation. With this metric, you can identify drop-off points and improve user engagement.

  2. You can customize the data that appears in the graphs:

    • Click Absolute Numbers or Percentage to switch between percentages and absolute numbers.

    • Click Maximizeto view the graph in full screen.

Viewing Data About Gen AI Performance

This graph displays the percentage of user queries that were effectively addressed by the generative AI engine.

  1. Click the Gen AI Performance label to drill down into the statistics. Three graphs appear:

    • Over Time: Displays the percentage of chatbot responses over time.

    • By Category: Displays the percentage of chatbot responses by category.

    • Queries to Generative Model: Displays the total number and percentage of chatbot queries processed by the generative engine. This metric provides insight into how frequently the generative engine is utilized in handling user interactions.

  2. You can customize the data that appears in the graphs:

    • In the Over Time and Category graphs, to toggle the display of different answer statuses, click on the Response or No Response legends in the graphs.

    • Click Absolute Numbers or Percentage to switch between percentages and absolute numbers.

    • Click Maximizeto view the graphs in full screen.

  3. Scroll down to see the data grouped by categories. The Categories View organizes the chatbot responses into different categories. Each category presents:

    • Total volume of responses

    • Total number of no responses

    • Average number of links and images provided

    • Average knowledge score (score assigned by the knowledge base)

  4. Clicking on a category reveals the specific queries and their details, such as:

    • Contact number of the interaction

    • Query that initiated the chatbot interaction

    • The chatbot’s reply, generated based on the user’s input, intent, and context.

    • Number of links and images provided

    • Date and time of the response

    • Average knowledge score

  5. You can switch the way you view this data. The default view is by category. Click Group By to change the grouping from Category to Contact Number. The data reappears based on the new grouping.

Viewing Data About Bot Performance

This graph displays the distribution of chatbot intents, highlighting the top six most common user requests along with fallback occurrences. It helps you understand what users ask and how the chatbot responds.

  1. Click the Bot Performance label to drill down into the statistics. Two graphs appear:

    • All Bot Intent: Displays the most common user requests and fallback cases, helping you improve how your chatbot responds.

    • Abandonment Indicator: Displays which chatbot intents were most common before users abandoned the conversation. It helps you identify drop-off points and improve user retention.

  2. You can customize the data that appears in the graphs:

    • Click Absolute Numbers or Percentage to switch between percentages and absolute numbers.

    • Click Maximizeto view the graphs in full screen.

Autopilot (Omilia)

The Observability Dashboard for Autopilot (Omilia) shows how effectively your knowledge base can handle customer questions. Use this dashboard to identify areas where you can add articles to your knowledge base or improve existing articles to better answer customer questions.

  1. Click the app selector and select Actions.

  2. On Actions, click Observability Dashboard.

  3. Click the Autopilot (Omilia) tab. It displays the Gen AI Performance graph.

  4. Set the desired Date Range for the dashboard, and click Run Query.

Viewing Data About Gen AI Performance

This graph shows the number of user questions that received relevant and complete answers from the AI engine.

  1. Click the Gen AI Performance label to view details about the questions asked and the articles provided for the time period specified.

    Two graphs appear:

    • Over Time graph: Shows the number of successful responses and no-responses over the selected time period. A response indicates the user was shown an article. A no-response indicates that no matching article was found.

    • By Category graph: Shows the number of successful responses and no-responses by categories.

    You can customize the appearance of data in the graphs:

    • To switch between percentages and absolute numbers, click Absolute Numbers or Percentage.

    • To view the graph in full screen, click Maximize.

    • To toggle the display of different answer statuses, click on the Response or No Response legends in the graphs.

  2. Scroll down beneath the graphs to see a table that provides details on the queries. The queries are grouped by categories.

  3. Clicking on a category reveals the specific queries and the provided responses. Use this to identify areas where you might be missing articles in your knowledge base.

Generate AI Powered Knowledge Articles

  1. Click the app selector and select Actions.

  2. On Actions, click Observability Dashboard.

  3. Click the Generative Responses label to view detailed statistics.

  4. Scroll down to the data grouped by categories section. Click a category to view specific queries.

  5. Select a query and click the Info button.

  6. In the Response details panel on the right, click Create Article. An AI-generated article is drafted based on the transcript. You can edit the article as needed and then publish it.

    For complete information on editing and publishing an article, see the knowledge generation help.

  7. When an article is already published, the Create Article icon appears in purple with a checkmark . This means a knowledge article is available and you can view it, even if it was created by someone else.

Export Data from Observability Dashboard

  1. Click the app selector and select Actions.

  2. On Actions, click Observability Dashboard.

  3. Click the Generative Response label to view detailed statistics.

  4. Scroll down to the data grouped by categories section. Click Export. You can download all data, both visible and hidden, based on the filters set in the query builder.

  5. When you export data from theObservability Dashboard, some fields in the spreadsheet are represented by numeric codes. These codes correspond to specific tags and feedback types, as shown below:

    Tag

    value
    Accurate 1
    Complete 2

    Relevant

    		3
    Other 4 (for positive feedback)
    Inaccurate 5
    Incomplete 6
    Irrelevant 7
    Slow 8
    Other 9 (for negative feedback)

    Feedback type

    value
    Positive 1
    Negative 2