Prerequisite: Verify the User has the Admin role and AI enablement admin permission.

Only Admins with this permission can view and accept the AI policy through Pulse, which displays a brief message with a link to the policy document. Administrators must accept the policy on behalf of the entire team.

For Nexa permission details, see User Management.

Non-administrative accounts receive a message instructing them to contact their administrator to enable Nexa.

1. Navigate to the Left Navigate pane and click VSI or DPI.

   Image: Nexa

   

2. Click Nexa on the navigation to see the Nexa page.

   Image: Nexa homepage

   

3. On the Nexa screen, click Enable Nexa for My Team to enable Nexa for the team.

   Image: Nexa Counter

   

The contextual action buttons appear alongside agent responses to provide intelligent, task-relevant follow-up suggestions. These buttons dynamically surface recommended next steps based on the agent’s output, enabling efficient continuation of analysis without manually formulating additional queries. The action buttons support common workflows such as drilling down into specific dimensions, refining filters, and comparing time periods. By presenting these contextual options in real time, the feature reduces interaction friction, accelerates decision-making, and enhances overall user productivity. This enhancement strengthens guided analytics capabilities by embedding actionable intelligence directly within the conversational experience, ensuring a seamless transition from insight to deeper exploration.

To see the action buttons,

1. Click the Settings button.

2. On the Manage screen, switch on the Contextual Actions toggle.

   

Tokens

Tokens are the fundamental units of text that large language models (LLMs) process. Nexa interprets text by breaking it into tokens, analyzing them, and predicting subsequent tokens to generate responses. Understanding tokens and their usage is crucial for effective use of Nexa. Tokenization influences how queries are processed, the accuracy of results, and the overall efficiency and cost of operations. Conviva continues to optimize token usage to ensure responses remain accurate, efficient, and cost-effective.

For example, the sentence “Nexa makes data simple” may be split into tokens such as “Nexa”, “makes”, “data”, and “simple”.

LLMs

LLM stands for Large Language Model. Nexa generates code using Gemini 2.5 Flash, which provides robust programming performance.

Note: Customer data from Nexa is never used to train Gemini AI.

At a high level, LLMs function as advanced autocomplete systems. They do not possess knowledge in the human sense; instead, they generate outputs by identifying and applying patterns learned during training. In Nexa, the LLM generate the insights that aligns with a given prompt, and the dashboard.

Token limits

LLMs can only handle a certain number of tokens at a time, which includes both:

• The input you give (for example, a long question or document)

• The output it generates (for example, the response, or the code)

• System Prompts or contexts

Prompts

A prompt is a message you send to the AI. How you write your prompts is key to getting good results.

Context

Context refers to all domain information available to the AI, including prompts, prior responses, and existing code. The context window defines the amount of text an LLM can process simultaneously. Nexa provides a large context window; however, the AI cannot be relied upon to retain the entire conversation. Larger context windows also consume tokens more quickly, which increases cost. To preserve context while maintaining a smaller window, the AI can summarize the conversation to date and then reset the context window.

Note: If Nexa is not used for 30 days, the conversation history will be removed.

Understanding Tokens – Monthly Token Limit

Nexa employs large language model (LLM) technology to process prompts and generate sites. While knowledge of the underlying technical details is not required, it is essential to understand that LLMs operate on a token-based system. Tokens provide a standardized measure of Nexa’s processing workload. Nexa structures its free and paid plans around token usage.

Token Display in Nexa

Token usage in chat provides insight into the number of tokens consumed by prompts. Nexa displays token usage by default.

Nexa uses Token when it:

• Reads the input

• Think and process

• Builds the output

Larger and more complex websites or applications require more tokens to generate.

Note:  Conviva provides 100 million free tokens each month for every customer. The counter refreshes at the start of every month (UTC zone), and unused tokens do not carry over. Once the free tokens are utilized, contact Conviva Support for additional access.

Accuracy

LLMs can generate inaccurate or outdated outputs for several reasons:

• Training set age: LLMs train on large datasets but cannot access information created after the training process concludes. When building software, developers must recognize that the LLM may not be aware of the latest versions of tools and frameworks.

• Hallucination: LLMs operate predictively rather than deterministically. They may return different outputs for identical prompts and occasionally generate false information.

Nexa enables real-time, user-level experience analysis, allowing Customer Support teams to instantly view session histories, performance issues, and user journeys.

For example, “Show issues for user 12345” or “List the last five sessions for client xyz,” teams get immediate, context-rich insights without switching dashboards.

The new User Timeline Dashboard consolidates session data, errors, and performance anomalies into a single, intuitive view. By combining performance telemetry with experience metrics, Nexa accelerates troubleshooting and improves ticket resolution. Overall, this capability helps teams understand user impact more clearly and deliver faster, more effective customer support.

For more information on user timeline, see User Timeline.

Example prompt and response:

"What were the last five sessions for client ID 1158818?”

To save the sessions,

1. After asking the query, click the Save Analysis icon.

   

2. Select the Visibility criteria.

   

3. Click Save and see the entry in the Nexa home page and in All Sessions page.

Nexa provides an option to rename saved sessions, making it easier to identify, organize, and retrieve them over time. Clear session names improve context tracking and keep your workspace easy to navigate.

To rename a session,

1. Click the Conversations icon to see all sessions.

   

2. Click the Kebab icon adjacent to the saved session which needs to be renamed.

   

3. On the Rename Session pop-up, update the name for the session and click Save to save the updated session.

   

   Note:  Saved sessions are retained for 30 days from the date they are saved.

Nexa enables pinning of a session to ensure prioritized visibility and quick access. Pinning keeps the selected session prominently displayed within the workspace. This functionality supports efficient session management and streamlined navigation.

To pin a session,

1. Click the Conversations icon to see All Sessions.

   

2. Click the Kebab icon adjacent to the saved session which needs to be pinned.

   

3. The pinned session is displayed in the pinned section of All Session page.

   

   Note:  Pinned sessions do not expire and cannot be deleted. Nexa allows a maximum of 10 pinned sessions at any given time.

Analyze any flow in Nexa and Nexa shows additional insights and recommendations for the flow.

Example prompt and response:

"Show details on application login process for the last week?"