Chatbot Settings

Chatbot settings are managed from the Settings tab. Settings are organised into three sections, accessible from the left sidebar within the tab.

Chatbot Settings tab

Basic Information

Found under Chat Details → Basic Information.

  • Name — the display name of the chatbot. Required.

  • Description — a brief description of the chatbot’s purpose. Required.

  • Wait Before Reply (ms) — how long the agent waits after receiving a message before processing and responding. This batches rapid successive messages from the user into a single response. Default is 1000ms. Range: 0–30000ms.

Output Details

Found under Chat Details → Output Details. Only available after the agent has been created.

Defines the schema of structured data that this chatbot should extract or produce during a conversation. Used for downstream processing and integration.

KPIs

Found under Chat Details → KPIs. Only available after the agent has been created.

Define custom KPI metrics to track business outcomes from this chatbot. KPI values are tracked per conversation and visible in the Analytics tab.

Channels

The Channels tab deploys this chatbot to external platforms. Supported channels include messaging apps (WhatsApp, Telegram, Facebook Messenger, Viber, Zalo, Slack, Microsoft Teams) and event-driven triggers (GitHub, Jira, Databricks, Outlook Calendar, Agent Schedule).

See Channels for per-channel prerequisites, credentials, and configuration.

Conversations

The Conversations tab shows the conversation history for this chatbot. Each row represents a session with the caller details, timestamp, and duration. Click a row to open the full conversation detail view including the complete message transcript and any structured output fields that were extracted.

Analytics

The Analytics tab shows usage and cost metrics for this chatbot over a selectable time range: conversation volume, average duration, LLM token usage, and cost breakdown.

LLM Traces

The LLM Traces tab shows a log of every LLM call made during conversations. Each entry shows the prompt sent to the model, the model response, token counts, and latency. Use this tab to debug unexpected chatbot behaviour or verify that prompts are being constructed as expected.

Simulations

The Simulations tab lets you run predefined test scenarios against the chatbot without publishing. Define a set of test inputs and review the agent’s responses in a consistent, repeatable way. Results are saved and can be compared across runs.

API Access

The API Access tab provides code snippets and credentials for calling this chatbot programmatically via the OneByZero Neo API. Use this to integrate the chatbot into external applications or trigger conversations from your own systems.

The tab shows ready-to-use code examples in multiple languages with the agent’s API endpoint and authentication details pre-filled.