Skip to main content
Agent behavior settings let you configure behavior profiles, alerts, agent transfer, Arch repair and triage, API and widget data access, attachments, omnichannel support, and governance policies.

Behavior profiles

The settings on the Behavior Profiles page let you define context-driven overrides for agent conversation behavior. Profiles apply in addition to any agent baseline when the defined conditions match, but don’t modify the core definition of the agent. Navigation: Project → Settings → Behavior Profiles

Create a behavior profile

Create profile

Select Create Profile to open the New Behavior Profile editor. The editor has two views: Structured, which presents each setting as a form field, and Raw ABL, which lets you edit the profile definition as code. Below the header, the profile editor organizes settings into the following sections: Behavior, Speaking, Listening, Interaction, and Authoring Note.

Behavior

Speaking

Listening

Keypad and speech input

These settings override the project-wide keypad and speech defaults for KoreVG voice calls. An empty field inherits the channel or platform default, which the editor shows below the field.

No-input handling configuration

This is only supported for pipeline voice using KoreVG.
Interaction Authoring Note: A free-text field for documenting when and why this profile applies. All settings default to Inherit, meaning the agent’s base configuration applies. Override any setting to customize behavior for the profile’s conditions. Select Save to create the profile, or switch to Raw ABL to edit the profile definition as code.

Alert settings

The Alert Settings page defines rules that trigger notifications when project metrics breach a threshold. The runtime evaluates each rule on a fixed cadence and delivers a notification by email or webhook when the condition matches. Navigation: Project → Settings → Alert Settings When the project has no rules yet, the page shows an empty state. Select Create alert rule to open the rule editor, or Browse available metrics to review every metric the evaluator can alert on before you start. Typical uses include containment rate drops, error spikes, latency increases, and sentiment degradation.

Create an alert rule

Select Create alert rule to open the New alert rule panel. The footer tracks what the rule still needs (for example, Still needed: name, metric, recipients) and keeps Save rule available once you supply those values. Select Cancel to discard the rule. If Deliver via : Email: If Deliver via : Webhook:

Subject scopes

Agent and LLM metrics

The Agent and LLM tabs list the same LLM metrics group. The Agent tab scopes each metric to agent activity, and the LLM tab scopes it to the LLM. All metrics in this group read from the LLM metrics source and support no channel or tool filters.

Tool metrics

Tool metrics read from the Platform events source. All three support channel filters, channel connection scope, and tool name and type filters.

Voice metrics

Voice metrics read from the Platform events source. All support channel filters and channel connection scope, and none support tool name and type filters.

Other metrics

The Others tab groups trace and sentiment metrics. Trace records Conversation sentiment

Agent transfer

The Agent Transfer Settings page configures defaults for agent transfer sessions, routing, voice gateway, and PII handling. These settings apply project-wide unless an individual agent or workflow overrides them at runtime. Navigation: Project → Settings → Agent Transfer
These are project-wide defaults for a human-agent transfer. An agent overrides them at runtime with an ESCALATE block’s routing and routing.voice. See Routing configuration and Voice transfer settings in the ABL reference.
The page organizes content into three collapsible sections. Select a section header to expand or collapse it. Select Save to apply changes or Reset to defaults to restore all values to defaults.

Default routing

Default Routing sets the fallback connection, queue, priority, and post-transfer behavior that the platform uses when an agent initiates a transfer. Individual agents or workflows can override these values at runtime.

Voice Gateway

Voice Gateway configures transfer behavior for voice channels. These settings determine how the platform hands off calls to the agent desktop over SIP or PSTN. Allowed transfer headers When Header Passthrough is on, the Allowed Transfer Headers table lists the SIP headers the platform can send on a transfer. Each row shows the header, its value source, its value, and its status. To change where an editable header gets its value, select a different option from its value source list. To allow another header, select Add header, enter the header name, and select Add.
If SIP settings are also defined in the agent DSL, the runtime resolves the transfer destination using the following priority order: the agent-defined default, then the project setting. If neither is available, the transfer fails. Learn how to define Trusted SIP Transfer Destinations in ABL.

PII handling

PII Handling controls how the platform treats personally identifiable information when transferring a conversation to a human agent.
Enabling De-tokenize Before Transfer exposes raw PII to the agent desktop. Only enable this for destinations where human agents have explicit authorization to view personally identifiable information.

Arch

The Arch page controls how Arch, the platform’s design and repair assistant, handles developer rulings, agentic repair, and failure triage for this project. Each setting shows the value it inherits and the value In effect, with its source (for example, On (platform default)). Override a setting only when the project needs a different value from the platform default. Navigation: Project → Settings → Arch Developer rulings Developer rulings are off by default. The Rulings list shows the rulings recorded for the project, or No rulings yet when there are none. Auto Loop agentic repair Qualification Select Save to apply changes, or Discard changes to return to the saved values.

Public API access

The Public API Access page configures which APIs end-users can access when authenticating through their organization’s identity provider (Azure AD, Okta, Google). Navigation: Project → Settings → Public API Access

Query API

Toggle the Query API to allow authenticated end-users to query agents through the public API endpoint. When you enable it, the following configuration fields appear: Session token duration

Public Widget Data

The Public Widget Data page controls the tables, columns, and SQL constructs that saved widgets can expose through the analytics:read scope. Projects start with sensitive analytics sources blocked, and all SQL constructs beyond a basic single SELECT stay disallowed until you enable them. Select Save to apply your changes. Navigation: Project > Settings > Public Widget Data

SQL validation

Choose which saved-widget SQL constructs the platform allows for analytics:read queries. DDL and mutation statements remain blocked regardless of these settings.

Restricted data

The Restricted data section lets you block specific analytics tables and columns from saved widgets. Every project contains a default configuration that restricts a few sensitive sources. You can remove a default restriction or add your own. After updating the restrictions, save the policy. Block a table
  1. Choose a table from the Select a table menu.
  2. Select Block table.
Blocked tables appear as removable tags. Select the delete icon on a tag to lift the restriction. The default blocked tables are:
  • abl_platform.audit_events
  • abl_platform.eval_conversations
  • abl_platform.eval_scores
  • abl_platform.search_queries
  • abl_platform.spatial_trace_records
  • abl_platform.custom_pipeline_results
  • abl_platform.workflow_events
Block a column
  1. Choose a scope from the table menu. Select All tables to block the column everywhere it appears, or select a specific table to block it there only.
  2. Choose a column from the Select a column menu.
  3. Select Block column.
Blocked columns appear as removable tags, grouped by name of the table. The following columns are blocked by default across all tables:
  • attributes
  • content
  • conversation_json
  • evidence
  • metadata
  • output
  • payload
  • prompt
  • query_text
  • trace_events
The following columns are also blocked by default in specific tables:

Attachments

The Attachment Settings page controls how files uploaded during chat sessions are accepted and processed for this project. Navigation: Project → Settings → Attachments General Default Allowed File Types The following MIME types are allowed by default:
  • Images: image/jpeg, image/png, image/gif, image/webp
  • Documents: application/pdf, application/msword, application/vnd.openxmlformats-officedocument.wordprocessingml.document, application/rtf
  • Spreadsheets: application/vnd.ms-excel, application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
  • Presentations: application/vnd.ms-powerpoint, application/vnd.openxmlformats-officedocument.presentationml.presentation
  • OpenDocument formats: application/vnd.oasis.opendocument.text, application/vnd.oasis.opendocument.spreadsheet, application/vnd.oasis.opendocument.presentation
  • Text formats: text/plain, text/markdown, text/csv, text/tab-separated-values, text/html, application/xml, application/json
  • Audio: audio/mpeg, audio/wav, audio/webm
  • Video: video/mp4, video/webm

Limits

Processing

Mode When Read Attachment is selected, the platform processes uploaded files according to the following settings:
  • Images: When Image Processing is enabled, images are sent directly to the model as Base64. The model analyzes the image; the platform does not extract its content. When Image Processing is disabled, images are not sent to the model, and only their details are shared.
  • Documents, audio, and video: When Document Processing is enabled, the platform extracts the content and sends the extracted text to the model instead of the raw file. For audio and video files, transcripts are shared. When Document Processing is disabled, documents are not processed and only their details are shared.
File metadata remains available through the attachment tools in this mode. Use this mode when the agent needs to read, search, and reason about uploaded content. Read Attachment configuration PII Handling Select how the platform handles personally identifiable information (PII) detected in text extracted from uploaded files.
PII redaction and blocking apply only to text extracted by the platform. Files sent directly to the AI model are not checked for PII. PII policies are not applied in Skip or Metadata Only modes.
Points to Note
  • Images in Read Attachment mode are sent directly to the model when Image Processing is enabled. Therefore, the selected model must support vision.
  • Documents processed using Platform Extraction are converted into text before being sent to the model, allowing text-capable models to process them.
  • When Send to the AI Model is selected, documents are sent directly to the model, provided the model supports the file type.
  • Metadata Only and Skip modes do not extract file contents. As a result, PII policies are not applied in these modes.
  • In Skip mode, direct file transfer is currently supported only for images and PDF files.

Omnichannel

The Omnichannel page configures cross-channel session continuity. Navigation: Project → Settings → Omnichannel Omnichannel settings allow users who start a conversation on one channel to continue it on another without losing context. Conversation Recall Allowed channels Lists all supported channels (web, voice, sms, whatsapp, email, slack, teams) with toggles for cross-channel recall participation. Identity Requirements Consent Live Transcript Sync Configure real-time transcript synchronization settings for cross-channel sessions. Recent Continuity Activity Shows operational events generated by cross-channel recall and live session continuity — for example, a session transferring channels or a live sync joining. Select Refresh to reload the list. If no sessions have used continuity features yet, the panel shows an empty state. Select Save Settings to apply changes.
If you see a “Failed to save settings” error, verify that your role has write permissions for project settings.

Governance

The Governance page sets the production approval policy for this project. The policy controls how strictly the platform gates production deployments, so a stricter level requires more sign-off before an agent version can ship. Navigation: Project → Settings → Governance Production approval policy The page shows whether the policy is Inherited (default) or set explicitly for the project, along with the Effective level currently in force and its source (for example, Standard from the platform default). To set an explicit policy, drag the Approval strictness slider to a level, then select Save policy. When you select a level, the page shows that level’s sign-off requirements below the slider. Saving an explicit policy overrides the inherited platform default.