ai_context - Topics

Free text that can provide context to the Omni Agent. Refer to the Optimizing models for AI guide for more information on best practices.

Syntax

ai_context: "<context_text>"

Or for multiline context:

ai_context: |
  <multiline_context_text>

Properties

string

Free text that provides context to the Omni Agent. Can include behavioral prompting, instructions for tone, or other guidance to .The following references are supported for this field:

User attributes, referenced with {{omni_attributes.<attribute_name>}}. This allows you to personalize the context for each user.
Model constants, referenced using @{constant_name} syntax. This allows you to maintain reusable instruction blocks such as tone, privacy guidance, and domain context instead of duplicating them.
omni_llm namespace, which allows you to tailor context to specific AI model tiers:
- {{ omni_llm.model }} — Substitutes the active model’s family name, which will be one of: smartest, standard, or fastest
- {{# omni_llm.<family> }}...{{/ omni_llm.<family> }} — Conditional sections for specific model tiers. <family> must be one of smartest, standard, or fastest
- {{^ omni_llm.<family> }}...{{/ omni_llm.<family> }} — Inverse sections, which apply when the specified tier is not used. <family> must be one of smartest, standard, or fastest
See the Examples section for more information.
omni_agent namespace, which allows you to scope context to specific AI agents:
- {{ omni_agent.name }} — Substitutes the active agent’s name, which will be one of: analyze, build, or simple_summarize
- {{# omni_agent.<agent> }}...{{/ omni_agent.<agent> }} — Conditional sections for specific agents. <agent> must be one of analyze, build, or simple_summarize
- {{^ omni_agent.<agent> }}...{{/ omni_agent.<agent> }} — Inverse sections, which apply when the specified agent is not used. <agent> must be one of analyze, build, or simple_summarize
See the Examples section for more information.

Examples

Personalized context using user attributes

ai_context: |
  You are a sales analyst. When someone asks about their team or pipeline, always filter by account.segment = {{omni_attributes.segment}} and account.region = {{omni_attributes.region}}.

Model-specific analysis depth

The following context will apply when the model tier is smartest.

Applies when the model tier is smartest

ai_context: |
  This topic focuses on financial transactions.

  {{# omni_llm.smartest }}
  For complex multi-table queries, consider indirect relationships and provide rationale for join path selection.
  {{/ omni_llm.smartest }}

The following context will apply when the model tier is not smartest.

Applies when the model tier is not smartest

ai_context: |
  This topic focuses on financial transactions.

  {{^ omni_llm.smartest }}
  Use straightforward joins between directly related tables.
  {{/ omni_llm.smartest }}

Agent-specific context

The following context provides query optimization tips to the analyze agent while providing field relationship guidance to the build agent.

Agent-specific optimization and field guidance

ai_context: |
  This topic contains e-commerce order data.

  {{# omni_agent.analyze }}
  For optimal query performance, always filter by order_date before joining to customer details. The orders table is very large.
  {{/ omni_agent.analyze }}

  {{# omni_agent.build }}
  When generating field relationships, note that order_id is the primary key. The customer_id foreign key links to the customers table, and product_id links to products.
  {{/ omni_agent.build }}

Using constant references

Reference constants to combine reusable context blocks with topic-specific guidance:

Topic file with constant references

ai_context: |
  @{tone} @{domain_finance}
  This topic covers customer invoices. One row is an invoice.
  Focus on payment status and overdue amounts.

The @{tone} and @{domain_finance} references will be substituted with the constant values defined in the model file.

Behavioral prompting

ai_context: |
  you are the head of finance. you are concerned with the status of customer payments. you often need to project into the future how many invoices are due and for how much. you also need to know if any invoices are late so you can reach out to those customers.

Getting started

Manage content

Analyze & build

Visualize & present

Deliver content

Model data

Manage integrations

ai_context - Topics

Syntax

Properties

Examples

Personalized context using user attributes

Model-specific analysis depth

Agent-specific context

Using constant references

Behavioral prompting

​Syntax

​Properties

​Examples

​Personalized context using user attributes

​Model-specific analysis depth

​Agent-specific context

​Using constant references

​Behavioral prompting

Syntax

Properties

Examples

Personalized context using user attributes

Model-specific analysis depth

Agent-specific context

Using constant references

Behavioral prompting