Braze Agents

Braze Agents are AI-powered helpers you can create inside Braze. Agents can generate content, make intelligent decisions, and enrich your data so you can deliver more personalized customer experiences.

Why use Braze Agents?

Braze Agents help your team deliver smarter, more personalized experiences—without adding extra work. They act as intelligent assistants that don’t just respond to prompts, but understand context, make decisions, and take action toward a goal.

In practice, agents can automatically create message copy—like subject lines or in-product text—so every customer gets communication that feels tailored to them. They can also adapt in real time, routing people through different Canvas paths based on preferences, behaviors, or other data.

Beyond messaging, agents can enrich your catalogs by calculating or generating product and profile field values, keeping your data fresh and dynamic. By taking on repetitive or complex tasks, they free your team to focus on strategy and creativity instead of manual setup. Braze Agents act more like collaborators than background processes—helping you solve problems and deliver impact at scale.

Features

Features for Braze Agents include:

• Flexible setup: Use a Braze-provided LLM or connect your own model provider (such as OpenAI, Anthropic, Google Gemini, or AWS Bedrock).
• Seamless integration: Deploy agents directly in Canvas steps or catalog fields.
• Testing and logging tools: Preview your agent’s output by testing with sample inputs before you launch. View logs for each time the agent runs, including the input and output for that run.
• Usage controls: Built-in invocation and size limits help manage performance and costs.

About Braze Agents

Agents are configured with instructions (system prompts) that define how they behave. When an agent runs, it uses your instructions along with any data you pass in to generate a response.

Key concepts

Term	Definition
Model	The agent’s “brain,” in this case a large language model (LLM). It interprets inputs, generates responses, and performs reasoning. A stronger model (trained on more relevant data) makes the agent more capable and versatile.
Instructions	The rules or guidelines you give the agent (system prompt). They define how the agent should behave each time it runs. Clear instructions make the agent more reliable and predictable.
Context	Data passed into the agent at runtime wherever it is deployed, such as user profile fields or catalog rows. This input provides the information the agent uses to generate outputs.
Output variable	The output the agent produces when used in Canvas steps. Output variables store the agent’s result to personalize content or guide workflow paths. Output variables can be a string, number, or boolean data type.
Invocation	A single run of the agent. This counts against your daily and total limits.

Limitations

Agents process requests at roughly 1,000 invocations per minute. Each workspace can support up to 1,000 agents. If this limit is reached, you’ll need to remove an existing agent before creating a new one.

Additionally, during the beta period:

• Invocation is limited to 50,000 runs per day and 500,000 runs in total.
• Each run must complete within 30 seconds. After 30 seconds, the agent will return a null response where it is used.
• Input data is limited to 10 KB per request. Longer inputs are truncated.
• For catalogs, agentic fields update only the first 10,000 rows.

Next steps

Now that you know about Braze Agents, you’re ready for the next steps:

• Creating custom agents
• Deploying custom agents