Define the task
Choose a repeatable action your users need and define what success looks like.
SOFTWARE & AGENTS
Put intelligence inside your product.
Build copilots and agent workflows around the model that fits each task.
THE WORKFLOW
Three steps from idea to agent.
Build the agent
Connect the right model, add context retrieval and tool use, then test end-to-end.
Iterate with users
Ship early, track where the agent succeeds or fails, and refine the workflow.
Models to explore.
Full catalog →Gimage
Nano Banana 2.1
Google
Nano Banana 2.1 API for image creation and editing. Explore features, use cases, comparisons, and Runbridge.ai integration guidance. Check limits.
View model family↗
Ximage
Grok-Imagine-Image-2.0
xAI
Grok Imagine Image 2.0, its upgraded AI image generation and editing model
View model family↗
A FEW THINGS TO KNOW
Frequently asked questions
How do we choose a model?+
Start with a baseline model that handles your task. Test on real inputs, then upgrade or switch based on quality, latency and cost.
What about tool use?+
Tool use lets agents search, fetch data and take actions. Define clear tool boundaries and handle edge cases where tools fail or return unexpected results.
Build smarter products.
Connect text, reasoning and code models through one API.