Coding Agents: Model Harnesses and Cortex Code

Two coding agents can use the same model and still produce very different results. The difference is often the harness around the model: the context it receives, the tools it can call, and the instructions that guide its work.

This session is for Snowflake developers, data engineers, and architects who want to understand what Cortex Code sends to the model and why that matters.

In this Hands-on Lab, attendees will:
 

• Inspect the prompt, system instructions, tool definitions, skill catalog, and selected context included in the first Cortex Code model call.
• Examine how retrieval accuracy changes as context grows.
• Compare real Cortex Code and general coding-agent tool calls from the same Snowflake dbt task.
• Trace a reported successful file write that persisted malformed content before the agent repaired it.

Attendees will leave with a practical framework for evaluating coding agents beyond the model name alone. They will understand:
 

• How context selection, tool contracts, and validation affect execution.
• How Cortex Code's Snowflake-specific harness changes the path from a user request to completed work.