POST https://api.zatomic.ai/v1/prompts/heatmap
Zatomic API
- Introduction
- Versioning
- Authentication
- Workspaces
- Status codes and errors
- Token usage
- Expanding objects
- OpenAPI spec
- Prompts
- The Prompt object
- Creating a prompt
- Updating a prompt
- Deleting a prompt
- Retrieving a prompt
- Retrieving all prompts
- Generating a prompt
- Versions
- The Version object
- Creating a version
- Updating a version
- Deleting a version
- Retrieving a version
- Retrieving all versions
- Retrieving a version score
- Calculating a version score
- Retrieving a version risk
- Analyzing a version risk
- Retrieving a version balance
- Analyzing a version balance
- Retrieving a version heatmap
- Generating a version heatmap
- Improving a version
- Scoring Criteria
- The Scoring Criteria object
- The Scoring Criterion object
- Creating scoring criteria
- Updating a scoring criteria
- Deleting a scoring criteria
- Retrieving a scoring criteria
- Retrieving all scoring criteria
- Generating scoring criteria
- Creating a scoring criterion
- Updating a scoring criterion
- Deleting a scoring criterion
- Retrieving a scoring criterion
- Scoring Criteria Results
- The Scoring Criteria Results object
- Scoring
- The Scoring object
- Calculating a prompt score
- Risk
- The Risk object
- Analyzing prompt risk
- Balance
- The Balance object
- Analyzing prompt balance
- Heatmaps
- The Heatmap object
- Generating a prompt heatmap
Heatmaps
Heatmaps allow you to visualize prompt phrases that the AI model gave most (or least) of its attention. Using prompt heatmaps through the API gives you the raw data for you to render heatmap visualizations in other ways.
Generating heatmap data can be performed and retrieved on individual prompt versions using their specific heatmap endpoints. You can also generate heatmap data for prompts without a version stored in the system by using the non-version specific endpoint.
When a prompt heatmap is generated, phrases are broken down into meaningful phrases and assigned a score based on how much attention the AI model gave the phrase. Those attention scores are then assigned a corresponding color level.
| Attention Score | Color Level |
|---|---|
| 1 | very-light |
| 2 | light |
| 3 | medium |
| 4 | dark |
| 5 | very-dark |
Endpoints