Insights
Category: AI & ML
Node id: insights
AI-powered data analysis and insights generation with trend and anomaly detection
What it does
- Comprehensive data analysis with trend and anomaly detection
- Confidence-scored insights with severity classification
- Configurable analysis types (comprehensive, trends, anomalies, recommendations)
- Historical data and benchmark comparison
- Visualization suggestions for key insights
- Structured JSON output with evidence-based findings
Use cases
- Analyzing patient population health trends
- Detecting anomalies in clinical or operational data
- Generating actionable recommendations from healthcare metrics
- Comparing performance against industry benchmarks
- Executive reporting with data-driven insights
Runtime
- Performance tier:
variable
Input ports
| Name | Type | Required | Description |
|---|---|---|---|
data | any | Yes | Data to analyze (string or structured) |
context | any | No | Additional context about the data |
objectives | any | No | Specific analysis objectives |
metrics | any | No | Key metrics to focus on |
historical_data | any | No | Historical data for comparison |
benchmark | any | No | Benchmark data for comparison |
constraints | any | No | Analysis constraints or limitations |
Output ports
| Name | Type | Required | Description |
|---|---|---|---|
result | json | No | Main result containing insights, summary, recommendations, and visualizations |
metadata | json | No | Execution metadata including tokens, insight_count, and severity counts |
success | boolean | No | Whether the operation succeeded |
Settings
Basic
| Setting | Name | Type | Required | Default | Allowed values | Description |
|---|---|---|---|---|---|---|
| Provider | provider | enum | No | openai | openai, anthropic | LLM provider |
| Model | model | string | No | "" | Model name (auto-selected if empty) | |
| Analysis Type | analysis_type | enum | No | comprehensive | comprehensive, trends, anomalies, recommendations | Type of analysis to perform |
| Timeframe | timeframe | string | No | "" | Timeframe for analysis | |
| Compare With | compare_with | string | No | "" | Comparison method (baseline, previous_period, industry_average) | |
| Include Visualization | include_visualization | boolean | No | false | Suggest visualizations for insights |
Auth
| Setting | Name | Type | Required | Default | Allowed values | Description |
|---|---|---|---|---|---|---|
| API Key | api_key | secret | No | API key for the LLM provider | ||
| Base URL | base_url | string | No | "" | Custom API base URL |
Advanced
| Setting | Name | Type | Required | Default | Allowed values | Description |
|---|---|---|---|---|---|---|
| Temperature | temperature | number | No | 0.3 | min 0; max 1 | Sampling temperature |
| Max Tokens | max_tokens | number | No | 4000 | min 1 | Maximum tokens for response |
Errors
| Code | Description |
|---|---|
DATA_REQUIRED | No data input was provided for analysis |
LLM_REQUEST_FAILED | LLM API call failed during analysis |
UNSUPPORTED_PROVIDER | Provider must be openai or anthropic |
Runtime notes
- Each insight includes a confidence score (0-1); filter on confidence >= 0.8 for high-confidence results
- LLM response is parsed as JSON — if parsing fails, a single fallback insight wraps the raw text
- metadata.tokens tracks LLM token usage for cost monitoring
- visualizations array is only populated when include_visualization config is true
See Build any workflow for how to put nodes together and Ports, types and data flow for how port types connect.
Quelque chose n'est pas clair ? Envoyez vos commentaires sur la documentation par courriel.