History - Entity Enricher Documentation

History

Browse, filter, and analyze all enrichment results. View detailed outputs with integrated schema navigation, grouping options, and batch operations.

Overview

The History page is the central place to review every enrichment, schema generation, playground execution, and fusion result. Records are stored in PostgreSQL and scoped to your organization. The page uses a virtualized table for smooth scrolling even with thousands of records.

Record Types
9
Grouping Modes
4
Detail Tabs
10
Bulk Actions
Multi-select

Record Types

Every LLM operation creates a record. The type filter lets you focus on specific kinds of results:

TypeSourceDescription
enrichmentWorkflow Editor / BatchEntity enrichment results with structured output matching the target schema
arbitrationFusionThe merged output of a multi-model run. It has no model of its own, so the Model column names the models it merged, and the Type column says how the conflicts were settled — by deterministic rules (no LLM call, no tokens, no cost) or by an arbiter model. The Overview tab carries the full audit trail: field tally, source records, and every decision with the rule that made it.
schema_generationWorkflow EditorAI-generated JSON schemas from sample data
schema_editWorkflow EditorAI-assisted schema modifications via natural language prompts
sample_generationWorkflow EditorGenerated sample JSON — the starting contract a schema is built from. One record covers the whole job, however many samples it produced.
playgroundPlaygroundFree-form prompt executions with raw responses
classificationWorkflow Editor / BatchThe pre-flight check asking whether the entity matches the schema's type. Cheap, non-blocking, and kept so you can see why an enrichment was warned about.
ambiguity_analysisWorkflow EditorThe ambiguity and identity-scoping review of a schema's properties — which names admit more than one reading, and which related items mix entity facts with pairing facts. Its findings become the advisory annotations shown in the editor.
db_classificationDatabase SyncThe link-time pass proposing each property's database key, SQL type, index and ownership. Curated in the Database Sync page's Model tab.

Combine multiple filters to narrow down results. All filters update the table in real time:

Provider filterFilter by AI provider (Anthropic, OpenAI, Google, etc.).
Success statusShow only successful, failed, or all records.
Record typeFilter by any of the nine record types — enrichment, fusion, schema generation, schema edit, sample generation, playground, classification, ambiguity analysis, or DB classification.
Text searchSearch across entity data and structured output content.
Sort optionsSort by date (newest/oldest), cost, or token usage.
Active models onlyHide records from models that have been deactivated.
CapabilitiesNarrow to runs that used web search, prompt caching, reasoning, structured output, or a specific input modality (vision, PDF, audio, video).
OriginWhere the run came from — the web app, n8n, Make, or the API.

System admins have additional filters: All organizations to view records across the entire platform, and Include deleted to see soft-deleted records.

Grouping

Group records visually to spot patterns and organize results:

None

Flat list sorted by the selected sort option. Default view.

By Type

Group records by type (enrichment, schema generation, etc.) with collapsible sections.

By Provider

Group by AI provider to compare results across different services.

By Date

Group by creation date to see daily activity patterns.

Selection & Bulk Operations

Select multiple records for batch operations using familiar keyboard shortcuts:

ShortcutAction
ClickSelect a single record and open its details
Ctrl + ClickToggle selection of a record without deselecting others
Shift + ClickSelect a range of records between the last click and current
Ctrl + ASelect all visible records
Ctrl + DDeselect all records

With records selected, use Batch Delete to soft-delete them. System admins can perform hard deletes for permanent removal and restore soft-deleted records.

Record Detail Panel

Clicking a record opens the detail panel. Tabs appear only when the record has something to show there, so a rule-based fusion has no prompt tab and an enrichment without files has no attachments tab. The URL updates to enable deep linking (e.g., /history/uuid?tab=prompt).

Output

The structured JSON output in a read-only Monaco editor with syntax highlighting. For enrichment records, this is the final merged result matching the schema.

Prompt

View the system prompt, user prompt, and raw response for each expertise domain. Multi-expertise records show a dropdown to switch between expertise prompts.

Overview

Token usage (input, output, cached), wall-clock duration, cost breakdown, retries and validation errors. For a fusion record this is also the audit trail: the field tally, the source records, and every decision with the rule that made it.

Database Sync

For enrichment and fusion records: which deltas this record produced and where they stand, plus a Send to database action that re-injects the stored output into the schema's database sync.

What the model actually saw

Four more tabs open up the exact request: System Prompt, Raw Response, Wire Schema (the structured-output contract sent to the provider) and Function Tools. Plus Schema and Attachments for the inputs.

Deep Linking & Navigation

Records integrate with other parts of the application:

URL-synced detailEach record has a direct URL (/history/:id) that can be shared or bookmarked.
Schema navigationEnrichment records link to their source schema in the Workflow Editor for quick reference.
Search key formDynamic form built from the schema's key properties, allowing you to search for specific entities.
Reload in PlaygroundReplay any record's prompts — and its attachments — in the Playground, to iterate on wording without re-running the pipeline.
Send to databaseFor enrichment and fusion records, inject the stored output into the schema's database sync — useful after fixing a replica or adding a database to a schema that already has results.

Next Steps