> ## Documentation Index
> Fetch the complete documentation index at: https://docs.flowx.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Agent typologies
> The recurring agent archetypes behind the FlowX.AI agent catalog, and the workflow nodes you combine to build each one.
The [FlowX.AI agent catalog](https://www.flowx.ai/ai-agents) publishes pre-designed AI agents for banking, insurance, and logistics. Behind the industry-specific names, every agent in the catalog is a variation of a small set of recurring **typologies** - reusable pipeline shapes you can build yourself with integration workflow and Agent Builder nodes.
This page describes each typology and how to implement it with the documented node palette.
The node decompositions shown in the catalog are illustrative. The implementations below use the nodes as they exist in the platform - see [AI node types](../agent-builder/node-types) for the full palette.
## The typologies at a glance
| Typology | What it does | Built with |
| --------------------------------------------------------------------- | ---------------------------------------------------------------- | -------------------------------------------------------------------- |
| [Document extractor and validator](#document-extractor-and-validator) | Extracts structured data from documents and gates on confidence | **Document Extraction** / **Extract Data from File** + **Condition** |
| [Grounded generator](#grounded-generator) | Drafts narratives, reports, and letters grounded in your content | **Context Retrieval** + **Custom Agent** |
| [Classifier and router](#classifier-and-router) | Classifies incoming text and routes it to the right handler | **Intent Classification** or **Text Understanding** + **Condition** |
| [Voice intake](#voice-intake) | Transcribes audio and extracts meaning from it | **Speech to Text** + **Text Understanding** |
| [Predictive scorer](#predictive-scorer) | Enriches data, scores it, and gates on a threshold | **REST Call** / **DB Operation** + **Condition** |
| [Privacy-guarded extractor](#privacy-guarded-extractor) | Document extraction with PII redaction in the pipeline | **Document Extraction** + **Personal Information Guard** |
| [Knowledge-validated extractor](#knowledge-validated-extractor) | Extraction checked against domain reference data | **Document Extraction** + **Context Retrieval** + **Custom Agent** |
| [Relationship reasoner](#relationship-reasoner) | Reasons over entities and their relationships | **Context Retrieval** + **Custom Agent** with response schema |
| [Human handoff](#human-handoff) | Escalates decisions above a threshold to a person | **Condition** + BPMN **User Task** |
***
## Document extractor and validator
The most common typology in the catalog: KYC pack validators, completeness checkers, cross-document consistency agents.
**When to use:** a document set arrives (identity documents, contracts, invoices, claims) and you need structured fields out of it, plus a decision on whether the result is good enough to proceed.
**How to build it:** a **Document Extraction** or **Extract Data from File** node extracts fields against a schema, then a **Condition** node gates on the extraction confidence - high-confidence results continue automatically, low-confidence results route to a review branch.
See [Fan-out extraction](./fan-out-extraction) for the multi-document-type variant, and [AI comparison and reconciliation](./ai-comparison-reconciliation) for cross-checking extracted data against a system of record.
## Grounded generator
The catalog's report writers: SAR drafts, case narratives, credit memos, customer letters.
**When to use:** the output is a document or narrative that must be grounded in verified content - policy texts, case data, templates - rather than generated freely.
**How to build it:** a **Context Retrieval** node pulls relevant chunks from a Knowledge Base, then a **Custom Agent** node generates the draft from those chunks. Constrain the output with a **Response Schema** so downstream nodes receive predictable structure, and turn on the **Personal Information Guard** where the input may contain PII.
See [Knowledge base RAG](./knowledge-base-rag) for the retrieval setup.
## Classifier and router
Complaint root-cause identifiers, alert triage screeners, exception handlers.
**When to use:** free-form input (a message, an alert, an email) must be understood and dispatched to the right specialized handler.
**How to build it:** an **Intent Classification** node classifies the input into up to 10 intents and routes each to its own branch in a single node - including a fallback branch when nothing matches. For classification against a custom label set with custom gating, use a **Text Understanding** node followed by a **Condition** node.
See [Intent classification and routing](./intent-classification-routing).
## Voice intake
Call transcribers, first-notice-of-loss agents, voice-driven notification generators.
**When to use:** the input is audio - customer calls, voice messages, dictated notes.
**How to build it:** a **Speech to Text** node transcribes the audio, then a **Text Understanding** node extracts the entities, topics, or sentiment you need from the transcript.
See [Speech to Text](../agent-builder/speech-to-text).
## Predictive scorer
Risk analyzers, churn predictors, KPI forecasters, failure-prediction agents.
**When to use:** a numeric or categorical prediction drives the decision - a score, a probability, a forecast - and you gate the flow on a threshold.
**How to build it:** FlowX orchestrates the pipeline around your scoring model rather than replacing it. Enrich the input with **REST Call** or **DB Operation** nodes, call your model (or a third-party scoring service) with a **REST Call** node, then gate with a **Condition** node on the returned score. Deterministic scoring logic can also run directly in a **Script** node.
See [Hybrid AI and business rules](./hybrid-ai-rules) for combining AI outputs with auditable deterministic logic.
## Privacy-guarded extractor
Identity and KYC extraction agents that must not leak personal data downstream.
**When to use:** documents contain PII and the extracted output crosses a trust boundary - external models, logs, or downstream systems that shouldn't see raw identifiers.
**How to build it:** the document-extractor pipeline above, with the **Personal Information Guard** enabled on the AI nodes' input and/or output to redact personal information.
See [Personal Information Guard](../personal-information-guard).
## Knowledge-validated extractor
Board-authority validators, contract-term checkers, coverage validators.
**When to use:** extracted data must be checked against domain reference content - policy rules, product terms, jurisdiction requirements - not just against a schema.
**How to build it:** extract with a **Document Extraction** node, retrieve the applicable reference content with a **Context Retrieval** node, then have a **Custom Agent** node compare the two and return a structured verdict with reasons via its **Response Schema**.
## Relationship reasoner
Ownership-structure mappers, treaty cross-referencers, entity-network agents.
**When to use:** the question is about how entities relate - who ultimately owns what, which contracts reference each other - rather than about a single document.
**How to build it:** there is no dedicated graph node; model the reference relationships in a Knowledge Base, retrieve the relevant slice with **Context Retrieval**, and let a **Custom Agent** node reason over it, returning the reconstructed structure through a **Response Schema**. For relationship data held in your own systems, enrich with **DB Operation** or **REST Call** nodes first.
## Human handoff
Escalation wrappers that route edge cases to a person.
**When to use:** any of the typologies above produces a low-confidence or high-stakes result that a human must approve.
**How to build it:** a **Condition** node detects the escalation case, and the surrounding BPMN process presents it to a person as a **User Task** - the agent workflow and the human step share the same process context.
See [Integrating agents in BPMN processes](../using-agents/bpmn-integration).
***
## Combining typologies
Catalog agents rarely ship alone - each lists companion agents, and the same is true when you build your own. Typical combinations:
| Scenario | Typology combination |
| --------------------- | ------------------------------------------------------------------------------- |
| Case investigation | Classifier and router → Document extractor → Grounded generator (the narrative) |
| Onboarding validation | Document extractor → Knowledge-validated extractor → Human handoff |
| Voice-driven claims | Voice intake → Document extractor → Predictive scorer |
***
## Related resources
The full AI node palette these typologies are built from
Implementation-level patterns with prompts and schemas
The full industry catalogs on flowx.ai
End-to-end builds that use these typologies