Skip to Workflow Atlas
Event-Driven AutomationAI systemIntermediate

WhatsApp AI Sales Assistant

WhatsApp AI Sales Assistant is a 18-node automation blueprint connecting OpenAI, WhatsApp API. Inspect its trigger, execution graph, branches, and implementation requirements.

Interactive system map

Follow the runtime. Inspect what supports it.

Solid horizontal paths show main-channel execution. Violet dependencies sit beneath the exact step they configure or empower.

18

Nodes

16

Links

2

Run groups

Connected tools

2 integrations

  • OpenAI
  • WhatsApp API

Canvas controls

Fit wide systems, then zoom into any run group.

WhatsApp AI Sales Assistant execution lanes2 run groups containing 18 workflow nodes and 16 visible links. Solid horizontal lines are main-channel runtime links. Violet dashed lines connect typed dependencies beneath the runtime step they support. Focus any node to inspect its immediate path.WhatsApp Trigger. trigger node, whatsAppTrigger. 0 incoming and 1 outgoing connections.STARTWhatsApp TriggerTRIGGERWHATSAPPTRIGGER0 IN / 1 OUTHandle Message Types. decision node, switch. 1 incoming and 2 outgoing connections.STEP 02Handle Message TypesDECISIONSWITCH1 IN / 2 OUTAI Sales Agent. ai node, agent. 4 incoming and 1 outgoing connections.STEP 03AI Sales AgentAIAGENT4 IN / 1 OUTReply To User1. integration node, whatsApp. 1 incoming and 0 outgoing connections.STEP 03Reply To User1INTEGRATIONWHATSAPP1 IN / 0 OUTReply To User. integration node, whatsApp. 1 incoming and 0 outgoing connections.OUTCOMEReply To UserINTEGRATIONWHATSAPP1 IN / 0 OUTOpenAI Chat Model. OpenAI node, lmChatOpenAi. 0 incoming and 1 outgoing connections.DEPENDENCY · DEPTH 1OpenAI Chat ModelOPENAILMCHATOPENAI0 IN / 1 OUTWindow Buffer Memory. ai node, memoryBufferWindow. 0 incoming and 1 outgoing connections.DEPENDENCY · DEPTH 1Window Buffer MemoryAIMEMORYBUFFERWINDOW0 IN / 1 OUTVector Store Tool. ai node, toolVectorStore. 2 incoming and 1 outgoing connections.DEPENDENCY · DEPTH 1Vector Store ToolAITOOLVECTORSTORE2 IN / 1 OUTProduct Catalogue. ai node, vectorStoreInMemory. 1 incoming and 1 outgoing connections.DEPENDENCY · DEPTH 2Product CatalogueAIVECTORSTOREINMEMORY1 IN / 1 OUTOpenAI Chat Model1. OpenAI node, lmChatOpenAi. 0 incoming and 1 outgoing connections.DEPENDENCY · DEPTH 2OpenAI Chat Model1OPENAILMCHATOPENAI0 IN / 1 OUTEmbeddings OpenAI. OpenAI node, embeddingsOpenAi. 0 incoming and 1 outgoing connections.DEPENDENCY · DEPTH 3Embeddings OpenAIOPENAIEMBEDDINGSOPENAI0 IN / 1 OUTWhen clicking ‘Test workflow’. trigger node, manualTrigger. 0 incoming and 1 outgoing connections.STARTWhen clicking ‘Test workf…TRIGGERMANUALTRIGGER0 IN / 1 OUTget Product Brochure. integration node, httpRequest. 1 incoming and 1 outgoing connections.STEP 02get Product BrochureINTEGRATIONHTTPREQUEST1 IN / 1 OUTExtract from File. integration node, extractFromFile. 1 incoming and 1 outgoing connections.STEP 03Extract from FileINTEGRATIONEXTRACTFROMFILE1 IN / 1 OUTCreate Product Catalogue. ai node, vectorStoreInMemory. 3 incoming and 0 outgoing connections.OUTCOMECreate Product CatalogueAIVECTORSTOREINMEMORY3 IN / 0 OUTEmbeddings OpenAI1. OpenAI node, embeddingsOpenAi. 0 incoming and 1 outgoing connections.DEPENDENCY · DEPTH 1Embeddings OpenAI1OPENAIEMBEDDINGSOPENAI0 IN / 1 OUTDefault Data Loader. ai node, documentDefaultDataLoader. 1 incoming and 1 outgoing connections.DEPENDENCY · DEPTH 1Default Data LoaderAIDOCUMENTDEFAULTDATALOAD1 IN / 1 OUTRecursive Character Text Splitter. ai node, textSplitterRecursiveCharacterTextSplitter. 0 incoming and 1 outgoing connections.DEPENDENCY · DEPTH 2Recursive Character Text …AITEXTSPLITTERRECURSIVECH0 IN / 1 OUT

Signal inspector

Focus, hover, or select a step to isolate its runtime and support links.

Main-channel runtimeTyped dependencytriggeraidecisiontransformintegration
Scroll horizontally to follow every connected flow.18 connected nodesEnter or click to lock · Escape to clear

Runtime breakdown

Read the execution spine before its dependencies.

Each run group separates main-channel steps from the models, tools, retrievers, and data services that support them. Start and outcome labels apply only to runtime nodes.

01

Run Group

WhatsApp Trigger

4 Execution Links6 Support Dependencies
  1. Start

    WhatsApp Trigger

    Trigger

  2. Step 2

    Handle Message Types

    Decision

  3. Step 3

    AI Sales Agent

    AI reasoning

    Reply To User1

    Integration

  4. Outcome

    Reply To User

    Integration

Attached dependencies

These nodes support the runtime above; they are not additional starts or outcomes.

6 nodes
  • OpenAI Chat Model

    AI reasoning dependency

  • Window Buffer Memory

    AI reasoning dependency

  • Vector Store Tool

    AI reasoning dependency

  • Product Catalogue

    AI reasoning dependency

  • OpenAI Chat Model1

    AI reasoning dependency

  • Embeddings OpenAI

    AI reasoning dependency

02

Run Group

When clicking ‘Test workflow’

3 Execution Links3 Support Dependencies
  1. Start

    When clicking ‘Test workflow’

    Trigger

  2. Step 2

    get Product Brochure

    Integration

  3. Step 3

    Extract from File

    Integration

  4. Outcome

    Create Product Catalogue

    AI reasoning

Attached dependencies

These nodes support the runtime above; they are not additional starts or outcomes.

3 nodes
  • Embeddings OpenAI1

    AI reasoning dependency

  • Default Data Loader

    AI reasoning dependency

  • Recursive Character Text Splitter

    AI reasoning dependency

Turn the map into a plan

Adapt this blueprint to your company.

Bring the system shape into a workspace, then define the production controls, data boundaries, owners, and delivery sequence around your context.