← All agents

AI & research · One purpose, multiple implementations

Personal Portfolio Resume CV Chatbot

Adapt the published “Personal Portfolio Resume CV Chatbot” workflow to other implementations while preserving its documented behavior.

The source contains 24 executable nodes and 20 connections. This draft is derived from the n8n export; it needs a human-reviewed purpose, input/output contract, and behavioral tests before a port can claim equivalence.

Open agent files on GitHub ↗

Shared workflow

This initial Mermaid diagram shows observed connections from the n8n source, including model and tool dependencies. Unresolved connections are listed under Evidence. It is a starting point for the shared design; it does not execute the agent or establish correctness.

Rendering the workflow diagram…

Read the Mermaid source
flowchart LR
  n0["Embeddings Google Gemini"]
  n1["Schedule Trigger"]
  n2["Google Gemini Chat Model"]
  n3["Google Drive - Resume CV File Created"]
  n4["Google Drive - Resume CV File Updated"]
  n5["Download CV File From Google Drive"]
  n6["Pinecone - Vector Store forr CV Content"]
  n7["CV File Data Loader"]
  n8["CV content - Recursive Character Text Splitter"]
  n9["Chat API - webhook"]
  n10["Personal CV AI Agent Assistant"]
  n11["Chat API Response - Webhook"]
  n12["Chat Memory - Window Buffer"]
  n13["Resume lookup : Vector Store Tool"]
  n14["Resume Vector Store #40;Retrieval#41;"]
  n15["Resume Embeddings Google Gemini #40;retrieval#41;"]
  n16["Resume Google Gemini Chat Model #40;retrieval#41;"]
  n17["Save Conversation API - Webhook"]
  n18["Save Conversation - NocoDB"]
  n19["Save Conversation API Webhook - Response"]
  n20["NocoDB - get all todays conversation"]
  n21["Group Conversation By Unique Session #43; Email - Code"]
  n22["Format HTML Display For email"]
  n23["Send Report To Gmail"]
  n1 -->|"main out 0 to in 0"| n20
  n9 -->|"main out 0 to in 0"| n10
  n7 -->|"ai_document out 0 to in 0"| n6
  n0 -->|"ai_embedding out 0 to in 0"| n6
  n2 -->|"ai_languageModel out 0 to in 0"| n10
  n18 -->|"main out 0 to in 0"| n19
  n12 -->|"ai_memory out 0 to in 0"| n10
  n22 -->|"main out 0 to in 0"| n23
  n10 -->|"main out 0 to in 0"| n11
  n14 -->|"ai_vectorStore out 0 to in 0"| n13
  n17 -->|"main out 0 to in 0"| n18
  n13 -->|"ai_tool out 0 to in 0"| n10
  n5 -->|"main out 0 to in 0"| n6
  n20 -->|"main out 0 to in 0"| n21
  n3 -->|"main out 0 to in 0"| n5
  n4 -->|"main out 0 to in 0"| n5
  n15 -->|"ai_embedding out 0 to in 0"| n14
  n16 -->|"ai_languageModel out 0 to in 0"| n13
  n8 -->|"ai_textSplitter out 0 to in 0"| n7
  n21 -->|"main out 0 to in 0"| n22
Read the specification and unresolved requirements ↗

Implementations

Each implementation shares the agent’s purpose. Available source, planned ports, and verified results are labeled separately.

Plain Python

Planned · no code yet

Read the implementation plan ↗

Pydantic AI

Planned · no code yet

Read the implementation plan ↗

CrewAI Flow

Planned · no code yet

Read the implementation plan ↗

CrewAI Crew

Planned · no code yet

Read the implementation plan ↗

LangGraph

Planned · no code yet

Read the implementation plan ↗

Build or operate with an assistant

Each prompt includes separate build and operating instructions tailored to this agent. They are untested instructions, not working implementations. Check the chosen product’s actual capabilities before using it.

Evidence and remaining work

The bulk collection has publication checks, not live-service testing. Diagrams and prompts are documentation. A port needs reviewed schemas, fixtures, actual execution results, and explicit limits before claiming equivalent behavior.

  • Define input/output schemas and expected outputs.
  • Review source expressions, external actions, and failure behavior.
  • Determine whether model judgment is required or deterministic rules suffice.

Curated by Nik Bear Brown. Preserve each implementation’s original attribution and license. These source templates are separate from the audited Claude directory.