← All agents

AI & research · One purpose, multiple implementations

HR Job Posting and Evaluation with AI

Adapt the published “HR Job Posting and Evaluation with AI” workflow to other implementations while preserving its documented behavior.

The source contains 30 executable nodes and 29 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["On form submission"]
  n1["Airtable"]
  n2["Upload CV to google drive"]
  n3["applicant details"]
  n4["download CV"]
  n5["Extract from File"]
  n6["AI Agent"]
  n7["OpenAI Chat Model"]
  n8["Airtable1"]
  n9["Structured Output Parser"]
  n10["shortlisted#63;"]
  n11["Rejected"]
  n12["Potential Hire"]
  n13["Airtable2"]
  n14["generate questionnaires"]
  n15["questionnaires"]
  n16["update questionnaires"]
  n17["job_posting"]
  n18["candidate_insights"]
  n19["Personalize email"]
  n20["Edit Fields"]
  n21["Send Email"]
  n22["Book Meeting"]
  n23["Google Calendar"]
  n24["update phone meeting time"]
  n25["Screening Questions"]
  n26["job_posting1"]
  n27["candidate_insights1"]
  n28["screening questions"]
  n29["Edit Fields1"]
  n6 -->|"main out 0 to in 0"| n10
  n1 -->|"main out 0 to in 0"| n4
  n8 -->|"ai_tool out 0 to in 0"| n6
  n13 -->|"ai_tool out 0 to in 0"| n14
  n21 -->|"main out 0 to in 0"| n22
  n20 -->|"main out 0 to in 0"| n21
  n4 -->|"main out 0 to in 0"| n5
  n17 -->|"ai_tool out 0 to in 0"| n19
  n22 -->|"main out 0 to in 0"| n24
  n29 -->|"main out 0 to in 0"| n28
  n26 -->|"ai_tool out 0 to in 0"| n25
  n10 -->|"main out 0 to in 0"| n12
  n10 -->|"main out 1 to in 0"| n11
  n12 -->|"main out 0 to in 0"| n14
  n15 -->|"main out 0 to in 0"| n16
  n23 -->|"ai_tool out 0 to in 0"| n22
  n5 -->|"main out 0 to in 0"| n6
  n7 -->|"ai_languageModel out 0 to in 0"| n6
  n19 -->|"main out 0 to in 0"| n20
  n3 -->|"main out 0 to in 0"| n1
  n0 -->|"main out 0 to in 0"| n2
  n18 -->|"ai_tool out 0 to in 0"| n19
  n25 -->|"main out 0 to in 0"| n29
  n27 -->|"ai_tool out 0 to in 0"| n25
  n16 -->|"main out 0 to in 0"| n19
  n14 -->|"main out 0 to in 0"| n15
  n9 -->|"ai_outputParser out 0 to in 0"| n6
  n2 -->|"main out 0 to in 0"| n3
  n24 -->|"main out 0 to in 0"| n25
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.