← All agents

AI & research · One purpose, multiple implementations

Noco Kanban Board with AI Prioritization

Adapt the published “Noco Kanban Board with AI Prioritization” workflow to other implementations while preserving its documented behavior.

The source contains 22 executable nodes and 21 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["Incident Form"]
  n1["Assign Category"]
  n2["OpenAI Chat Model1"]
  n3["Structure Output Todoist Ready1"]
  n4["Get incident definitions"]
  n5["Insert Incident"]
  n6["Aggregate for AI parsing"]
  n7["On schedule or during flow"]
  n8["When clicking #8216;Test workflow#8217;"]
  n9["Task is not picked up after expected response"]
  n10["Send email to client"]
  n11["Check status every day"]
  n12["Send email to asignee"]
  n13["Get Unpicked Tasks"]
  n14["Get Unfinished Tasks"]
  n15["Task is not complete in expected time"]
  n16["Send email to client1"]
  n17["If there is asignee email"]
  n18["If there is assignee slack"]
  n19["Slack to assignee"]
  n20["Send another email to asignee"]
  n21["Format for Noco"]
  n0 -->|"main out 0 to in 0"| n4
  n1 -->|"main out 0 to in 0"| n21
  n21 -->|"main out 0 to in 0"| n5
  n5 -->|"main out 0 to in 0"| n7
  n13 -->|"main out 0 to in 0"| n9
  n2 -->|"ai_languageModel out 0 to in 0"| n1
  n14 -->|"main out 0 to in 0"| n15
  n11 -->|"main out 0 to in 0"| n7
  n6 -->|"main out 0 to in 0"| n1
  n4 -->|"main out 0 to in 0"| n6
  n17 -->|"main out 0 to in 0"| n12
  n18 -->|"main out 0 to in 0"| n19
  n18 -->|"main out 1 to in 0"| n20
  n7 -->|"main out 0 to in 0"| n13
  n7 -->|"main out 0 to in 0"| n14
  n3 -->|"ai_outputParser out 0 to in 0"| n1
  n8 -->|"main out 0 to in 0"| n7
  n15 -->|"main out 0 to in 0"| n16
  n15 -->|"main out 1 to in 0"| n18
  n9 -->|"main out 0 to in 0"| n10
  n9 -->|"main out 0 to in 0"| n17
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.