AI & research · One purpose, multiple implementations
ERP AI chatbot for Odoo sales module
Adapt the published “ERP AI chatbot for Odoo sales module” workflow to other implementations while preserving its documented behavior.
The source contains 15 executable nodes and 15 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["Window Buffer Memory"] n1["OpenAI Chat Model"] n2["Calculator"] n3["Schedule Trigger"] n4["Convert to File"] n5["Save Summary to File"] n6["Get All Opportunities from Odoo"] n7["Read Summary From File"] n8["If Summary Exists"] n9["Merge Opportunities"] n10["Extract Text From File"] n11["AI Conversational Agent"] n12["Summarize Opportunities"] n13["OpenAI Summarization Model"] n14["Chat Trigger"] n2 -->|"ai_tool out 0 to in 0"| n11 n14 -->|"main out 0 to in 0"| n7 n4 -->|"main out 0 to in 0"| n5 n3 -->|"main out 0 to in 0"| n6 n8 -->|"main out 0 to in 0"| n10 n8 -->|"main out 1 to in 0"| n6 n1 -->|"ai_languageModel out 0 to in 0"| n11 n9 -->|"main out 0 to in 0"| n12 n5 -->|"main out 0 to in 0"| n7 n0 -->|"ai_memory out 0 to in 0"| n11 n10 -->|"main out 0 to in 0"| n11 n7 -->|"main out 0 to in 0"| n8 n12 -->|"main out 0 to in 0"| n4 n13 -->|"ai_languageModel out 0 to in 0"| n12 n6 -->|"main out 0 to in 0"| n9
Implementations
Each implementation shares the agent’s purpose. Available source, planned ports, and verified results are labeled separately.
n8n
Source available · not runtime-tested
Read setup and source ↗Inspect the n8n canvas and download JSON →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.