AI & research · One purpose, multiple implementations
Ask AI what are the information you are looking for about the company
Adapt the published “Ask AI what are the information you are looking for about the company” workflow to other implementations while preserving its documented behavior.
The source contains 14 executable nodes and 14 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["When clicking #34;Test workflow#34;"] n1["Input"] n2["OpenAI Chat Model"] n3["Get website content"] n4["SerpAPI - Search Google"] n5["Structured Output Parser"] n6["Loop Over Items"] n7["AI Researcher Output Data"] n8["Google Sheets - Update Row with data"] n9["Merge data"] n10["Get rows to enrich"] n11["Schedule Trigger"] n12["AI company researcher"] n13["Search Google with ScrapingBee"] n1 -->|"main out 0 to in 0"| n6 n9 -->|"main out 0 to in 0"| n8 n6 -->|"main out 1 to in 0"| n12 n6 -->|"main out 1 to in 0"| n9 n11 -->|"main out 0 to in 0"| n10 n2 -->|"ai_languageModel out 0 to in 0"| n12 n10 -->|"main out 0 to in 0"| n1 n3 -->|"ai_tool out 0 to in 0"| n12 n12 -->|"main out 0 to in 0"| n7 n4 -->|"ai_tool out 0 to in 0"| n12 n5 -->|"ai_outputParser out 0 to in 0"| n12 n7 -->|"main out 0 to in 1"| n9 n0 -->|"main out 0 to in 0"| n10 n8 -->|"main out 0 to in 0"| n6
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.