AI & research · One purpose, multiple implementations
Extract & Summarize Indeed Company Info with Bright Data and Google Gemini
Adapt the published “Extract & Summarize Indeed Company Info with Bright Data and Google Gemini” workflow to other implementations while preserving its documented behavior.
The source contains 13 executable nodes and 12 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 #8216;Test workflow#8217;"] n1["Google Gemini Chat Model For Summarization"] n2["Set Indeed Search Query"] n3["Perform Indeed Web Request"] n4["Indeed Expert AI Agent"] n5["Google Gemini Chat Model"] n6["Markdown to Textual Data Extractor"] n7["Indeed Summarization"] n8["Convert Markdown to HTML"] n9["Initiate a Webhook Notification for Markdown to HTML Response"] n10["Google Gemini Chat Model for AI Agent"] n11["Initiate a Webhook Request"] n12["Initiate a Webhook Notification for Summarization"] n7 -->|"main out 0 to in 0"| n4 n7 -->|"main out 0 to in 0"| n12 n2 -->|"main out 0 to in 0"| n3 n8 -->|"main out 0 to in 0"| n9 n5 -->|"ai_languageModel out 0 to in 0"| n6 n11 -->|"ai_tool out 0 to in 0"| n4 n3 -->|"main out 0 to in 0"| n6 n3 -->|"main out 0 to in 0"| n8 n0 -->|"main out 0 to in 0"| n2 n6 -->|"main out 0 to in 0"| n7 n10 -->|"ai_languageModel out 0 to in 0"| n4 n1 -->|"ai_languageModel out 0 to in 0"| n7
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.