BotShelf Vampire BOTSHELF VAMPIRE Register

EXPLORE · SAME JOB, BY TOOL

Support Triage: 15 versions, one per tool

The same job, written separately for AutoGen, Claude Code, CrewAI, Cursor, DeepSeek, Dify, Flowise, Gemini, LangGraph, LM Studio, MCP, n8n, Ollama, Open WebUI, OpenRouter. Each version is its own text; what you get is text to copy into that tool, not something BSV installs or runs for you. Pick the tool you already use and open its page: the full text is there, with Copy and a file to download. No sign-up.

ToolDescription on the item pageStatusRaw
AutoGenUse AutoGen to classify support issues by severity, missing data and route, optimized for bounded multi-agent collaboration.Untestedfile
Claude CodeUse Claude Code to classify support issues by severity, missing data and route, optimized for terminal-first repository work.Untestedfile
CrewAIClassify an inbound message, propose a first reply hold, and flag escalation — human sends. (CrewAI multi-agent Python sketch for one job.)Untestedfile
CursorUse Cursor to classify support issues by severity, missing data and route, optimized for repository-aware coding.Untestedfile
DeepSeekUse DeepSeek to classify support issues by severity, missing data and route, optimized for technical reasoning, coding and structured data.Untestedfile
DifyUse Dify to classify support issues by severity, missing data and route, optimized for node-based AI applications and automation.Untestedfile
FlowiseUse Flowise to classify support issues by severity, missing data and route, optimized for visual LLM and agent flows.Untestedfile
GeminiUse Gemini to classify support issues by severity, missing data and route, optimized for long-context research and synthesis.Untestedfile
LangGraphClassify an inbound message, propose a first reply hold, and flag escalation — human sends. (LangGraph stateful graph with a human checkpoint.)Untestedfile
LM StudioClassify an inbound message, propose a first reply hold, and flag escalation — human sends. (LM Studio system prompt + local server notes.)Untestedfile
MCPClassify an inbound message, propose a first reply hold, and flag escalation — human sends. (MCP-oriented tool + prompt recipe (read-only first).)Untestedfile
n8nClassify an inbound message, propose a first reply hold, and flag escalation — human sends. (n8n workflow recipe (Manual Trigger → LLM → output).)Untestedfile
OllamaClassify an inbound message, propose a first reply hold, and flag escalation — human sends. (Ollama Modelfile + chat prompt for offline runs.)Untestedfile
Open WebUIClassify an inbound message, propose a first reply hold, and flag escalation — human sends. (Open WebUI system prompt / custom agent notes.)Untestedfile
OpenRouterUse OpenRouter to classify support issues by severity, missing data and route, optimized for multi-model production routing.Untestedfile

0 of these 15 versions have a recorded check; the rest are marked untested. Status comes from each item page. BSV does not run any of them for you.

Search this job in Explore How to run How to fork All jobs

Used one of these versions? Say how it went, or ask, in Community.