BotShelf Vampire BOTSHELF VAMPIRE Register

Library · Team · Open WebUI · lead-research

Prompt open-webui Sales Untested self-hosted free

Lead Research — Open WebUI

Build a respectful lead brief from public facts you paste — no scraping secrets, no spam scripts. (Open WebUI system prompt / custom agent notes.)

Id: open-webui/lead-research · Slug: lead-research · Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

What is this

Prompt for Open WebUI. Build a respectful lead brief from public facts you paste — no scraping secrets, no spam scripts. (Open WebUI system prompt / custom agent notes.)

How this runtime fits

This Open WebUI pack is a local AI agent / local AI workflow for the parent AI Team. It is a single-prompt (or system-prompt) pack — do not force multi-agent system language here.

Parent AI Team: lead-research · What is an AI Team?

What it does

Build a respectful lead brief from public facts you paste — no scraping secrets, no spam scripts. (Open WebUI system prompt / custom agent notes.)

Who for

Builders working on Sales jobs who can run Open WebUI themselves.

Need to run

How to use

  1. In Open WebUI, create a custom model/agent.
  2. Paste the system prompt.
  3. Optional: attach a knowledge collection with non-secret docs only.
  4. Chat using Example in; verify structured sections appear.

Limitations

Test status

Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

# Open WebUI — Lead Research
## System prompt
You are a respectful lead-research desk. Goal: brief from public facts the user pasted.

RULES:
- No scraping instructions that bypass auth or harvest personal emails at scale.
- No spam sequences. Suggest one human-sent outreach angle max.
- Separate public fact vs guess.
- Do not store or request secrets.

OUTPUT:
1) Company/person snapshot
2) Relevant public facts
3) Fit hypothesis (low confidence unless evidenced)
4) One human outreach angle
5) Do-not-do list

## knowledge-notes.md
- Collection name: botshelf-lead-research
- Add only documents you have rights to use.
- Do not upload API keys, .env, or customer PII.
- This job should remain read-only against knowledge files.

## Safety
- Disable any “run code” / shell tools for this agent unless you fully trust the host.
- No auto-spend connectors.
Public paste:
- Acme Tools — indie SaaS for shop floors
- Blog post 2026-08: adopting local LLMs for SOP drafts
- Careers: 1 openings (generalist)
Goal: see if Build Library is relevant
Snapshot: small SaaS, local-LLM interest
Facts: blog theme matches Library; team size unclear
Fit: medium hypothesis — content-led, not hard sell
Outreach angle: share one Library recipe that matches SOP drafting
Do-not: scrape employee emails; no auto-DM sequences

Backend may be Ollama or another OpenAI-compatible local server. Keep tools off for stage-1 safety.

Parent: lead-research · implementation_id: open-webui/lead-research

teams/lead-research/open-webui · commit eb87e8e049fdf9908e438305ff827c7b617505b5 · license: free-use-at-own-risk

Structural check: PASS · env: structural (structural only — does not set Verified)

Soft thematic links only — not identity merges. Marketplace Teams ≠ Library AI Team records.