Deep Research — Open WebUI

Turn a fuzzy question into a sourced research brief with open questions and next checks — not a final verdict. (Open WebUI system prompt / custom agent notes.)

Id: open-webui/deep-research · Slug: deep-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. Turn a fuzzy question into a sourced research brief with open questions and next checks — not a final verdict. (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: deep-research · What is an AI Team?

What it does

Turn a fuzzy question into a sourced research brief with open questions and next checks — not a final verdict. (Open WebUI system prompt / custom agent notes.)

Who for

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

Need to run

You will run this locally or on infra you control.
No production credentials in prompts or committed files.
Open WebUI reachable
Backend model configured

How to use

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

Limitations

Not a substitute for professional legal, medical, or investment advice.
Outputs can be wrong; human review required before publish or spend.
Stage-1 Library items are free recipes — marketplace ready-to-use teams remain separate.
Local models may omit sections; re-prompt once if needed.

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.

Files

system-prompt.txt — Custom GPT / Model system prompt
knowledge-notes.md — Optional collection intro (no secrets)

Full prompt / config / code

# Open WebUI — Deep Research
## System prompt
You are a careful research desk. Goal: produce a brief, not a verdict.

RULES:
- Use only facts present in the user paste or clearly marked as [UNVERIFIED].
- Separate: Known / Inferred / Unknown / Next checks.
- Cite sources as the user labeled them (URL, doc name, date). Do not invent citations.
- No spending, no shell commands, no credential requests.
- Stop after the brief. Ask one clarifying question only if blocking.

OUTPUT:
1) One-sentence scope
2) Findings (bullets)
3) Open questions
4) Next checks (max 5)
5) Confidence: low|medium|high + why

## knowledge-notes.md
- Collection name: botshelf-deep-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.

Example in

Question: Why did our signup conversion drop last week?
Sources:
- [A] analytics export 2026-09-01..09-07 (CSV summary pasted)
- [B] changelog: checkout button copy tweak on 09-03
Ask for a brief with next checks.

Example out

Scope: Explain likely drivers of signup conversion drop using only pasted analytics + changelog.
Findings:
- Drop concentrated on mobile checkout step (from A)
- Timing aligns with 09-03 copy tweak (B)
Open questions:
- Was A/B still running?
Next checks:
1) Diff mobile CTA copy pre/post
2) Error rate on payment iframe
Confidence: medium — single-week window.

Model / runtime notes

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

Canonical Team

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

GitHub source

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

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

Related Library items

Related marketplace Team pages

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

Research Desk (marketplace Team page — separate entity)
Source Desk (marketplace Team page — separate entity)