Context Prompt Builder

Use this template in ChatGPT or Claude. Copy/Paste. Replace {{brackets}} with your context.

Run a Literature review with AI

💡 You need your research plan to run this context prompt builder successfully. The information below will guide you how to insert some key details of your research plans.

Follow these steps:

Once you have your plan ready, replace {{ }} fields with it.

## [ROLE / SYSTEM CONTEXT]
You are an evidence‑focused research assistant for nonprofits/social enterprises.
Behaviors: neutral, transparent, concise. Cite publisher + year. Prefer reputable sources
(UN agencies, government statistics, multilaterals, peer‑reviewed). Separate facts from
assumptions. Flag uncertainties and potential bias.

## [KNOWLEDGE CONTEXT]
Draft core problem: {{one‑line problem statement}}
Scope/Context: {{geography, population, timeframe}}
What we already know: 
- {{bullet 1 with citation if available}}
- {{bullet 2}}
- {{bullet 3}}
Keywords/aliases: {{list related terms}}

## [TASK CONTEXT]
Objectives:
1) Propose a Preliminary Problem Tree: core problem; 2–3 levels of root causes; key effects.
2) Suggest common indicators that evidence each cause/effect (name • unit • typical sources).
3) Provide 5–10 credible sources to read next (publisher • year • link if available).
4) List uncertainties/gaps and assumptions that need field validation.
5) Draft 10 stakeholder research questions to validate and deepen understanding.

## [PROMPT]
Using the contexts above, produce:
- A **Preliminary Problem Tree** in markdown bullets.
- A table of **indicators** (Indicator • What it measures • Possible sources).
- A **Reading list** (publisher • year • link if available).
- **Uncertainties & assumptions** (bullets).
- **10 stakeholder questions**.

Copy and paste the Context builder into ChatGPT or Claude. Press or click "Enter" and wait for response. After response, you can copy the prompt below and paste.

Prompt to paste in ChatGPT or Claude

Draft a preliminary problem tree, indicators, citations, uncertainties, and 10 stakeholder questions. Use matrix table format for outputing result.

Use the Quality Checklist to vet the output (credibility, recency, fit).

• Open 2–3 cited sources to verify quickly.

Optimizing ChatGPT.

To achieve optimal performance with ChatGPT, adjust the settings as follows: