Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

chimaobim1/African-Chain-of-Thought-Prompt

Domain:

natural language processing

Record type:

tools
Creator:
chi
Host:
A reusable, African-contextualized chain-of-thought prompt engineering template for LLMs. # African-Chain-of-Thought-Prompt A reusable, African-contextualized chain-of-thought prompt engineering template for LLMs. # 🌍 African Context Chain-of-Thought Prompt Engineering Template --- ## 📌 Overview This repository provides a **structured, reusable prompt engineering template** for Large Language Models (LLMs). It enables **transparent chain-of-thought reasoning** while embedding context from **leading African tech-driven cities** such as Lagos, Abuja, Port Harcourt (Nigeria) and Accra, Kumasi (Ghana). The template is: - **Structured** – step-by-step reasoning. - **Contextualized** – grounded in African urban/tech realities. - **Fluid** – adaptable across tasks and audiences. - **Self-checking** – includes a review step to improve quality. --- ## 🎯 Purpose This template guides LLMs through reasoning while: - Embedding African context for realism. - Adapting outputs for both technical and non-technical audiences. - Ensuring reliability with a built-in self-review loop. --- ## 🛠️ How to Use 1. Open `template.md`. 2. Fill in the parameters (task, audience, depth, etc.). 3. Paste the template into your LLM environment. 4. Run with your specific input. 5. Review output and adapt as needed. --- ## 💡 Example **Input:** Task: Design a smart transport solution for improving commuting. Audience: mixed Depth: standard Output format: markdown Cities focus: Lagos, Accra Constraints: limited electricity Evidence required: yes **Output (excerpt):** 1. Restate → "We are designing a smart transport solution for African cities." 2. Context → "Lagos and Accra face congestion, unstable electricity, and fragmented transport..." 3. Approaches → - Option A: IoT-enabled traffic lights + GPS bus tracking. - Option B: Ride-hailing + commuter apps. 4. Evaluation → "IoT requires reliable electricity; ride-hailing leverages mobile penetration but faces regulatory hurdles." 5. Conclusion → **"A hybrid approach combining ride-hailing data with optimized bus scheduling is …

Visit

github.com

Languages

Ga