MyConstituency

Note: This analysis is based entirely on self-reported information from the project description. No independent verification, revenue data, customer base, or historical usage is available.

The description states that MyConstituency is a tool that allows users to find electoral data — such as MPs, local governments, and Traditional Authorities (T/A) — in one place. It was built using a combination of technologies including Rust for backend, Supabase for database, and Qwik for frontend rendering.

• The author describes building a full-stack app from scratch.
• Data comes from government PDFs that were manually scraped and cleaned.
• The system includes historical views and maps of constituencies.
• It is described as being built with AI assistance (e.g., ChatGPT).

Inference: Based on the description, MyConstituency appears to be a data aggregation and visualization tool aimed at improving access to electoral information in Malawi. However, no actual product or live deployment is evidenced.

The author positions MyConstituency as an effort to democratize access to public data in Malawi — especially where infrastructure and service delivery are lacking. The project was inspired by the difficulty of finding basic electoral information, which led to a desire to make such data searchable and accessible.

• The tagline says: “A place where my fellow Malawians and any foreign weirdos curious about our electoral process can easily find all the data in one place.”
• The author claims that technology can fix access issues without waiting for large-scale infrastructure or budgetary support.
• There is an emphasis on using AI to extract and clean data from PDFs.

Claim vs Fact: These are self-reported claims about intent, not proof of traction or impact. The project was submitted to a hackathon and has no evidence of being used beyond its development phase.

The description states that the target users are:

• Fellow Malawians who need to know their electoral representatives.
• Foreign observers or researchers interested in Malawi’s electoral process.

There is no indication of specific personas, segmentation strategies, or user research. The author mentions a “foreign weirdo” — implying curiosity from outsiders — but does not elaborate on how they would engage with the tool.

Not evidenced: No evidence of defined customer segments, usage patterns, or feedback loops.

There is no mention of pricing, monetization, or business model in the description. The project was built as a hackathon submission and does not appear to have any revenue streams or commercial intent described.

Not evidenced: No evidence of pricing, subscriptions, or monetization strategy.

The author reports building:

• A Rust-based backend
• Supabase for data storage
• Qwik for frontend rendering
• GSAP for animations
• GraphQL for API access
• MEC (likely a reference to Malawi Electoral Commission)
• Data cleaning pipelines using AI tools like ChatGPT

Challenges included:

• Government data not designed for use (PDF-only, no APIs)
• Scope creep due to over-engineering (e.g., choosing Rust)
• Token exhaustion from AI usage
• Missing data year

Inference: The technical stack suggests a developer-focused approach with some ambition. However, the project was built under time constraints and with limited resources — not necessarily a scalable or production-ready architecture.

There is no evidence of:

• Users or customers
• Revenue or monetization
• Product adoption or engagement metrics
• Deployment in production
• Any form of public release or ongoing maintenance

The project was submitted to a hackathon and described as being "out of tokens" — indicating it has not yet reached a functional state for broader use.

Not evidenced: No traction, user base, or product maturity indicators are provided.

No competitive landscape is described. The author does not reference existing tools or platforms that might offer similar services in Malawi or elsewhere.

Not evidenced: No information on competitors or market positioning.

• Unverified data source: Government PDFs are not structured for machine use, and the project relies heavily on manual scraping.
• Limited team size: Only one developer (Manfred Chirambo) is mentioned.
• Over-engineering risk: Choice of Rust and AI-heavy development may have added unnecessary complexity.
• No commercial viability: No pricing or monetization model is evident.
• Token dependency: The project ran out of OpenAI tokens, suggesting reliance on external tools that are not scalable or sustainable.
• Lack of traction: No evidence of users or adoption beyond the author’s own development.

Inference: The project lacks commercial viability and scalability without further development and validation.

1. What is the current status of data availability? Are there any ongoing efforts to obtain structured datasets from official sources?
2. Has there been any feedback or engagement from users in Malawi beyond the author’s own use?
3. How do you plan to sustain development beyond the initial hackathon phase?
4. Do you have a clear path toward monetization or long-term impact?
5. What are the legal and ethical considerations around scraping government data?
6. Are there any partnerships with local organizations, NGOs, or government bodies that could support this project?