Practical notes on AI, surveys, official statistics, and development data.

AI agents are becoming genuinely useful collaborators for technical teams. Tools like Codex, Claude Code, and other agentic development environments can read documentation, inspect files, write code, and work through multi-step tasks. But t [...]

The Concept Survey data cleaning is one of those jobs that matter enormously yet remains largely manual, and often a little messy! By the time a project reaches cleaning, teams are under pressure, fieldwork has moved on, and nobody wants to spend days buried in spreadsheets working out which cases to keep, which values to [...]

High-quality data collection sits at the heart of good statistics. Many survey teams recognize the importance of conducting thorough Quality Control (QC) from the outset of fieldwork, but time constraints and competing priorities often prevent it from receiving the necessary attention. That is the gap I have been exploring at Impact Engines, particularly the potential [...]

OpenClaw has been hard to ignore lately. It has been everywhere in AI circles, climbed the GitHub charts at remarkable speed, and become one of those projects that naturally invites curiosity if you are paying attention to where AI tooling is heading. I was interested not just in the usual personal productivity angle, but in [...]

If you work in national statistics or monitoring and evaluation within the global development space, you know how important digital questionnaires are. If the survey is badly structured, the data quality suffers; if the data quality suffers, so do the decisions that follow. That makes survey programming a natural place to look for AI support. [...]

It started with a spark of curiosity. My six-year-old son began asking the question every modern parent eventually hears: "How do computers actually work?", shortly followed by "I want my own computer!". I decided this was a good teaching opportunity; let's attempt to build our own computer. With the "Great RAM Crisis" of 2026 making [...]

AI has enormous potential for small non-profits and community-based organizations to overcome resource constraints and maximize their impact. However, across the sector, the shift to AI tools has remained predominantly employee-driven and reliant on "free" tiers of the big providers OpenAI, Google and Anthropic. This setup creates two main issues: A Governance Problem - When [...]

General-purpose AI fails in specialized environments like Survey Solutions, where "standard" code breaks under unique architectural rules. We built a custom AI assistant that combines expert-tuned logic with PDF and vision capabilities to turn practically useless generic advice into precise, field-ready solutions for global data collection.