Blog
Practical notes on AI, surveys, official statistics, and development data.
AI Agents for Survey Data Cleaning
Survey data cleaning is high-value, messy, and under pressure. Agentic workflows can prepare issue logs, callback sheets, open-end coding suggestions, and reproducible Stata implementation while keeping human decisions visible.
Fieldwork QCAI Agents for Survey Quality Control
Good fieldwork quality control is not just a dashboard. A dedicated agent can review questionnaires, write checks, compare enumerator patterns, analyse comments, and keep monitoring after intervention.
Agentic AIWhat OpenClaw Could Mean for International Development Organisations
OpenClaw points to a different kind of AI adoption for development teams: local workspaces, durable tasks, files, scripts, and agents that can keep working beyond a single prompt.
Survey scriptingAI for Survey Scripting: Where It Actually Helps
Survey programming is a natural place for AI support, but generic models need structure, platform context, and guardrails before their advice becomes useful in real CAPI workflows.
Responsible AIBring Your Own Key: Safer AI for Non-Profit Teams
BYOK patterns can give smaller organisations more control over model choice, cost, governance, and data retention when adopting AI tools.
Survey SolutionsUsing Specialized AI to Transform Global Data Collection
General-purpose AI often fails in specialised survey environments. A custom Survey Solutions assistant can make platform-specific advice precise and field-ready.