Sheet 03. The archive.
Working notes from the space between protocol and practice.
Essays on method, on AI in public health, and on what the field keeps teaching me. Sources are cited. Opinions are mine. The list is the archive; there is nothing else on this sheet.
A3 · Index
All essays
11 sheets
- 03/11 Sept 2026 The 0.9 percent Rapid qualitative analysis appears in less than one percent of implementation science studies. AI may finally make it common. The question is what we trade for the speed. 3 min
- 03/10 Aug 2026 The red alert and the ASHA A clinical copilot in Nairobi cut diagnostic errors most when it interrupted. What would an interruption mean for a community health worker with no clinical backstop? 3 min
- 03/09 Jul 2026 Novices with a probe One day of training produced sonographer-level gestational age estimates in Lusaka. The hard question is what happens to the referral chain after the machine says high risk. 3 min
- 03/08 Jun 2026 Silicon mothers Language models can produce plausible answers about pregnancy in Assam. Plausibility is not validity, and formative research cannot be outsourced to a model that has never missed an antenatal visit. 3 min
- 03/07 May 2026 ABHA before algorithms India's bet is that identity, registries, and consent come before models. I think the consent manager, not the model, is the real AI policy. 3 min
- 03/06 Apr 2026 Five thousand alerts, zero outcome studies India's media-scanning surveillance system has flagged thousands of potential outbreaks. Nobody has yet shown it changed the course of one. Surveillance AI needs the discipline we demand of drugs. 3 min
- 03/05 Mar 2026 Consulting without selling Most AI readiness tools for non-profits are written by vendors. Responsible advice often means recommending no AI at all, or a spreadsheet. 3 min
- 03/04 Feb 2026 Code-mixed and context-less Real maternal health queries are short, mix languages, and leave out the symptom. The safety problem in chatbots for mothers is linguistic and social before it is technical. 3 min
- 03/03 Jan 2026 Hypothesis machines Causal machine learning can generate hypotheses, not answers. On resisting the pull to let a model settle what a field trial should decide. 3 min
- 03/02 Dec 2025 Screening with a model that cannot be embarrassed Language models now screen abstracts for systematic reviews with a sensitivity that varies by model, prompt, and threshold. The new reporting standards are good. The habit they protect is better. 3 min
- 03/01 Nov 2025 Who participates when a model is in the room Participatory research assumes people can see and shape the method. When the method is a model, that assumption needs rebuilding from the ground up. 3 min