When a plausible answer is not enough
The question that started determinIQ: what should we be able to check when an AI-assisted analytical answer matters?
Read the articleResearch, case studies and reflections connected by this topic.
The question that started determinIQ: what should we be able to check when an AI-assisted analytical answer matters?
Read the articleWhy an automated discovery system should be able to finish without claiming that every dataset contains something noteworthy.
Read the articleReflections on using AI to accelerate product engineering while keeping architecture, testing, product acceptance and accountability human-led.
Read the articleAn investigation into how natural-language collaboration can accelerate practical engineering while retaining architectural authority, verification and human judgement.
Read the studyA practical case study of the WordPress research website: its editorial architecture, accessible presentation, automated draft publishing and observed local test results.
Read the studyHow natural-language intentions become bounded engineering changes, with architectural constraints and observable acceptance criteria.
Read the studyWhy rapid AI-assisted implementation still needs explicit responsibility boundaries, stable ownership and human acceptance.
Read the studyAn examination of evidence-led engineering iterations, why working code still needs inspection, and how removing complexity can improve a product.
Read the study