Yearly Archives: 2026

Enterprise Point-in-Time (PIT) Reconstruction: The Regulatory Playbook

Leave a Reply · 03/01/2026 · 89 of 89 reads (last 12 months vs since 2024)

This article sets out the definitive regulatory playbook for enterprise Point-in-Time (PIT) reconstruction in UK Financial Services. It explains why PIT is now a supervisory expectation: driven by PRA/FCA reviews, Consumer Duty, s166 investigations, AML/KYC forensics, and model risk, and makes a clear distinction between “state as known” and “state as now known”. Covering SCD2 foundations, entity resolution, precedence versioning, multi-domain alignment, temporal repair, and reproducible rebuild patterns, it shows how to construct a deterministic, explainable PIT engine that can withstand audit, replay history reliably, and defend regulatory outcomes with confidence.

Continue reading →

The Work Speaks for Itself

Leave a Reply · 02/01/2026 · 159 of 159 reads (last 12 months vs since 2024)

This article explains why I am stepping back from writing about neurodiversity as a primary lens for my work. Not because the subject no longer matters, but because over time it has begun to obscure achievement rather than illuminate it. This is a reflection on explanation, authority, and the point at which context stops being helpful and starts getting in the way.

Continue reading →

Building Regulator-Defensible Enterprise RAG Systems (FCA/PRA/SMCR)

Leave a Reply · 02/01/2026 · 130 of 130 reads (last 12 months vs since 2024)

This article defines what regulator-defensible enterprise Retrieval-augmented generation (RAG) looks like in Financial Services (at least in 2025–2026). Rather than focusing on model quality, it frames RAG through the questions regulators actually ask: what information was used, can the answer be reproduced, who is accountable, and how risk is controlled. It sets out minimum standards for context provenance, audit-grade logging, temporal and precedence-aware retrieval, human-in-the-loop escalation, and replayability. The result is a clear distinction between RAG prototypes and enterprise systems that can survive PRA/FCA and SMCR scrutiny.

Continue reading →

The Hidden Costs of Masking: What Research and Autistic Voices Reveal

Leave a Reply · 01/01/2026 · 265 of 265 reads (last 12 months vs since 2024)

This article explores the hidden psychological, physical, and social costs of autistic masking, drawing on current research and lived experience. Combining academic insight with personal anecdotes, it examines how masking impacts wellbeing, identity, and burnout, and argues that masking is not an individual adaptation but a response to structural neurotypical norms and inequality embedded in modern social and professional life.

Continue reading →

Temporal RAG: Retrieving “State as Known on Date X” for LLMs in Financial Services

Leave a Reply · 01/01/2026 · 120 of 120 reads (last 12 months vs since 2024)

This article explains why standard Retrieval-Augmented Generation (RAG) silently corrupts history in Financial Services by answering past questions with present-day truth. It introduces Temporal RAG: a regulator-defensible retrieval pattern that conditions every query on an explicit as_of timestamp and retrieves only from Point-in-Time (PIT) slices governed by SCD2 validity, precedence rules, and repair policies. Using concrete implementation patterns and audit reconstruction examples, it shows how to make LLM retrieval reproducible, evidential, and safe for complaints, remediation, AML, and conduct-risk use cases.

Continue reading →