Blog
Field notes on shipping AI-native systems with human engineering judgement: architecture, modernisation, automation, and the tradeoffs in between.
Every distributor sends secondary sales data in a slightly different shape, and the pipeline you build to read it spends most of its life absorbing that variance. Here is how we treat file-format normalization as the real engineering problem, and the failure modes we have watched break in production.
Primary sales are clean because they are billed from your own systems. Secondary sales are the number that tells you what the market actually bought, and they are the hardest thing in distribution to capture. Here is why the last mile breaks first, and what we have learned rebuilding these pipelines in client work.
How pharma secondary-sales pipelines fail - ingestion, parsing, validation, reconciliation - and the controls that fix them.
Break down voice-agent latency across VAD, STT, LLM, TTS and network; prioritize p95, fix endpointing and lower LLM TTFT.
Agentic IDEs can break legacy refactors-do scope limits, dependency mapping, characterization tests, and rules first.
Pick the smallest model and simplest runtime to self-host a private coding assistant-match model size, VRAM, and security to your use case.
A 2026 guide comparing Figma-to-code tools for handoff, prototypes, repo-mapped production - engineering cleanup remains necessary.
Shows how repeated inputs and parallel agents drive token costs-and how caching, scoping, and model routing cut spend.
Why micro-frontends often fail after 12-18 months and the safe defaults to avoid it: local state, pinned deps, CI/CD, and domain teams.
AI-generated PRs can overwhelm reviewers and raise defect risk; fix with ownership, CI gates, PR limits, and review caps.
Always-on clash-detection agents shift BIM to event-driven workflows: triage, traceability, reduced noise, and human approval.
Treat AI-generated code like a controlled engineering loop: standardize prompts, validate edits, fix exact errors, test, and gate by risk.