Research & Insights
Thinking out loud about technology
Original research, technical deep-dives, and honest takes on the technologies shaping enterprise AI, data infrastructure, and legacy modernisation in regulated industries.
How to implement RAG on enterprise data: the honest guide
The tutorials assume a clean corpus. Your corpus is not clean. Discovery sprints, chunking strategy, retrieval evaluation, and governance — what actually matters when building RAG for enterprise data.
Read article →Why on-premise AI is not a step backward
The narrative that cloud-native equals modern is wrong for regulated industries. Here is the architectural and governance case for sovereign, on-premise AI infrastructure in healthcare and pharma.
Read article →RAG vs fine-tuning: a pragmatic guide for enterprise AI teams
A decision framework for choosing between retrieval-augmented generation and fine-tuning, based on data freshness, inference cost, latency requirements, and the risk profile of your use case.
Read article →Governing AI outputs in regulated industries: a technical playbook
Healthcare, pharma, and public sector AI deployments require more than guardrails. Audit logging, output validation, human-in-the-loop patterns, and model card requirements from production deployments.
Read article →The lakehouse is not enough: why operational and analytical data need different treatment
Lakehouses excel at analytical workloads but struggle with the transactional guarantees and schema evolution pace of operational systems. How to architect for both without rebuilding everything.
Read article →AI-assisted reverse engineering of legacy platforms: lessons from the field
Applying RAG and multi-agent workflows to reconstruct functional and architectural knowledge from large legacy codebases. What works, what does not, and what traceability requirements actually look like.
Read article →Legge 132/2025 e AI in sanità: cosa cambia per ospedali, farmacie e aziende farmaceutiche
La Legge n. 132 del 23 settembre 2025 è la prima normativa organica italiana sull'intelligenza artificiale. Per le organizzazioni in ambito sanitario e farmaceutico, introduce obblighi specifici su governance, data residency e uso secondario dei dati.
Read article →Event sourcing in practice: lessons from five production systems
Event sourcing promises auditability and temporal querying. In practice, projection management, schema evolution, and snapshot strategy are where most implementations struggle.
Read article →Let's talk about your project
AI infrastructure to build, a legacy system to modernise, or an ERP to connect to the future? Get in touch.
Start the conversation →