◆ Blog
Notes on building AI that ships.
Practical, production-focused writing on RAG, agents, OCR and automation, from real delivered work.
-
What is an AI medical scribe? A clinician's guide
A plain-language guide to AI medical scribes: what they are, how ambient scribing works, the benefits and limits, and how to choose one you can trust in real care.
Read -
AI in medical notes: what it changes for clinicians
What AI in medical notes really changes: accuracy, review workflow, EMR integration and the risks to manage, so the technology helps clinicians instead of adding work.
Read -
AI for medical notes: a practical guide
How AI for medical notes works, from speech to structured documentation, what it saves clinicians, and what to look for in a system you can actually trust in care.
Read -
AI medical scribe notes: a real example (audio to SOAP note)
A concrete example of what an AI medical scribe produces: turning a patient-doctor conversation into a structured SOAP note, and how the pipeline maps speech to clinical charting fields.
Read -
Case study: +40% query accuracy with graph + vector retrieval
How EpochC built a dual-module retrieval platform combining Neo4j knowledge graphs and vector embeddings that beat a vector-only baseline by 40% for FinTech research.
Read -
Case study: one conversational API over four clinical AI agents
How EpochC used a LangGraph ReAct orchestrator to collapse scattered healthcare endpoints into a single conversational API, with persistent memory and zero citation hallucinations.
Read -
Case study: automating KYC to remove EUR 40,000 a year
How EpochC built a full-stack identity-verification system with OCR, facial recognition and a lightweight document classifier that automated customer onboarding for a money-transfer platform, at 98% field accuracy.
Read -
How to reduce LLM costs in production
Practical ways to cut the running cost of an LLM application without hurting quality: model routing, caching, retrieval, prompt discipline and smaller models where they fit.
Read -
LangGraph vs LangChain: which should you use?
LangChain and LangGraph are not competitors. Here is how they fit together, and when you should reach for LangGraph's graph model over a simple LangChain chain.
Read -
How to choose an AI development company
A practical checklist for hiring an AI development partner: what to look for, the red flags that predict a failed project, and the questions that separate builders from demo-makers.
Read -
Building an AI medical scribe: from audio to structured notes
How to turn a patient-doctor conversation into accurate, structured clinical documentation with speech-to-text, entity extraction and confidence-scored form filling.
Read -
Knowledge graphs vs vector search for RAG
Vector search finds similar text. Knowledge graphs capture relationships. Here is when each wins, and why the best retrieval systems use both.
Read -
What is agentic AI? A practical guide for businesses
Agentic AI explained without the hype: what it is, how it differs from a chatbot, where it creates real value, and how to start safely.
Read -
How much does it cost to build an AI agent?
A practical breakdown of what actually drives the cost of building a production AI agent, why cheap prototypes fail, and how to budget for something that ships.
Read -
RAG vs fine-tuning: which do you actually need?
RAG and fine-tuning solve different problems. Here is a practical decision framework for choosing between them, and why most teams reach for fine-tuning when they need retrieval.
Read -
Multi-agent systems with LangGraph: when you need them (and when you don't)
Multi-agent architectures are powerful and easy to over-use. Here is how to tell when a LangGraph multi-agent system is the right call, and how we build them for production.
Read -
OCR for KYC: building document verification that actually works
What it takes to build automated identity verification with OCR and facial recognition, from field accuracy to edge deployment, based on a system that removed EUR 40,000 per year in cost.
Read -
How to stop your RAG system from hallucinating
Most RAG hallucinations are a retrieval problem, not a model problem. Here is how we build retrieval-augmented generation that cites its sources and refuses to make things up.
Read