Knowledge Hub: a domain, ready for your project

A Knowledge Pack gathers in one kit what you need to make a language model or assistant work on a sector: a clean corpus with sources, evaluation questions with a reference answer, production prompts and a data model. The glossary, FAQ and best practices of every pack are free; the full kit is paid.

7macro-areas

51domains

306free artefacts

Software Engineering

Drop-in kit for developers building AI/RAG/agent apps on software engineering: verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Software Architecture

Drop-in kit for developers building AI/RAG/agent apps on software architecture (patterns, trade-offs, decision records): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Microservices

Drop-in kit for developers building AI/RAG/agent apps on microservices (decomposition, service mesh, Saga, resilience): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

API Design

Drop-in kit for developers building AI/RAG/agent apps on API design (REST, GraphQL, OpenAPI, versioning, security): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Testing & QA

Drop-in kit for developers building AI/RAG/agent apps on testing & QA (unit, integration, E2E, test strategy): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Web Frontend

Drop-in kit for developers building AI/RAG/agent apps on web frontend (components, state, performance, accessibility): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Web Cybersecurity

Drop-in kit for developers building AI/RAG/agent apps on web cybersecurity (OWASP, authentication, hardening, threat modeling): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Docker & Kubernetes

Drop-in kit for developers building AI/RAG/agent apps on Docker & Kubernetes (containers, orchestration, deployment, scaling): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

DevOps & CI/CD

Drop-in kit for developers building AI/RAG/agent apps on DevOps & CI/CD (pipelines, automation, infrastructure-as-code, releases): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Observability

Drop-in kit for developers building AI/RAG/agent apps on observability (metrics, logs, tracing, alerting, SLOs): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Cloud Infrastructure

Drop-in kit for developers building AI/RAG/agent apps on cloud infrastructure (compute, networking, storage, IaC, cost): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Databases & SQL

Drop-in kit for developers building AI/RAG/agent apps on databases & SQL (modeling, queries, indexing, performance, transactions): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Data Engineering

Drop-in kit for developers building AI/RAG/agent apps on data engineering (ETL/ELT pipelines, streaming, data lakes, orchestration): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

RAG Systems

Drop-in kit for developers building AI/RAG/agent apps on RAG systems (chunking, embeddings, vector stores, retrieval, re-ranking): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

AI Agents

Drop-in kit for developers building AI/RAG/agent apps on AI agents (tool use, planning, memory, multi-agent orchestration): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Prompt Engineering

Drop-in kit for developers building AI/RAG/agent apps on prompt engineering (patterns, few-shot, chain-of-thought, structured output): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

LLM Ops

Drop-in kit for developers building AI/RAG/agent apps on LLM Ops (deployment, evaluation, monitoring, cost, guardrails): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

HIPAA Compliance for Software Builders

RAG/agent-ready kit for developers building HIPAA-compliant applications: golden eval set, cleaned RAG corpus, production prompts and a data model with labeled dataset.

MiFID II Compliance for EU Fintech Builders

RAG/agent-ready kit for developers building MiFID II-compliant EU fintech applications: golden eval set, cleaned RAG corpus, production prompts and a data model with labeled dataset.

GDPR for Software Builders

RAG/agent-ready kit for developers building GDPR-compliant applications: golden eval set, cleaned RAG corpus, production prompts and a data model with labeled dataset.

Supply Chain Management

Drop-in kit for developers building AI/RAG/agent apps on supply chain (logistics, procurement, Incoterms 2020, OTIF, WMS/TMS): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Manufacturing Engineering

Drop-in kit for developers building AI/RAG/agent apps on manufacturing (OEE, ISO 9001/14001, MES/ERP, quality, predictive maintenance): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Human Resources Management

Drop-in kit for developers building AI/RAG/agent apps on human resources management (recruiting, performance, GDPR-HR, onboarding, payroll): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Customer Relationship Management

Drop-in kit for developers building AI/RAG/agent apps on CRM (pipeline, segmentation, lifetime value, churn prediction, marketing automation): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Marketing & SEO

Drop-in kit for developers building AI/RAG/agent apps on marketing & SEO (content strategy, keyword research, ROAS/CPM, ePrivacy, GDPR-descriptive): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Automotive

Drop-in kit for developers building AI/RAG/agent apps on the automotive sector (emission regulations, V2X, ADAS, WP.29 type approval, fleet management): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Energy

Drop-in kit for developers building AI/RAG/agent apps on the energy sector (electricity markets, renewables, grid management, ARERA unbundling): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Telecom

Drop-in kit for developers building AI/RAG/agent apps in telecommunications (5G, MVNO, roaming, MNP, AGCOM regulation, billing): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Real Estate

Drop-in kit for developers building AI/RAG/agent apps in real estate (land registry, property valuation, auctions, condo management, PropTech): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Education

Drop-in kit for developers building AI/RAG/agent apps in education (LMS, adaptive learning, SCORM/xAPI, assessment, EdTech): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Tourism

Drop-in kit for developers building AI/RAG/agent apps in tourism (booking, GDS, revenue management, OTA, customer experience): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Logistics

Drop-in kit for developers building AI/RAG/agent apps on logistics (TMS/WMS, last-mile, cold chain, customs clearance, route optimization): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Retail & E-commerce

Drop-in kit for developers building AI/RAG/agent apps in retail & e-commerce (OMS, PIM, product recommendations, omnichannel, inventory): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Food & Beverage

Drop-in kit for developers building AI/RAG/agent apps in food & beverage (HACCP, traceability, EC 852/2004, nutri-score, food safety): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Business Insurance

Drop-in kit for developers building AI/RAG/agent apps in business insurance (corporate policies, claims management, actuarial pricing, Solvency II basics): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Construction

Drop-in kit for developers building AI/RAG/agent apps in construction (BIM, specifications, building bonuses, site safety D.Lgs. 81/08, public procurement): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Fashion & Textile

Drop-in kit for developers building AI/RAG/agent apps in fashion & textiles (fast fashion, luxury, PLM, sustainability, manufacturing supply chain): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Trekking

Drop-in kit for developers building AI/RAG/agent apps on trekking and mountaineering (UIAA grades, CAI signage, navigation, mountain safety): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Botanica

Drop-in kit for developers building AI/RAG/agent apps on botany (APG IV taxonomy, GBIF, scientific names, ethnobotany, plant ecology): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Biologia Marina

Drop-in kit for developers building AI/RAG/agent apps on marine biology (WoRMS, FishBase, coastal biodiversity, corals, cetaceans, water quality): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Cartografia

Drop-in kit for developers building AI/RAG/agent apps on cartography (projections, WGS84/UTM datum, IGM, OpenStreetMap, GeoJSON, GIS analysis): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

Urbex

Drop-in kit for developers building AI/RAG/agent apps on urban exploration (safe documentation, access regulations, industrial history, photography, no-locality ethics): verified golden eval set, cleaned RAG corpus, production prompts (Claude/GPT/Cursor/Copilot) and a data model with labeled dataset.

What a Knowledge Pack is

A language model answers well about a sector only if it has clean, source-anchored, verifiable material. Putting together a corpus, test questions and prompts for each domain takes a lot of work: in a Knowledge Pack you get them already structured, with the source cited line by line.

Who it is for

Developers building an assistant, semantic search or an agent on a sector they do not know in depth and who need a reliable corpus to start from.
Teams that need to measure a RAG system: the golden eval set provides questions and reference answers, with the passages that justify them.
Anyone who wants to understand a domain before writing code: the glossary, FAQ, best practices and Domain Knowledge Base are free and readable right away.

What every pack contains

Free, CC BY 4.0 license

GlossaryDefinitions of the domain's key terms, short and quotable.
TerminologySynonyms, abbreviations and IT/EN translations to normalise the language your users use.
FAQThe recurring questions about the domain, each with a direct answer.
Best practicesThe established practices of the domain, with the reason they work.
SourcesThe list of public sources the pack relies on.
ChangelogThe version history of the pack and what changed.

Premium, commercial license

Golden eval setQuestions with a reference answer and the passages that justify it, to measure faithfulness and relevance with RAGAS, promptfoo or DeepEval.
RAG corpusClean, self-contained passages, with source and section, ready to index.
Production promptsSystem prompts and instructions for Claude, GPT, GitHub Copilot and Cursor.
Data modelSQL (PostgreSQL) and Prisma schema for sources, corpus, embeddings and evaluation results.
Labeled datasetExamples with topic, intent and difficulty, for classification, routing or fine-tuning.
Use casesImplementation blueprints for concrete applications in the domain.
Business processesThe domain's process maps, to see where software fits in.

Every premium kit contains at least 50 evaluation questions, 40 corpus passages and 30 labeled examples. The premium material is in Italian; most packs also come in English.

The seven areas: which one is for you

Software: For people who build and maintain production software: architecture, APIs, testing, frontend and web security. Gives you an organised, cited knowledge base to build code assistants, technical documentation search and review tools on.
Cloud & DevOps: For people who run infrastructure, release pipelines and production systems. Brings together practices, vocabulary and references on cloud, containers and observability, useful for assisted runbooks, incident triage and infrastructure questions.
Data: For people who design databases, data pipelines and analytical models. Offers definitions, rules and check questions on SQL and data engineering, to build query assistants and data quality checks.
AI & ML: For people who build RAG systems, agents and applications on top of language models. Provides the material to measure and ship these systems: evaluation questions with sources, ready-to-use prompts and a data model to track runs.
Regulated: For people who build software subject to regulation: healthcare, finance, insurance, data protection. Organises the obligations, definitions and deadlines of each regulation into a cited corpus. It is for information only and does not replace the advice of a qualified professional.
Industry: For people who build software for an economic sector: logistics, retail, manufacturing, tourism, energy and more. Saves you from starting from zero on the language and processes of the sector: glossary, business processes and use cases, so you understand the customer before writing code.
Outdoor: For people who build apps and services about nature, hiking, cartography and exploration. Puts nomenclature, standards and open sources in order (taxonomies, reference systems, difficulty scales) for assistants and guides built on reliable data.

Pricing

Each pack costs from €15.00 to €19.00, as a one-off payment with no subscription. For several packs in the same area there is a discounted bundle; the exact price is always the one shown before payment.

Frequently asked questions

Can I reuse the free artefacts?

Yes. The glossary, terminology, FAQ, best practices, sources and changelog of every pack are released under a CC BY 4.0 license: you can copy, adapt and use them, including in a commercial product, as long as you credit the author.

Can I use the premium material in a commercial product?

Yes, to build, evaluate and run internal or commercial software. The license is non-exclusive and non-transferable; you may not resell or republish the material as a competing dataset or kit.

How do I receive a pack I bought?

Payment is one-off and handled by Stripe. After purchase, sign in with your account and download the pack as a ZIP archive from the pack page.

Do the regulated-sector packs replace a consultant?

No. Healthcare, finance, insurance and data protection packs are for information and training only: they do not replace the advice of a qualified professional.