Knowledge that's correct — and gets cited
No content mill, just pieces that explain how reliable AI really works. Written for people who want to understand it properly — and structured so AI assistants pick it up correctly (GEO).
More from Insights
How do you create an AI policy that employees can actually apply?
A practical AI policy for employees: approved tools, safe data handling, human oversight, and clear working rules on a single page.
ReadWhat does a RAG system cost an SME per month?
What determines the monthly costs of a RAG system for SMEs? Learn which cost components to include and how to prepare a realistic monthly budget yourself.
ReadHow do you make SharePoint documents searchable with RAG?
RAG lets employees search SharePoint documents with everyday questions. Permissions, synchronization and document structure need attention from the start.
ReadHow do you find shadow AI inside your organization?
Find out where employees use AI through open conversations, logs and a no-blame survey. Then make safe use practical with clear rules and alternatives.
ReadWhat happens when your agent stops halfway?
When an agent stops halfway, it may leave changes incomplete or repeat work after restarting. Learn how to save progress, resume safely, surface failures, and give a person control.
ReadHow do you create a brand-neutral questionnaire for an AI baseline?
A brand-neutral questionnaire shows whether and how AI assistants mention your organisation in response to questions customers actually ask. Learn how to choose prompts, record answers and make a baseline useful over time.
ReadCan an AI agent prepare your bookkeeping?
An AI agent can read and sort receipts and invoices, then suggest entries. Learn how to review its work, limit its permissions, and run a small trial with your accountant.
ReadWhy does my AI assistant give two answers to the same question?
An AI assistant may answer the same question differently because of model variation, conversation context, or retrieved sources. Learn how to make responses more consistent and when differences point to a question or knowledge base that needs attention.
ReadWhen Is a Small Model Good Enough?
Learn when a small AI model can handle a task, how to test it on your own examples, and when to scale up. See how error costs, privacy, RAG, routing, and quantization affect the choice.
ReadAI for Associations and Foundations on a Small Budget
Associations and foundations can use AI for recurring writing tasks without a large budget. Learn how to start small, manage costs, protect personal data and give volunteers clear rules.
ReadMultilingual Sites and AI: How to Stop Your Translations Competing with Each Other
Keep language versions of your site from competing in search. Learn how to structure URLs, hreflang, canonicals, translations, and internal links so search engines and AI assistants can identify the right version.
ReadFrom script to agent: when is AI overkill?
Learn when a script or fixed rule is a better fit than an AI agent. Compare workflows and agents on cost, speed, predictability, testing and maintenance, then choose an approach that matches the task and its risks.
ReadHow do you keep an AI knowledge base up to date without reindexing everything?
Keep an AI knowledge base current by detecting changes at the document level and processing only new or revised content. Remove retired sources, test answers after updates, and use full reindexing as a backstop.
ReadBudget Guards That Actually Slow Things Down
A budget guard limits AI use and intervenes when consumption rises. Learn how to set layered limits, curb agents, test an emergency stop, and explain clearly to users what happens when a limit is reached.
ReadAI for HR: CV screening is where things go wrong
AI can support routine HR work, but screening and ranking candidates raises risks around fairness, privacy and explainability. Learn how to set boundaries, keep people responsible for decisions and inform candidates and staff.
ReadAre you cited or summarized—and what does that mean for traffic?
An AI assistant may name your website as a source, summarize its information without attribution, or answer from model memory. Learn what each means for visibility, traffic, and measurement.
ReadHow do you test an AI agent without blowing up production?
Learn how to test an AI agent safely with mock data, simulated tools, repeatable scenarios and human approval, then roll it out gradually with monitoring and an emergency stop.
ReadWhat does on-prem AI cost per year, honestly calculated?
On-prem AI costs more than hardware. Learn how to include investment, energy, operations, security, and actual usage in an annual estimate, then compare it fairly with an external AI service.
ReadRAG, fine-tuning, or long context: when should you choose each?
RAG, fine-tuning, and long context solve different problems. Learn when to use current, source-backed knowledge, when to shape a model’s behavior, and when to provide documents directly.
ReadLatency: why users abandon an AI assistant after eight seconds
Why can an AI assistant feel slow? Learn what causes latency and how streaming, model routing, progress updates, sensible timeouts and measurement can improve the user experience.
ReadAI for maintenance teams: making manuals searchable
Make manuals, maintenance schedules and fault reports searchable with an AI assistant that answers in plain language and points to its sources. Learn how to prepare documents, protect safety and check quality.
ReadWhat should you ask an AI provider before signing?
Before choosing an AI provider, ask about data, model training, security, quality, support, costs and regulation. Get the answers in writing so you can review the commitments and assess the risks.
ReadInternal links as a topic cluster: how do you show AI what you know best?
Learn how a central pillar page, supporting articles and relevant internal links can make your site’s topic structure clearer to readers, search engines and AI assistants.
ReadLeast privilege for non-human users: what permissions should an agent get?
Give an AI agent its own identity and only the limited, temporary permissions its task requires. Separate reading, writing and high-risk actions, with approval and logging where appropriate.
ReadAI behind the firewall: can you run your model entirely in-house?
Learn what it takes to run a language model and its search and document layer entirely inside your network, including updates, access controls, logging, backups, trade-offs and hybrid options.
ReadDo you actually need a vector database?
A vector database is not essential for every RAG project. Learn about simpler options, what to consider when choosing, and when a dedicated database may be useful.
ReadA NAS as an AI foundation: what can it do, and what can’t it?
A NAS can provide a dependable storage and management layer for an AI setup, but it is usually not the right machine for large models. Learn which tasks fit, where the limits are, and how to protect reliability and access.
ReadAI for estate agents and real estate: what is realistic?
Explore practical uses of AI in an estate agency, from property descriptions and customer questions to document search. Learn why pricing, tenant screening and personal data still require careful human oversight.
ReadThe AI Act and the GDPR: where do they overlap, and where do they clash?
The AI Act and the GDPR often apply at the same time, but address different aspects of AI. Learn where transparency, oversight and risk assessment meet, where data rules can pull in different directions, and how to approach them in practice.
ReadWhat does an AI assistant do with your prices if you don’t publish them?
Find out how AI assistants may answer questions about unpublished prices, and how clear pricing principles, an indication or explanation, and consistent website information can reduce guesswork.
ReadRetries, timeouts and dead agents: reliability in practice
An agent can stall or repeat an action unexpectedly. Learn how timeouts, bounded retries, resumable steps, status monitoring and human escalation make these failures manageable.
ReadQuantization explained: how much quality do you trade for speed?
Quantization makes AI models smaller and often faster by storing their weights with fewer bits. Learn what quality may be lost, how to test it, and how to choose a balance for your hardware and use cases.
ReadMetadata filters: searching within the right department, period or case
Metadata filters narrow RAG searches to the relevant department, period or case. Learn how to maintain metadata, apply access controls and test filters so answers are more precise and safer.
ReadDocker or native: where should you run a critical AI service?
Docker can make an AI service easier to reproduce and recover, while native deployment may simplify hardware access. Learn how to choose based on maintenance, recovery, updates and hardware requirements.
ReadAI in education: where is the line?
AI can support learning, planning, feedback and administration in education. The line is crossed when it replaces students' own thinking, makes consequential decisions, or handles student data without adequate privacy and human oversight.
ReadWho is liable when an AI answer is wrong?
Who bears responsibility when an AI system gives a wrong answer? Learn how liability can be divided across the AI supply chain and which contractual and technical measures can reduce risk.
ReadE-E-A-T for small businesses: showing expertise without a big brand
A practical guide for small businesses that want to strengthen E-E-A-T through real experience, expertise, trustworthy company information, structured data and consistent online profiles without relying on a famous brand.
ReadCan an AI agent handle your email?
An AI agent can sort, summarise and draft email replies. Autonomous sending requires strict permissions, logging, human approval and safeguards against prompt injection and confidential-data exposure.
ReadWhat Are You Allowed to Keep From an AI Conversation?
Which parts of an AI conversation can you retain, for how long, and why? A practical guide to conversation logs, personal data, pseudonymisation, audit trails, providers, deletion and workable retention policies.
ReadRAG over PDFs: why scans are your biggest enemy
Scanned PDFs make RAG systems vulnerable to extraction errors. Learn why OCR, tables and complex layouts cause problems and how to validate documents before indexing them.
ReadBackups for AI systems: what should you keep besides the data?
A usable AI backup contains more than documents and databases. Models, prompts, indexing configuration, agent permissions, evaluation sets and recovery procedures also determine whether the system can actually be restored.
ReadAI for webshops: product data, reviews and customer questions
AI can help webshops manage product data, reviews and customer questions, provided the source data is reliable, human oversight remains in place and the system does not invent specifications, reviews or customer information.
ReadKeeping an AI register: what should you put in it?
A practical AI register creates visibility into AI systems, suppliers, data, risks and oversight. Learn which fields to record, who should maintain them and how the register connects to GDPR records, DPIAs and AI governance.
ReadHow important is page speed when a model reads your page?
Page speed still matters to visitors and automated retrieval systems. For AI visibility, the priority is making essential content quickly and reliably available without requiring complex JavaScript rendering.
ReadWhen does a human need to approve? A decision tree for AI agent autonomy
Not every action an AI agent can take deserves the same amount of freedom. A practical framework based on reversibility, impact, scale and input trustworthiness — with a concrete decision tree for when a human should approve first.
ReadHow do you anonymise documents before they enter a model?
Documents should be anonymised before AI processing by detecting personal information and removing, masking or replacing it — ideally locally, before text reaches an external API. Pseudonymisation is often more practical, but the resulting data remains personal data under the GDPR.
ReadHow do you measure whether your RAG system is improving?
Without a fixed evaluation set, improving a RAG system is largely guesswork. How to measure retrieval precision and recall, answer quality, latency and cost — and how to prevent regressions.
ReadMonitoring AI services: which signals actually matter?
An AI service can be technically "up" while users get slow, expensive or low-quality answers. Which signals beyond latency, cost, drift and hallucinations your monitoring actually needs to catch.
ReadChatbot disclosure: how do you say it without scaring visitors off?
A chatbot disclosure doesn't need to sound like a legal warning. Where the notice belongs, five example sentences from subtle to explicit, and when to be more explicit in healthcare, finance or with minors.
ReadWriting for Humans and Models: A Structure That Serves Both
Content that works well for people often works well for language models too — if you write with the same discipline. Why the answer should come first, when a list or table helps, and how to write content that stays easy to retrieve without sounding robotic.
ReadHow do you see what your agent did last night?
An agent that runs autonomously overnight should be traceable the next morning. What to log, how tracing with something like OpenTelemetry helps, and how to build a simple audit trail and dashboard.
ReadData residency: what does an 'EU region' really mean with a US cloud provider?
An EU cloud region does not automatically mean European control. What data storage location, access, the US CLOUD Act and cloud sovereignty really mean for your AI project.
ReadRate limits and quotas: how do you stop your service from grinding to a halt?
Rate limits and quotas can slow down or interrupt AI services without warning. Retries, queues, model routing, budget guards and monitoring together turn temporary scarcity into controlled degradation instead of an outage.
ReadAI for Municipalities: Making Policy Documents Searchable
Policy papers, council records, permit files and local regulations become searchable by meaning instead of just keywords with RAG, with citations back to the original document. Why the Woo and data sovereignty matter, and when an application can qualify as high-risk under the AI Act.
ReadWhen Should an AI Assistant Say 'I Don't Know'?
An AI assistant that never refuses is predictably unreliable. How relevance thresholds, missing-context detection and citation verification let a RAG system refuse exactly when it should.
ReadWhy Does Your FAQ Page Rank Worse Than One Good Question Per Page?
A long FAQ page makes several topics compete for attention, while search and retrieval systems often process content in smaller passages. When does a question deserve its own knowledge-base page, and when does it belong in the FAQ?
ReadPrompt injection: how a single email can hijack your agent
An AI agent that reads email and takes action can be manipulated by text inside that email — no password, no hack required. What indirect prompt injection is, and how least privilege and human-in-the-loop limit the damage.
ReadWhat is a DPIA and when do you need one for AI?
You need a DPIA for an AI system when its processing of personal data is likely to result in a high risk to individuals. AI itself is not the legal trigger — the combination of data, purpose, scale and consequences is.
ReadChoosing embeddings: which model understands Dutch best?
There is no embedding model that is objectively "best for Dutch". E5-NL, Qwen3 Embedding, Jina Embeddings v5, BGE-M3 and multilingual-e5 are candidates — your own retrieval test should decide the winner.
ReadCaching for AI: which answers are safe to reuse?
AI responses are safest to reuse when the same request, under the same conditions, should produce the same valid result. Time-sensitive, personalised or creative answers usually aren't — and semantic caching has its own risks.
ReadAI in healthcare: why on-prem is almost always the answer
Health data is a special category of personal data under GDPR. That's why on-prem or a tightly controlled private environment is usually the most defensible architecture for AI working with patient records — not an absolute ban on cloud AI, but a much higher bar.
ReadAI literacy (Article 4): what does the law expect from your staff?
Article 4 of the AI Act requires providers and deployers to take measures supporting AI literacy among staff — proportionate to role and risk, with no mandatory certificate. In force since 2 February 2025, amended in 2026.
ReadWhich AI crawlers visit your site — and how do you spot them in your logs?
GPTBot, ClaudeBot, PerplexityBot and more do not all do the same thing: some gather training data, some build a search index, some fetch a page live at a user's request. How to filter and verify them in your logs.
ReadHow do you give an AI agent safe access to your files?
Keep the scope as small as possible: an explicit allowlist instead of a denylist, separate read and write permissions, backups before every mutation, and a tool layer that enforces the boundary outside the model.
ReadAre you allowed to run customer data through ChatGPT?
Under GDPR it's allowed under conditions: a lawful basis, data minimisation, and — when OpenAI acts as a processor — a data processing agreement. But a personal ChatGPT account is not the same as ChatGPT Business, Enterprise or the API.
ReadHow many documents do you need before RAG is worth it?
There is no minimum. RAG earns its complexity once documents no longer fit a single context, content changes often, many users need to search, or answers need citations — not at a fixed file count.
ReadFallback chains: what does your system do when the provider goes down?
A fallback chain combines alternative AI providers or models with health checks, timeouts, retries and circuit breakers. Downtime is not the only failure mode — measurable quality degradation counts too.
ReadAI for accountants: where's the upside, and where's the risk?
The upside lies in faster document processing, journal-entry suggestions and periodic close support. The risk lies in hallucinated figures, tax interpretation, GDPR and liability.
ReadWhat is a high-risk AI system — and are you running one?
Not every advanced AI system is high-risk under the EU AI Act, and not every simple one is exempt. Article 6 and Annex III decide it — along with the deadlines the Digital Omnibus pushed back in mid-2026.
ReadShould you block AI crawlers or let them in?
Blocking every AI crawler is usually too blunt. GPTBot, ClaudeBot, PerplexityBot, Google-Extended and CCBot each serve a different purpose — how to configure robots.txt for training versus visibility.
Readn8n or code: when is a workflow tool enough?
Where workflow tools are strong, when custom code fits better, and why combining n8n with code is often the strongest architecture for AI automation.
ReadArticle 50 explained: when do you have to disclose that it's AI?
Article 50 does not require every use of AI to be disclosed. The transparency duty applies specifically to chatbots, AI-generated content, deepfakes and emotion recognition — in force since 2 August 2026.
ReadDo You Need to Label AI-Generated Content?
The AI Act does not require a blanket visible label on all AI content. Article 50 distinguishes between technical marking, deepfakes and AI text on matters of public interest.
ReadModel routing: why not every request should go to the most expensive model
Not every AI task needs the biggest model. How to route on task complexity, latency, cost and reliability — with classifiers, rules, fallbacks and cost ceilings.
ReadCan AI search case law without making things up?
A language model without source grounding can produce convincing but non-existent judgments and ECLI numbers. How RAG, mandatory grounding and a link to the actual judgment reduce that risk.
ReadOllama, vLLM or llama.cpp: which runtime fits your situation?
llama.cpp is the C/C++ inference engine, Ollama the user-friendly layer around it for local experimentation, and vLLM the production-serving engine for GPUs with many concurrent users. Which one fits your workload.
ReadHow do ChatGPT, Perplexity and Gemini decide which source to cite?
Ranking well in Google is not the same as being cited in an AI answer. How ChatGPT Search, Perplexity and Gemini retrieve, assess and link sources to specific claims — and what that means for GEO.
ReadWhat is MCP (Model Context Protocol) and why is it changing agents?
The open protocol that lets AI agents connect to tools, data and systems in a standardized way. How it relates to APIs, function calling and RAG, and what it means for security and on-premises AI.
ReadWhat hardware do you need to run a language model locally?
RAM, VRAM, quantization and storage determine which LLMs you can run locally. Practical memory rules for 7B to 70B+ models on CPUs, GPUs and Apple Silicon.
ReadWhat is reranking and when do you need it?
Reranking is the second stage in a RAG pipeline that reorders candidate documents by relevance using a cross-encoder. When does it actually add value, and when is it unnecessary complexity?
ReadChunking explained: how do you split a document without breaking its meaning?
Good chunking determines what your RAG system can retrieve in the first place. Why chunking goes wrong, how to choose chunk size and overlap, and how to chunk PDFs, tables and code differently.
ReadWhat does AI really cost? From API token to your own server
APIs bill by the token, a server you own bills in purchase price, electricity and upkeep. What a million tokens actually costs at Anthropic and OpenAI, when owned hardware pays for itself, and the hidden line items that inflate the bill.
ReadAI in legal practice: what can a law firm actually use it for today?
Case law and legislative research, contract analysis, case-file search and draft correspondence already work — provided the output stays verifiable. Why hallucination is the core risk, and what RAG with source-grounded citation fixes.
ReadThe EU AI Act for SMEs: what do you need to have in place right now?
Since 2 August 2026 the transparency rules apply and enforcement has begun. The high-risk system rules have been postponed to 2027/2028 — what that concretely means for SMEs.
ReadFrom a score of 36 to 85+: what actually raises an agent-readability score
An online store scored 36 on AI readability and climbed to 85+ without changing a single line in the CMS. Which fixes made the difference, and why they shipped through an edge worker.
ReadMeasure your AI visibility: is it you in the answer, or your competitor?
A ranking in Google no longer says anything about whether ChatGPT, Perplexity or Gemini mention your business. How to measure, yourself, whether you show up in AI answers — and what to do when the answer is no.
ReadRAG: from demo to production
A demo answers ten questions well. Production has to answer ten thousand, including the ones nobody anticipated. What breaks along the way, and what it takes to hold up.
ReadAI agents with guardrails: letting a system act without losing control
The brain may only propose, the hands may only act within limits set in advance. On whitelists, deny-lists, cooldowns and the approval card.
ReadKeeping AI costs under control without crippling your system
Most AI bills grow because nobody measures per call. On routing to the cheapest model that fits, caching, and knowing the cost of every request.
ReadGetting found by AI assistants: what actually works
Which crawlers matter, what robots.txt and llms.txt do for them, and the checks that took one site from 36 to 85+.
ReadSchema.org for AI: which structured data do assistants actually understand?
The five types that actually pay off, how to tie them into a single entity with @id, and the four mistakes that turn markup against you.
Readllms.txt: the new robots.txt — what it is and whether you need one
A proposed file in your site root that tells AI systems in plain text what your site is and where things live. Origin, structure, and whether your site needs one.
ReadMulti-agent orchestration: how do you get several AI agents to work together without chaos?
Adding more agents rarely fixes the problem — it moves it to the coordination between them. On one shared playbook, fixed roles and one log as the single source of truth.
ReadRAG explained: how to build an AI that doesn't lie
Retrieval, context, generation and citation verification — the four ingredients that separate a RAG demo from a system you can actually trust.
ReadOn-prem AI: when is it worth the investment?
Cloud is easy, until your bill and your DPO start paying attention. An honest trade-off.
ReadWhy your AI agents start over every session — and how to fix it
The most expensive problem in agent work is memory loss. On the memory layer that turns separate sessions into one continuous brain.
ReadGEO: how to get cited by ChatGPT and Gemini
SEO got you into Google. GEO gets you into the answer the user reads next.
ReadTraining your own model? Start with RAG.
Why "our own LLM" is in practice usually RAG plus light fine-tuning — and that’s good news.
ReadAI and GDPR: what's allowed, what isn't, and how to get it right
Using AI with personal data is allowed under the GDPR — provided you have a legal basis, apply data minimisation, and know where the data goes. From legal basis to DPIA, and where the EU AI Act adds requirements.
ReadAI agents for SMEs: what actually works today (and what doesn't yet)
Searching documents and fixed workflows already work reliably. Fully autonomous decision-making doesn't yet. What works, what doesn't, and how an SME gets started.
ReadAir-gapped AI: can a language model run without the internet?
Yes, it can — but the question is whether your threat model justifies that level of isolation. What it takes technically, and why most businesses only need on-prem.
ReadLocal models in 2026: Llama, Qwen and Gemma compared fairly
Licensing, sizes and context of Llama 4, Qwen 3.5/3.6 and Gemma 4, laid out plainly — and why "which one is best" is the wrong question in a field that shifts monthly.
ReadA question that should be answered here?
The articles here describe what the lab systems actually run into — every showcase explains the technique behind it.