<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Semitora — Insights</title><description>Practical writing on AI implementations for business: RAG, AI agents, the EU AI Act and production costs — backed by first-party production data.</description><link>https://semitora.com/</link><language>en-GB</language><item><title>RAG for technical manuals: 7 controls before rollout</title><link>https://semitora.com/blog/en/rag-manufacturing-technical-documents/</link><guid isPermaLink="true">https://semitora.com/blog/en/rag-manufacturing-technical-documents/</guid><description>How to deploy RAG on manuals and service procedures: versions, permissions, citations, refusal, golden sets, approval and monitoring.</description><pubDate>Thu, 30 Jul 2026 00:00:00 GMT</pubDate></item><item><title>API, RPA, RAG or an AI agent: how to choose the right mechanism</title><link>https://semitora.com/blog/en/api-rpa-rag-or-ai-agent-how-to-choose/</link><guid isPermaLink="true">https://semitora.com/blog/en/api-rpa-rag-or-ai-agent-how-to-choose/</guid><description>A practical decision tree for choosing API automation, RPA, RAG, an AI agent or no-go based on process, data, risk, error cost and control before a PoC.</description><pubDate>Wed, 22 Jul 2026 00:00:00 GMT</pubDate></item><item><title>7 Evidence Pack items an auditor or board will ask for</title><link>https://semitora.com/blog/en/ai-act-evidence-pack-7-proof-items/</link><guid isPermaLink="true">https://semitora.com/blog/en/ai-act-evidence-pack-7-proof-items/</guid><description>Which evidence should exist before an AI system reaches production? Seven Evidence Pack items: owner, risk, golden set, evaluations, logs, handoff and rollback.</description><pubDate>Wed, 15 Jul 2026 00:00:00 GMT</pubDate></item><item><title>AI for handling email queries — a knowledge base, sources and human handoff</title><link>https://semitora.com/blog/en/ai-email-handling-knowledge-base-human-handoff/</link><guid isPermaLink="true">https://semitora.com/blog/en/ai-email-handling-knowledge-base-human-handoff/</guid><description>How to automate email query handling with RAG and an AI agent: classification, answers with a source, escalation rules and human handoff. Not an autonomous inbox, but consistent answers under control.</description><pubDate>Thu, 09 Jul 2026 00:00:00 GMT</pubDate></item><item><title>AI for B2B e-commerce and distribution — where it actually pays off fast</title><link>https://semitora.com/blog/en/ai-b2b-ecommerce-distribution-alerts-cross-sell/</link><guid isPermaLink="true">https://semitora.com/blog/en/ai-b2b-ecommerce-distribution-alerts-cross-sell/</guid><description>Where AI makes sense in wholesale and B2B distribution: pre-meeting customer briefs, order-drop alerts, cross-sell, price monitoring and a safe shop bot. Process, data and a first PoC.</description><pubDate>Thu, 09 Jul 2026 00:00:00 GMT</pubDate></item><item><title>How to choose an AI vendor in 2026: 12 questions before you sign</title><link>https://semitora.com/blog/en/how-to-choose-ai-vendor-2026/</link><guid isPermaLink="true">https://semitora.com/blog/en/how-to-choose-ai-vendor-2026/</guid><description>12 questions to ask an AI vendor before a PoC, RAG or agent: data, security, the AI Act, evaluations, code ownership and maintenance — with a strong-vs-weak signal matrix.</description><pubDate>Wed, 08 Jul 2026 00:00:00 GMT</pubDate></item><item><title>AI concierge for hotels — RAG and agents for guests, with clear limits</title><link>https://semitora.com/blog/en/ai-for-hotels-rag-concierge/</link><guid isPermaLink="true">https://semitora.com/blog/en/ai-for-hotels-rag-concierge/</guid><description>How a hotel can use RAG and AI agents for guest service: a multilingual concierge from your own materials, with clear limits and a realistic first PoC.</description><pubDate>Mon, 06 Jul 2026 00:00:00 GMT</pubDate></item><item><title>AI in insurance — RAG for claims documents, without deciding the payout</title><link>https://semitora.com/blog/en/ai-insurance-claims-rag/</link><guid isPermaLink="true">https://semitora.com/blog/en/ai-insurance-claims-rag/</guid><description>How to use RAG and AI agents to analyze claims documents, policies and procedures — with a source and an audit trail, without automating the payout decision.</description><pubDate>Mon, 06 Jul 2026 00:00:00 GMT</pubDate></item><item><title>A safe AI PoC in 30 days: a step-by-step implementation plan</title><link>https://semitora.com/blog/en/safe-ai-poc-30-days/</link><guid isPermaLink="true">https://semitora.com/blog/en/safe-ai-poc-30-days/</guid><description>An operational plan for a safe AI PoC in 30 days: pick a process, inventory shadow AI, prepare data, run a PoC on a real slice, evaluations, guardrails, logs and a go/no-go decision.</description><pubDate>Mon, 06 Jul 2026 00:00:00 GMT</pubDate></item><item><title>22 July and 2 August: who does Article 50 AI Act really apply to?</title><link>https://semitora.com/blog/en/labelling-chatbots-ai-content-article-50/</link><guid isPermaLink="true">https://semitora.com/blog/en/labelling-chatbots-ai-content-article-50/</guid><description>The 22 July initial-signatory deadline for the voluntary code has passed; Article 50 duties apply from 2 August. Check role and use case.</description><pubDate>Thu, 02 Jul 2026 00:00:00 GMT</pubDate></item><item><title>AI readiness audit: what exactly we check and what you get at the end</title><link>https://semitora.com/blog/en/ai-readiness-audit-what-we-check/</link><guid isPermaLink="true">https://semitora.com/blog/en/ai-readiness-audit-what-we-check/</guid><description>An AI readiness audit step by step: processes, data, shadow AI, AI Act risk classification and an implementation roadmap. What the final report contains.</description><pubDate>Thu, 02 Jul 2026 00:00:00 GMT</pubDate></item><item><title>The Digital Omnibus and the AI Act: what moved to 2027/2028, and what still applies from 2 August 2026</title><link>https://semitora.com/blog/en/digital-omnibus-ai-act-deadlines/</link><guid isPermaLink="true">https://semitora.com/blog/en/digital-omnibus-ai-act-deadlines/</guid><description>Regulation (EU) 2026/1744 is in force from 27 July 2026. Annex III moves to 2 Dec 2027 and Annex I to 2 Aug 2028; most AI Act dates stay.</description><pubDate>Thu, 02 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Data readiness for RAG — a checklist before you deploy AI</title><link>https://semitora.com/blog/en/data-readiness-for-rag/</link><guid isPermaLink="true">https://semitora.com/blog/en/data-readiness-for-rag/</guid><description>Before you build RAG, check the data: sources, permissions, document quality, freshness and tests. A data-readiness checklist before you deploy AI.</description><pubDate>Tue, 30 Jun 2026 00:00:00 GMT</pubDate></item><item><title>AI Act glossary — key terms in plain language</title><link>https://semitora.com/blog/en/ai-act-glossary-key-terms/</link><guid isPermaLink="true">https://semitora.com/blog/en/ai-act-glossary-key-terms/</guid><description>The AI Act in a nutshell: AI system, prohibited practices, high-risk, GPAI, provider vs deployer, human oversight, KRiBSI. Each term in one sentence.</description><pubDate>Mon, 29 Jun 2026 00:00:00 GMT</pubDate></item><item><title>How much does an AI agent or RAG system cost in Poland in 2026? Cheap chatbot vs production system</title><link>https://semitora.com/blog/en/ai-agent-rag-cost-2026/</link><guid isPermaLink="true">https://semitora.com/blog/en/ai-agent-rag-cost-2026/</guid><description>AI price lists start &quot;from a few thousand złoty&quot;, but a price without scope says nothing. Cheap chatbot vs a production RAG/agent system — what drives the cost.</description><pubDate>Mon, 29 Jun 2026 00:00:00 GMT</pubDate></item><item><title>AI Act risk classification — a step-by-step method</title><link>https://semitora.com/blog/en/ai-act-risk-classification-method/</link><guid isPermaLink="true">https://semitora.com/blog/en/ai-act-risk-classification-method/</guid><description>How to tell whether your AI system is prohibited, high-risk or minimal under the EU AI Act (Regulation 2024/1689). A step-by-step classification method.</description><pubDate>Mon, 29 Jun 2026 00:00:00 GMT</pubDate></item><item><title>AI governance for regulated industries — what it means in practice</title><link>https://semitora.com/blog/en/ai-governance-regulated-industries/</link><guid isPermaLink="true">https://semitora.com/blog/en/ai-governance-regulated-industries/</guid><description>AI governance is not a document but an ongoing function: owner, roles, human oversight, evaluations, data control and audit. What it means in finance, healthcare and manufacturing.</description><pubDate>Mon, 29 Jun 2026 00:00:00 GMT</pubDate></item><item><title>AI: buy off-the-shelf or build your own? A decision rubric</title><link>https://semitora.com/blog/en/ai-build-vs-buy-decision/</link><guid isPermaLink="true">https://semitora.com/blog/en/ai-build-vs-buy-decision/</guid><description>When to take a ready-made AI tool and when to build your own on your infrastructure. Five questions that settle build vs buy — and why the answer is often a mix.</description><pubDate>Mon, 29 Jun 2026 00:00:00 GMT</pubDate></item><item><title>AI on AWS compliant with GDPR and the AI Act</title><link>https://semitora.com/blog/en/ai-on-aws-architecture-for-compliance/</link><guid isPermaLink="true">https://semitora.com/blog/en/ai-on-aws-architecture-for-compliance/</guid><description>How to design AI on AWS with control over Regions, access, logs and retention. Bedrock, Guardrails, PrivateLink, CloudTrail and responsibility.</description><pubDate>Mon, 29 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Production-grade AI agents — how they differ from a chatbot, and how to keep control</title><link>https://semitora.com/blog/en/production-grade-ai-agents/</link><guid isPermaLink="true">https://semitora.com/blog/en/production-grade-ai-agents/</guid><description>A chatbot answers; an AI agent acts — it uses tools and reaches into your systems. With autonomy comes risk — how to build and supervise a production agent.</description><pubDate>Mon, 29 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Evaluating RAG — how do you know it answers accurately and from sources</title><link>https://semitora.com/blog/en/rag-evaluation-measuring-quality/</link><guid isPermaLink="true">https://semitora.com/blog/en/rag-evaluation-measuring-quality/</guid><description>How to measure RAG quality: retrieval relevance, answer groundedness, citation correctness and hallucination control. Five metrics and a method.</description><pubDate>Mon, 29 Jun 2026 00:00:00 GMT</pubDate></item><item><title>mojApteczka as proof: GenAI and RAG in healthcare from idea to production</title><link>https://semitora.com/blog/en/mojapteczka-genai-rag-healthcare/</link><guid isPermaLink="true">https://semitora.com/blog/en/mojapteczka-genai-rag-healthcare/</guid><description>How a production GenAI system was built in a high-stakes domain: RAG architecture, hallucination control, inference cost and GDPR plus AI Act compliance. Hard numbers from production.</description><pubDate>Thu, 25 Jun 2026 00:00:00 GMT</pubDate></item><item><title>AI grants in Poland 2026: FENG, Dig.IT and KFS without the bureaucratic noise</title><link>https://semitora.com/blog/en/ai-grants-2026/</link><guid isPermaLink="true">https://semitora.com/blog/en/ai-grants-2026/</guid><description>Got an AI project but the budget is blocking it? Three programmes — FENG / SMART Path, Dig.IT and KFS 2026 — which fits, what qualifies and what does not.</description><pubDate>Sun, 21 Jun 2026 00:00:00 GMT</pubDate></item><item><title>USD 0.0006 per AI scan: what GenAI really costs in production</title><link>https://semitora.com/blog/en/what-genai-really-costs-in-production/</link><guid isPermaLink="true">https://semitora.com/blog/en/what-genai-really-costs-in-production/</guid><description>We have our own production number: USD 0.0006 per AI scan. But inference cost is the tip — the real cost of GenAI sits before the model, not in it.</description><pubDate>Sun, 21 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Guardrails are not an AI policy. They are a technical layer you must test</title><link>https://semitora.com/blog/en/guardrails-are-not-ai-policy/</link><guid isPermaLink="true">https://semitora.com/blog/en/guardrails-are-not-ai-policy/</guid><description>Teams confuse AI policy with technical safeguards. Guardrails (e.g. AWS Bedrock Guardrails) help — but without tests, evals and an owner they are decoration.</description><pubDate>Sun, 21 Jun 2026 00:00:00 GMT</pubDate></item><item><title>RAG on company documents — when a chatbot starts answering from sources</title><link>https://semitora.com/blog/en/rag-on-company-documents/</link><guid isPermaLink="true">https://semitora.com/blog/en/rag-on-company-documents/</guid><description>What RAG is, how it connects AI to your company knowledge base, and how it limits hallucinations — with source citations, on AWS.</description><pubDate>Sun, 21 Jun 2026 00:00:00 GMT</pubDate></item><item><title>AI Act 2026 — a readiness checklist for the board</title><link>https://semitora.com/blog/en/ai-act-2026-readiness-checklist/</link><guid isPermaLink="true">https://semitora.com/blog/en/ai-act-2026-readiness-checklist/</guid><description>Regulation (EU) 2026/1744 is in force. Most AI Act provisions apply from 2 Aug 2026; full high-risk duties follow in 2027/2028. Board checklist.</description><pubDate>Thu, 28 May 2026 00:00:00 GMT</pubDate></item></channel></rss>