# AI Practitioner > An online, self-paced AI course from ARFA, the TIBLOGICS AI Academy. Intermediate level, about 19.5 hours, in English and French, with a verifiable certificate. Web page: https://tiblogics.com/learning-box/ai-practitioner ยท All tracks: https://tiblogics.com/learning-box.md ## Key facts - Level: Intermediate - Time: about 19.5 hours including hands-on work (6 modules, 25 lessons, 6 labs); self-paced, no deadline - Price: $487 one time for lifetime access to this track, or every track for $89 a month (cancel anytime) - Certificate: TIBLOGICS Certified AI Practitioner, with a public verification page - Languages: English and French ## About You already use AI tools. This level makes you reliable with them. You will start by mapping your own work as a system, because where AI helps depends on where the real bottleneck is. Then you will learn to write prompts that hold up every time, work accurately with your own documents and data, check quality at scale instead of trusting a single good answer, automate repetitive work with a person still in the loop, and do all of it responsibly. Every module ends in a hands-on lab done inside the platform: prompts run against a real model, a summary with planted errors to catch, and your own workflow mapped and redesigned. The capstone is a real workflow of yours, rebuilt with AI and reviewed by a person. Skills this track builds also appear in AI-at-work courses and entry-level AI practitioner certifications. This track is independent: it is not affiliated with any vendor and is not official exam preparation. Who it is for: People who already use AI tools for everyday tasks and want to use them reliably in their actual job: analysts, managers, operators, consultants, small business owners. ## What you will be able to do - Map a workflow as a system and find where AI genuinely helps - Write reusable prompts that give consistent, structured results - Summarise and question your own documents and data without losing accuracy - Test AI output on a set of cases and decide what needs human review - Design an automation with an AI step and a human checkpoint - Handle confidential data, prompt injection and bias responsibly ## Curriculum ### Module 1: Seeing Your Work as a System Map one real workflow as a system, find the step that actually limits it, anticipate the knock-on effects of adding AI, and build in feedback so you know whether it is working. - Map your workflow (30 min) - Find the real bottleneck (25 min) - Knock-on effects of AI at work (25 min) - Build feedback into the process (25 min) - Module quiz ### Module 2: Prompts That Hold Up Write prompts that give dependable results on new inputs: a clear structure, well-chosen examples, checkable output, and a disciplined way to test and save what works. - Anatomy of a reliable prompt (30 min) - Show, don't tell: using examples (25 min) - Asking for structure (25 min) - Iterating like an engineer (30 min) - Module quiz ### Module 3: Working With Your Own Material Use AI on your own documents and data without losing what matters: purposeful summaries, checked calculations, answers grounded in sources, and long documents handled in stages. - Summarising without losing what matters (25 min) - Asking questions of spreadsheets and data (30 min) - Grounding answers in your sources (25 min) - Long documents and context limits (30 min) - Module quiz ### Module 4: Checking Quality at Scale Define what good looks like before you prompt, test on a small set of real cases, catch confident errors, and put human review where the risk is. - Write the checklist before the prompt (25 min) - Test on ten cases, not one (30 min) - Catching confident errors (30 min) - Deciding what needs a human (25 min) - Module quiz ### Module 5: Automating Repetitive Work Build simple automations from triggers, steps and actions, put AI only where judgement on language is needed, keep a human in the loop, and plan for failure. - How automation works: triggers, steps and actions (25 min) - Where an AI step belongs (25 min) - Keeping a human in the loop (25 min) - When automations fail (30 min) - Module quiz ### Module 6: Using AI Responsibly at Work Keep confidential data out of the wrong tools, guard against prompt injection, be honest about AI use, and check everyday decisions for bias. - Confidential data and what to keep out (25 min) - Prompt injection, explained for non-engineers (25 min) - Being honest about AI use (20 min) - Bias and fairness in everyday decisions (30 min) - Before you switch it on: security doors for AI automations (25 min) - Module quiz ## How you are assessed - A quiz after each module (80% to pass, retakes allowed). - A timed final exam: 35 questions in 60 minutes, 75% to pass, 90% for distinction, 3 attempts. - A capstone project reviewed by a person against a published rubric (70% to pass). - Each certificate has a public page at https://tiblogics.com/certificates/ that anyone can open to check it.