Certificate programme
AI and automation
In almost every organisation, a considerable share of working time goes into tasks that add no value: copying data from a form into a spreadsheet, renaming and filing documents, sending reminder emails, reformatting a report, compiling the same figures every week. These tasks are tedious, error-prone and almost all of them can be automated.
- Duration
- 5 weeks, 8 sessions, 40 hours
- Format
- In person or online
- Credential
- Training certificate
Tuition140,000 XOF
By the end of the programme, you will be able to
- Understand what a large language model is, what it can really do and the errors it predictably makes
- Write structured, repeatable prompts that produce usable output
- Obtain output in a structured format, ready for another tool to use
- Work from a corpus of internal documents and get answers that cite their sources
- Analyse a dataset with AI and verify every figure it produces
- Build an automation workflow with n8n: triggers, conditions, loops, error handling
- Automate an office task and call a language model through its API
- Design an agent or a conversational assistant, with its guard rails
- Write an AI usage charter and protect your organisation's data
- Put an automation into service and monitor it so that it keeps running
Who it is for
Target audience
The certificate is for anyone whose work involves repetitive tasks or producing content: project officers, executive assistants, administrative and finance managers, communications officers, monitoring and evaluation officers, human resources staff, entrepreneurs, consultants, teachers and IT staff.
Prerequisites
Three requirements:
- Be comfortable with a computer at the level of files, browser, email and a spreadsheet
- Have a laptop and a work or personal email address usable during the sessions
- Come with at least two real repetitive tasks from your own job, which will serve as the material for the exercises
No programming background is required. Participants who already code work on more advanced workflows during the application exercises, as the sessions are designed at two levels of difficulty.
Teaching method
The certificate runs over five weeks: two sessions a week in weeks 1 to 3, then one a week in weeks 4 and 5 — eight five-hour sessions and 40 supervised hours. Sessions are held on Saturday and Sunday from 8.30 a.m. to 1.30 p.m., in person or online and live, as each participant prefers, at the same price. Personal work is estimated at two or three hours a week, and three or four during the project weeks.
The format is hybrid: before each session, participants watch at their own pace about an hour and a quarter of video capsules, given to them on enrolment. Theory and demonstrations go there; the sessions are spent practising, on the participant's own data and tasks. Each session also has a "going further" section covered in the course material.
The course teaches two skills together, because they are only worth having combined: steering a model so that it returns reliable, usable output, and building the automation chain that triggers that processing without anyone intervening. It ends with a real automation going live, chosen from the participant's own work, which keeps running after the course. That deliverable is what the certificate rests on. The cohort is limited to fifteen, and every project is supervised individually until it goes live.
Tools and accounts: every tool used has a free tier sufficient for the course and for ordinary use afterwards. The necessary accounts are created and configured during the first session. The credits for calls to paid models during the exercises are covered by Waaldé Impact for the whole course. You need a laptop with at least 4 GB of RAM, 8 GB preferred, an email address and a phone number for account verification, n8n installed locally, accounts on at least two generative AI assistants on their free tiers, and a Google or Microsoft online workspace.
Every participant leaves with:
- The complete course material in PDF, module by module
- The video capsules for each session, to keep for revision
- A library of more than a hundred ready-made prompts, sorted by profession
- Some twenty exported n8n workflows, ready to import and adapt
- A document assistant template and a conversational agent template
- A process mapping grid and a grid for costing the time saved
Detailed program
8 sessions · 40 h of teaching
Week 1 — Understanding and steering artificial intelligence
2 sessions · 10 h- Turn five vague requests into structured prompts: role, task, context, constraints, format
- Compare the outputs before and after, against a common scoring grid
- Create a specialised assistant and file its instructions in a personal library
- Identify the data that must never be sent to an outside service
- Exercise: turn five of your own requests into structured prompts and measure the gain in quality
- Going further, in the course material: context windows and the cost of tokens; a detailed survey of the models; step-by-step reasoning techniques
- Write, shorten and adapt a text to an audience, then produce a note or a set of minutes
- Summarise a long document and check the summary against its source
- Extract the information from a hand-filled form into a table
- Classify and code open-ended survey answers into themes
- Exercise: build a processing chain that turns fifty open-ended answers into a coded table
- Going further, in the course material: terms of reference and pitch documents; local administrative French; translation and adaptation
Week 2 — AI applied to the organisation's data and documents
2 sessions · 10 h- Have a complex spreadsheet formula written, explained and checked
- Clean and recode a real dataset with a model's help
- Have a processing script generated and run, without knowing how to program at the start
- Produce a reporting table and the text that interprets it
- Exercise: have a real file processed, then verify every figure produced
- Going further, in the course material: annotated charts; spotting anomalies in a dataset; quality checks
- Prepare a real corpus: formats, chunking, cleaning and metadata
- Build a document assistant that answers while citing its sources
- Test a dozen questions and spot the invented answers
- Build the same chain without code, then with n8n
- Exercise: build an assistant that queries your organisation's procedures or reports
- Going further, in the course material: document embeddings in detail; hosting a sensitive corpus locally
Week 3 — Automating processes
2 sessions · 10 h- Map a real process in your department, step by step
- Install n8n locally and build a first workflow: trigger, processing, action
- Add a condition, a loop over a list and a branch
- Handle an error: retries, fallback workflow and execution log
- Exercise: build a six-step workflow that includes a call to a language model
- Going further, in the course material: Make, Zapier, Power Automate and Apps Script compared; overnight batch processing
- Automate the mailbox: sorting, extracting attachments, chasing replies
- Connect a collection form to a database and to a notification
- Call a model from n8n, test the call with a dedicated tool, then read the JSON response
- Compare two models on the same task and work out the unit cost
- Exercise: put an office automation into service, from the form to the distributed report
- Going further, in the course material: document mail-merge; Google Apps Script; the limits of free Power Automate; open models running locally
Week 4 — Agents, governance and the project
1 sessions · 5 h- Build a simple n8n agent: instructions, memory and two tools — spreadsheet and mailbox
- Set the guard rails: scope, human validation, irreversible actions forbidden
- Write an AI usage charter for your organisation, clause by clause
- Choose where your workflow will run: local machine, internal server or online service
- Scope your project: process chosen, expected result, success criteria, sign-off
- Exercise: write your project's scoping sheet, reviewed by the trainer at the end of the session
- Going further, in the course material: deploying to WhatsApp or a website; the running cost of an agent; how to leave a provider
Week 5 — Project, defence and certificates
1 sessions · 5 h- Build the chosen automation with one-to-one support from the trainer
- Test on real cases, handle the edge cases, schedule the runs and set up the alerts
- Write the operating documentation for the workflow
- Defend it in ten minutes, plus five minutes of questions
- Exercise: demonstrate the workflow live in service, then receive your certificate
- Going further, in the course material: peer review of workflows between participants; where to go next in Python programming and data science
Assessment and certification
The AI and automation certificate is awarded on an admission average out of 20, made up of three components:
- The certification exam (50%) — 25 questions drawn at random from a bank of more than eighty, in 75 minutes. Two attempts are allowed, seven days apart, and the better one counts.
- The deployed automation (30%) — presented in the eighth session.
- Attendance (20%) — recorded session by session. An absence announced at least three days in advance counts as half; an unannounced absence does not count.
The admission average is 12 out of 20. A mark below 8 out of 20 in the exam is eliminatory: neither the project nor attendance can make up for it. As soon as the average is reached, the certificate is issued automatically and becomes available in the participant's account.
The certificate is issued by Waaldé Impact, signed by the trainer, and states the course title, the 40 hours, the period, the list of modules completed and the subject of the automation presented. Each certificate carries a unique number and a verification code.
Participants who do not reach the average receive a certificate of attendance. They may retake the exam and present their automation with the following cohort, at no extra cost.
Participants also receive:
- The complete course material in PDF, module by module
- A library of over a hundred ready-to-use prompts, organised by profession
- Around twenty exported n8n workflows, ready to import and adapt
- A document assistant template and a chatbot template
- A process mapping grid and a time-saving costing grid
- A template charter for the use of artificial intelligence in organisations
- A workflow documentation sheet and a pre-launch checklist
Upcoming sessions
Next dates being prepared
Leave your email: we will let you know as soon as registration opens.
Frequently asked questions
140,000 XOF per participant. Training for a team or an organisation is quoted on request.
5 weeks, 8 sessions, 40 hours.
Yes: you can attend onsite or online, as you prefer.
Three requirements: be comfortable with a computer at the level of files, browser, email and a spreadsheet ; have a laptop and a work or personal email address usable during the sessions ; come with at least two real repetitive tasks from your own job, which will serve as the material for the exercises ; no programming background is required. Participants who already code work on more advanced workflows during the application exercises, as the sessions are designed at two levels of difficulty.
Yes: participants who meet the completion requirements receive a Waaldé Impact certificate with a unique number that employers can verify online.
Fill in the online enrolment request: no payment is taken on the site. The firm reviews your application, then contacts you to confirm your place and the payment terms. No session is scheduled yet: leave your email on this page to be told when registration opens.
Join the next cohort
Cohorts are deliberately small to guarantee genuine individual support. Reserve your place or ask us your questions.