AI for Project Managers: the complet guide

Use AI to generate a complete project charter you can defend in front of a sponsor or a steering committee. The lesson covers what a charter is, the document that authorizes the project and gives the project manager a mandate, and the questions it must answer: purpose, in-scope and out-of-scope items, stakeholders and decision authority, constraints, measurable success criteria. It presents a three-pass method (a complete structure from a charter template, section-by-section enrichment with your real figures, then the AI as devil's advocate playing a skeptical sponsor), followed by the essential checks on dates, names and budget.

Learn the context, role, task, format method to write effective project management prompts and get documents you can actually use instead of generic answers. Concrete examples show the difference between a vague request and a complete prompt, for instance to identify the risks of an e-commerce website redesign in table format. You'll also see how to follow up with the AI in the same conversation when the answer stays vague, and how to ask it for several distinct scenarios, such as three approaches to rolling out a tool, to avoid falling for the first idea.

A six-step guided exercise to write the charter of your current project with AI: an initial prompt using the context, role, task, format method, the expected sections (objectives, scope, stakeholders, constraints, success criteria, budget and timeline), a first review to spot what is generic or invented, the three-pass method, the devil's advocate, then a final check. You'll also see how to save time with your AI tool's voice input. The result is a solid project charter that you'll reuse throughout the rest of the course.

Write SMART objectives and a quantified business case with AI, without letting it invent your numbers. The lesson reviews the five SMART criteria and shows how to turn a vague objective like "improve customer satisfaction" into a measurable, time-bound goal. It then explains what a business case is (cost, gain or avoided loss, payback period) and how to build one with AI from your own data, requiring that any missing data be flagged as an assumption to validate.

Generate a complete WBS (Work Breakdown Structure) with AI from your project's objective. The lesson explains the difference between a WBS and a schedule, the levels of decomposition, and the rule of a task that one person can complete in less than a week. It presents a two-step method, a broad structure first, then a detailed breakdown work package by work package, illustrated by a product launch where forgotten tasks come to light, before the essential review of each task's dependencies and owners.

Build a realistic project schedule with AI and identify the critical path. The lesson explains task dependencies (finish-to-start, start-to-start, finish-to-finish), the critical path and float, with a simple numerical example. You'll see how to turn your WBS into a schedule in table format, ask the AI for the critical path and the float of each task, and check that you've given it your team's real availability constraints.

A six-step guided exercise to break down a vague task from your project, such as "prepare the rollout", into actionable subtasks with AI. You apply the rule of one subtask per person per week, each with a concrete, verifiable deliverable, then the deliverable test: would a team member know exactly when they're done? The exercise ends by identifying the subtask most exposed to delays in your real context.

Understand what a project risk is, an uncertain event that affects the project, either a threat or an opportunity, and identify every risk on your project with AI. The lesson shows why identifying risks on your own is limited by your own experience, and how to ask AI for a list of risks sorted by category: technical, people, financial, regulatory, external. It also stresses looking for opportunities and for risks tied to the organization's internal politics, which the project manager must always add personally.

Assess and prioritize project risks with AI using probability, impact and the probability and impact matrix. The lesson explains the two assessment axes, how to read the matrix by red, amber and green zones, and how to ask AI for a justified assessment of each risk. It also shows why you should manually correct a generic assessment that doesn't reflect the reality on the ground.

Build a complete risk register with AI and choose the right response for each risk: avoid, mitigate, transfer or accept. You'll see how to ask for a table with risk, category, probability, impact, response, mitigation action and likely owner, ready to present to a steering committee. An example shows how to replace a vague mitigation like "choose the right supplier" with a concrete, verifiable action, with a clause, a figure and a deadline.

A guided exercise to produce your current project's risk register with AI, applying everything from the risk management module. Six steps: broad identification by category including opportunities, manually adding the risks specific to your organization, assessing probability and impact, spotting the red zone of the matrix, choosing responses and building the complete register, then the vague wording test on every mitigation action.

Use AI to prepare a requirements elicitation interview guide that misses nothing. The lesson distinguishes the solution a stakeholder asks for from the real need behind it. It shows how to generate fifteen interview questions covering the current process, pain points and non-negotiable constraints, then add a set of questions on edge cases, while keeping active listening at the center of the interview.

Turn raw interview notes into a structured requirements document with AI. The lesson explains the difference between functional and non-functional requirements, and how to rephrase a vague requirement like "the system must be fast" into a measurable, verifiable criterion. It stresses a line-by-line comparison between your notes and the generated document, to recover critical requirements that were mentioned briefly and diluted by the AI.

A six-step guided exercise to convert your own meeting notes into a usable requirements document with AI. You structure your notes into functional and non-functional requirements, apply the measurable criterion test, compare the result against your source notes to spot omissions, fill in the gaps by hand and check that no category is empty. The resulting document is ready to be validated by the stakeholder concerned.

Prioritize project requirements with the MoSCoW method (Must have, Should have, Could have, Won't have) assisted by AI. The lesson details the four levels, explains why a list where everything is a Must have is useless, and how to require a justification for every ranking the AI proposes, so you can spot the bias caused by the length of the source notes. It also shows how to use AI to settle a disagreement between stakeholders by reasoning on concrete impact, while the final decision stays human.

Estimate a project's workload and resource needs with AI. The lesson distinguishes workload from capacity and explains over-allocation, the most common mistake in a resource plan built in a hurry. You'll see how to give the AI your WBS and your team's availability to calculate each person's weekly workload and flag every overloaded week, while keeping control over duration estimates.

Assign project tasks based on your team's skills and availability with a RACI matrix generated by AI. The lesson explains the Responsible, Accountable, Consulted and Informed roles, and the classic mistake of naming several Accountable people on the same task. It shows how to check the matrix proposed by the AI against each person's real authority, then share it with the whole team to prevent conflicts over responsibility.

Prepare a difficult team management conversation with the help of AI, without ever handing it the conversation itself. The lesson offers a three-part structure (the observed fact, the impact on the project, a clear expectation going forward) and shows how to ask AI to anticipate the person's possible reactions. You'll also see the confidentiality precautions to take and why you should make the structure your own rather than recite a generated script.

A six-step guided exercise to build your team's resource plan and RACI matrix with AI. You gather each person's real availability, generate the weekly workload, fix over-allocations without pushing a critical task out of its float, then build a RACI matrix with a single Accountable per task, checked against the actual reporting lines. You leave with two documents ready for your next team meeting.

Build a project communication plan tailored to each stakeholder with AI. The lesson presents the four questions of a communication plan (message, format, frequency, channel) and the power and interest grid to calibrate each communication. You'll see how to generate this plan in table format from the stakeholders listed in your project charter, then review it against each person's real information needs.

Generate meeting minutes and a weekly project status report in a few minutes with AI. The lesson explains what a status report must show at a single glance and how to use RAG status (red, amber, green). You'll see how to structure meeting minutes into decisions, open issues and action items with an owner and a due date, and why you should give the AI the real gap between planned and actual to get honest reporting instead of a status that is always green.

Use AI to write a sponsor escalation and a follow-up email that get a quick reply. The lesson presents an effective structure: the problem and its urgency in the first line, a short context, then a single closed or limited-choice decision question. It also shows how to match the tone of the email to the real severity of the issue and why a follow-up should never reopen the debate with new arguments.

A six-step guided exercise to write your next project progress report with AI. You start from raw facts including at least one gap between planned and actual and a RAG status, generate the report, apply the honesty test, add a sponsor escalation with a closed question if needed, then check that every action item has an owner and a due date. The result is a progress report ready to send.

Use AI to build a quality checklist and testable acceptance criteria to avoid deliverables rejected at the last minute. The lesson distinguishes the quality checklist, which checks that the deliverable is built correctly, from acceptance criteria, which check that it meets the need, and introduces the definition of done. An example shows how to turn a subjective requirement like "the dashboard must be clear" into a verifiable criterion in the format "the deliverable is accepted if".

Why project closure is so often rushed, and what it must cover so the organization builds on what it has learned. The lesson details the four parts of a complete closure: final acceptance, lessons learned, handover and administrative closure. An example from a regulated industry shows the compliance risk created by a closure that was never formalized, and why AI makes this step much faster to complete.

Use AI to generate a complete, usable project final report and lessons learned. The lesson presents a three-question structure: what worked well, what caused problems and why, and the concrete corrective action for the next project. You'll see how to feed the AI with your status reports, risk register and meeting minutes, then review the document so it points to process-related causes rather than to people.

Prepare the handover and the administrative closure of a project with AI. The lesson shows how to generate a handover document with the deliverables and where to find them, the risks still active, the key contacts and the points to watch during the first three months. It also covers the administrative closure checklist (contracts and purchase orders, final budget compared with the business case, release of resources), to be checked with the people concerned, especially in finance and human resources.

A six-step guided exercise to write your project's closure report with AI: gather the project material, structure the lessons learned, apply the neutrality test, produce the handover document, generate the administrative closure checklist, then review the whole thing as if you were handing it to your successor. You get a complete closure report, ready to share.

Create a library of reusable prompts for every project management document, so you never start from scratch again. The lesson explains how to turn an effective prompt into a prompt template with placeholders in square brackets, and lists the seventeen prompt templates that cover the charter, planning, risks, requirements, resources, communication, quality and closure. It also gives tips to organize this library in the order of the project life cycle and keep it evolving.

Adapt AI output to your organization's templates and methodologies. The lesson shows how to give the AI an internal template that has already been approved so it follows its structure, and how to specify an Agile or hybrid methodology in your prompt templates. An example of numbering decisions in meeting minutes shows how to build a formatting constraint into your prompts for good, then test the adapted prompt on a different case.

A six-step guided exercise to build your personal library of five project management prompts. You choose the five documents most useful to your practice, turn them into prompt templates with square brackets, adapt them to your organization's templates and vocabulary, test one on your current project, then date the document so you keep it up to date.

Course conclusion: a recap of the skills you've gained to initiate, plan, manage risks, document requirements, manage resources, communicate and close a project with generative AI. The lesson offers a 30-day action plan in three stages: rework an existing document with your prompt library, apply the method to a document with real stakes, then update your prompts. It restates the core rule of the course: AI speeds up the production of your project documents, while verification, judgment and accountability remain the project manager's.