The task
You are kicking off a project and need a plan stakeholders can react to in 48 hours. Not a Gantt chart, but a one-page plan that names the milestones, the dependencies, the risks, and what “done” looks like for each milestone. The risk is producing a plan that reads well in a meeting but breaks the first time reality intervenes. The job is honest scoping, not impressive scoping.
When AI helps — and when it does not
AI is excellent at structure: enumerating milestones, surfacing dependencies, listing risk categories (technical, organisational, market, regulatory). It is poor at estimating effort and at knowing your organisation’s actual constraints (who has bandwidth, who is on holiday, which team owes you). Plug those in before asking AI to estimate.
What to feed the AI
- Goal: what success looks like in one sentence
- Deadline (hard or soft, and why)
- Budget: money, headcount, calendar time
- Team: roles, seniority, time allocation %
- Known constraints (technical, regulatory, dependencies on other teams)
- What you have already decided is out of scope
- Past similar projects: what went well, what went wrong
Copy-ready prompt
Draft a project plan I can present in 2 days.
Goal (one sentence): <line>
Deadline: <date, hard or soft>
Budget: <money / headcount / calendar>
Team: <roles, seniority, allocation %>
Known constraints: <technical, regulatory, cross-team>
Out of scope: <list>
Past similar projects (wins and losses): <notes>
Return:
1. Milestones (4-7), each with: name, success criterion (testable), owner, due date, dependencies
2. Critical path — the longest dependency chain
3. Risk register: top 5 risks, each with probability (L/M/H), impact (L/M/H), mitigation
4. A "what could blow this up" section — 3 most likely failure modes
5. Decision log: 3 decisions that need to be made in the first week, with owner
6. Success metrics: 2-3 leading + 1 lagging, with definitions
7. Communication cadence: who hears what, how often
Be honest about estimates. If a milestone has uncertainty > 50%, mark it [UNCERTAIN: needs spike].For high-uncertainty projects: “Add a Week-2 reassessment built into the plan — explicit Go / No-Go criteria.”
Recommended output structure
A one-page table: milestone / owner / due / dependencies / success / done?. Below it, the risk register as a separate table, decision log as a list, communication cadence as one paragraph. Avoid Gantt-chart formatting in the draft; it hides logic behind shapes.
How to check the output is usable
- Every milestone has a testable success criterion (“API deployed to staging passing all integration tests”), not a fuzzy one (“API ready”)
- The critical path is named, not implied
- Risks are real to your project, not boilerplate
- The communication cadence is realistic (daily standup plus weekly exec read-out, not three weekly meetings)
- Out-of-scope items do not sneak back as requirements
Common mistakes
- No risks listed: every plan without risks is a wishful plan
- Milestones with no success criteria, so “done” becomes argument fodder
- Letting AI estimate effort without grounding (engineering effort needs an engineer)
- Confusing milestones with tasks (milestones are observable outcomes, not to-dos)
- No decision log, so projects stall on undeclared decisions
- One owner per milestone is missing, and accountability dissolves
Practical depth notes
For AI Project Plan Draft: Milestones, Dependencies, Risks, Success, the difference between a usable AI result and a generic one is the input packet. Give the model the audience, the current draft or raw material, the desired format, the decision you need to make, and two examples of what good and bad output look like. Ask it to preserve facts first, then improve structure or wording second.
After the first response, do a separate review pass. Look for missing constraints, invented details, weak calls to action, and language that sounds plausible but does not match the real situation. The best final output should be easy to use immediately: clear owner, clear next step, and no hidden assumption that someone else has to untangle. A stronger version of this workflow also defines the handoff. Decide who will use the output, what they should do next, and what information would make them reject it. If the deliverable is copy, test whether it has a single clear action. If it is analysis, test whether it separates observation from recommendation. If it is planning, test whether dates, owners, and tradeoffs are explicit enough for someone else to execute.
FAQ
- PRD or project plan? PRD describes what you are building; project plan describes how you will deliver it. See PRD draft for the PRD side.
- What about agile vs waterfall? Plan iterations vs phases differently, but milestones still apply.
- How often should I re-plan? Weekly soft check, milestone-completion hard check.
Related
- PRD draft: product spec that precedes the plan
- User story writing: break milestones into user stories
- Feature prioritisation: choose which milestones go in
- Roadmap planning AI: multi-project view
- Launch checklist: the final milestone
- AI task breakdown tutorial: break a milestone into tasks
- Project Planning Prompts: From Goal to Sprint Plan
Tags: #Workflow #Productivity #PRD