Projects

Projects you're working on

Projects are the medium-term containers where work, decisions, and context accumulate, and AI needs to understand them to help with anything inside them.

A project is more than a name and a deadline. It is a body of accumulated context: the decisions already made, the constraints in play, the history of what was tried and discarded, the relationships involved. A tool that does not know that context is working from the most recent file it can see, not from the full picture.

When you brief an AI on a project, the question is not just what the project is but what context it needs to understand the current task. That usually means a short summary of where things stand, what has been decided, and what is still open. A tool reading that summary can contribute much more usefully than one reading only the task.

Projects also change. What was true three weeks ago may not be true now. Keeping project context current is a readiness habit: the more your project summaries reflect the actual state of things, the more useful any AI help will be.

Make it visibleWrite a current-state summary for your most active project: what the goal is, what has been decided, what is in progress, and what is still open. Keep it to a short paragraph and update it after each significant development. Use it as the context block whenever you bring AI into that project.

Why AI needs this

Each part of your work matters to AI in a specific way. Some of it is context a tool needs before it can help, some of it is work a tool can take on, and some of it is judgment that should stay with you.

Accumulated decisions as context

Every project carries a history of decisions: what was ruled out, why the approach is the approach. AI needs that history to avoid suggesting things that were already tried and rejected.

Where the project stands now

A current project summary (what is done, what is in progress, what is blocked) lets a tool understand which tasks are live and which questions are actually open.

Relationships and dependencies

Projects involve people, handoffs, and dependencies. A tool helping with one part needs to know what it feeds into and who else is involved or it will optimize in isolation.

Scope and constraints

Budget, timeline, and scope shape what is possible. Without knowing the constraints, an AI will often suggest the ideal solution rather than the workable one.

Questions to explore

Use these on your own or in a group. There are no right answers, only better conversations.

If you had to brief a new team member on your most important current project in three minutes, what would you say?
What decisions have already been made in this project that a newcomer would need to know not to reopen?
Which projects are well-documented enough that someone else could pick them up, and which live mostly in your head?
Where do projects stall in your team, and is that stall visible in the way the work is described?
What would a good project summary include that your current project notes do not?

Readiness traps

Project briefs written for kickoffs go stale quickly. What an AI reads should reflect where the project is now, not where it was when it started.
The most important context in a project is often what was ruled out and why. If that is not captured, a tool will rediscover and propose the same discarded ideas.
Projects with many stakeholders tend to have many private interpretations of what the project is for. Aligning on a shared description before giving AI access saves a lot of corrective work later.