The Context Compact

Before you prompt, agree on the one page of truth the model is allowed to use.

AI fails teams less often from bad models than from missing context. Someone prompts with half the brief. Another person pastes last week's numbers. A third assumes the audience is the board when the real reader is a frontline manager. The draft looks sharp. The decision is wrong.

Next-gen leaders do not fix this with longer prompts. They fix it with a Context Compact: a short, shared page that states what is true, what is out of scope, and who the work is for — before anyone opens a chat window.

Why a compact beats a clever prompt

A clever prompt is private. A compact is shared. That difference matters.

When context lives only inside one person's head (or one chat thread):

  • two people get two different "truths" from the same tool
  • stale facts travel farther because they sound current
  • reviewers argue about taste when they should argue about premises
  • juniors learn to prompt faster instead of thinking clearer

The compact turns AI from a private assistant into a team instrument. Same facts. Same constraints. Same reader.

What goes on the one page

Keep it to one screen. If it needs a second page, you are writing a brief, not a compact.

1. Decision or deliverable

One sentence: what must this work produce or decide? Not "explore options." Name the artifact or the choice.

2. Audience and use

Who will read or act on this, and what will they do with it? Board, customer, ops lead, or internal draft — each needs a different voice and depth.

3. Hard facts (dated)

List the 5–7 facts the model may treat as true. Put a date next to each. Anything without a date is a guess wearing a suit.

4. Boundaries

What must AI not invent, soften, or expand? Pricing, legal claims, people data, unannounced strategy — write the fences before the model runs.

5. Success look

Two or three lines on what "good" looks like: length, tone, structure, and the one question the output must answer.

How to run it in ten minutes

Monday morning, or before any AI-heavy sprint:

  1. Owner drafts the compact in a shared doc (not a private chat).
  2. One peer checks facts and dates in five minutes.
  3. Team agrees: this is the only context allowed until we revise the compact.
  4. Then — and only then — people prompt.

Pin the compact at the top of the working folder. Update it when reality changes. Do not "quietly fix" context inside a prompt.

A simple test

Before you hit send on a prompt, ask: Could a teammate reproduce this request using only the compact? If not, you are still carrying private context. Put it on the page or leave it out.

Closing

AI multiplies whatever you give it. Unshared context multiplies confusion. The Context Compact is a small leadership habit with a large effect: one page of agreed truth, then speed.

Try it this week on one piece of work that usually starts with "just ask the model." Write the compact first. Prompt second.

AImpactNI | Next Gen Leadership Thinking using AI

Comments

Post a Comment

Popular posts from this blog

The Tool Sunset

Every AI tool your team adopts should arrive with a date it has to earn its place again. Most teams are good at saying yes to AI tools. A pilot here, a plug-in there, an automation someone built on a Friday afternoon. Very few teams are good at saying goodbye. Six months later there are eleven tools, three overlapping subscriptions, two automations nobody remembers building, and company data flowing to places no one has checked. That isn't innovation. It's clutter, and clutter has a cost: money, attention, and trust. Good stewardship means caring for what you already carry, not only adding more. The Tool Sunset is a simple habit that keeps your AI stack lean, owned, and honest. Why AI Tools Pile Up Adoption is easy, retirement is nobody's job Trying a new AI tool takes minutes. Turning one off feels risky, because someone might still depend on it. So nothing gets switched off, and the pile grows quietly. The hidden costs don't show on the invoice Every tool...
Read more

The Skill Reserve

Keep the judgment your team needs when AI takes the easy reps. AI is very good at the first pass: the draft, the summary, the first cut of the forecast, the shortlist. That is a real gift of time. It is also a quiet risk, because the first pass is where people used to learn. When the reps disappear, judgment thins out, and nobody notices until the day the tool is wrong, down, or out of its depth. Stewardship means handing the next generation a team that can still think without the tool. The Skill Reserve is a simple practice for that: name the few skills your team must never lose, and protect a small amount of unaided practice for each. Why the reps matter The first pass is the classroom Most of us learned to spot a weak argument by writing weak arguments and having them corrected. If AI writes every first draft, people end up reviewing polished text instead of building their own reasoning. Skill loss is silent No dashboard shows a skill fading. You see it later, when a rev...
Read more

The Mandate Card

Image
One page that says what your AI is allowed to do — and what kills it Before any AI tool, agent, or automation gets operational authority, write one page that names what it may do — and what kills it. Teams move fast with AI. A new agent drafts emails, an automation updates a sheet, a tool reads client files. Authority arrives quietly, often without anyone writing down what "allowed" means. When something goes wrong, the room says "the AI just did that," and nobody can point to who granted the permission. That isn't speed. It's fog. Stewardship means clarity before capability: who owns this, what may it touch, and under what condition do we pull the plug. Good AI leadership thinking starts there — not after the surprise. The Mandate Card is a one-page brief you write before go-live. No mandate, no go-live. Why Authority Without a Mandate Fails Capability arrives before consent Modern tools can send, edit, fetch, and decide with a few toggles. Th...
Read more