Context Pillars
Context Pillars is a set of interview prompts that help you create reusable briefing documents for AI conversations.
The core insight: most people treat AI like an Oracle - query it, evaluate the answer, trust or reject. When it gets something wrong, the whole model collapses. The shift that changes everything is treating AI as a teammate who needs proper onboarding.
What it provides
Three interview prompts you can paste into any AI:
-
Onboarding prompt - Creates a personal briefing document covering how you think, work, and what useful help looks like for you. Update frequency: years.
-
Working context prompt - Maps your current role: what you’re accountable for, how decisions get made, and the 2-3 relationships that most shape your effectiveness. Update frequency: when your role shifts.
-
Landscape prompt - Maps your operating environment: players, pressures, dynamics, and what outsiders typically get wrong. Update frequency: weeks or months.
The three-layer model
Context has layers with different lifespans:
- Personal onboarding (stable) - who you are, how you think
- Working context (semi-stable) - your current role and key relationships
- Domain landscape (perishable) - the world you’re operating in right now
Different documents, different update frequencies. Create once, maintain as things change.
What it doesn’t try to do
- Write your documents for you
- Replace your judgement about what context matters
- Automate the thinking that makes AI useful
Why this matters
The quality of AI output is almost entirely determined by the quality of context you bring. That’s a skill. Context Pillars helps you build it.
Blogs & Insights
- Your AI Isn’t Failing You. You’re Failing to Onboard It. - The concept: Oracle vs Teammate
- Building Context Pillars - The execution: three-layer model and proof of concept
If you want more control, you can run your own instance from the source, or get in touch about a private setup.
View the source and install instructions on GitHub