A framework by Mike Cilla · Beta

Build a living profile of how you actually lead.

Leadership OS turns assessments, AI-observed work patterns, and structured reflection into practical documents you can use with your team, your AI tools, and your own development.

Start Leadership OS → See sample outputs
~90 minutes · Works with any AI tool
Leadership OS · Analysis Engine
claude-sonnet
Leadership Profile — Sample Output 3 sources · 9 constructs
Systems Orientation
● High Confidence
Evidence across assessment results, behavioral patterns, and structured reflection suggests this leader naturally frames challenges as interconnected systems rather than isolated events. This pattern appears consistently — not just in strategic contexts, but in how everyday problems are described and diagnosed.
Decision Style
● Moderate Confidence
The pattern suggests a deliberate decision style: strong at integrating complexity, but at risk of waiting too long when the cost of delay increases. Behavioral evidence shows a consistent gap between when the evidence was clear and when commitment occurred.
→ Primary development insight
Delegation appears less constrained by trust and more constrained by personal quality standards. The growth edge is not "delegate more" — it is defining what good enough looks like before the work begins, not after.
Governing question (extracted from evidence)
"Does this make the system more trustworthy and capable — or does it just make it look that way?"
Sample output · Fictional persona · Generated from 3 evidence sources
Understand it in 60 seconds

What it is.
Why it's different.

Four ideas. No jargon. Read this first.

📥
You bring three inputs
A personality assessment. A structured reflection on how you work. And a behavioral audit from your existing AI conversation history — evidence of how you actually think, not how you describe yourself thinking.
🧠
Your AI finds the patterns
A synthesis prompt guides your AI to identify your decision tendencies, communication patterns, energy sources, friction points, and governing questions — across all three inputs simultaneously.
📘
You get three working documents
A Leadership User Manual. A Working-With-Me Guide. An AI Calibration Document. Not a report. Documents you share, update, and return to as your leadership evolves.
Traditional assessments
○Based on self-report only
○Produces a report you read once
○Static — a snapshot at one point in time
○No connection to how you actually work
○Insight fades within weeks
Leadership OS
→Combines self-report with behavioral evidence
→Produces documents you use and update
→Living — gets more accurate over time
→Grounded in patterns observed across the evidence you provide
→Built to persist and compound
How evidence becomes a profile
📋
Assessments
Trait tendencies
+
🔍
Behavioral
Observed patterns
+
🪞
Reflection
Meaning-making
=
📘
Profile
Construct hypotheses
PrinciplesYou · HEXACO · Big Five
AI conversation history
6 structured prompts
4 working documents
The complete process

Seven steps.
One living system.

Every step has a clear objective, specific inputs, and a prompt you can copy directly into your AI tool. Steps 4 and 4b (Analysis Engine and Construct Analysis) are where your evidence becomes a Leadership Profile — the intermediate artifact that grounds all your output documents. The whole process takes about 120 minutes the first time.

High
3 sources converge. "The evidence consistently shows..."
Moderate
2 sources converge. "The evidence suggests..."
Emerging
1 source points toward. "Worth exploring whether..."
Insufficient
Not enough evidence to form a useful hypothesis.
01
Assessment Inputs · 20 min
Take PrinciplesYou
The scientific anchor for everything that follows. PrinciplesYou is grounded in Big Five personality science — the same empirical foundation used in decades of leadership research. It produces an archetype profile and facet-level data that your AI will use to calibrate its pattern analysis.
What you need
  • 20 minutes of uninterrupted focus
  • Free account at principlesyou.com
  • Your full results — screenshot or PDF
What you get
  • Primary archetype + secondary attributes
  • Facet-level scores across 4 dimensions
  • Behavioral context for each dimension
Free · principlesyou.com · 20 min
Assessment Ingestion Prompt — paste into your AI after sharing your results
The Starter Kit contains the complete, governed version of this prompt. The assessment ingestion prompt teaches your AI how to treat assessment results as developmental hypotheses rather than objective facts — and what not to claim from them. Open the Starter Kit → Section 4 → Initialization Prompt
Works with ChatGPT, Claude, Gemini, or any frontier model. Keep this conversation open — all subsequent prompts build on this context.
02
Behavioral Evidence · 15 min
Run the Corpus Audit
This is the piece that makes Leadership OS genuinely different. If you use ChatGPT, Claude, Gemini, or any AI tool regularly, you've accumulated a behavioral record — thousands of decisions, communications, and challenges documented in a way no other medium captures. The Corpus Audit Prompt asks your AI to reflect on patterns it has observed across your conversations.
Works best with
  • 3+ months of regular AI use
  • Strategic or professional conversations
  • Decision-making, writing, analysis work
What you get
  • Observed behavioral patterns
  • Recurring themes and priorities
  • Communication and decision tendencies
15 min · any AI tool with conversation history
Corpus Audit Prompt — paste into the AI tool you use most
The Starter Kit contains the complete corpus audit prompt. It asks your AI to identify behavioral patterns — how you frame problems, what energizes you, how you make decisions — based on your conversation history. Not summaries. Patterns. Open the Starter Kit → Section 2 → The Corpus Audit Prompt
Paste this into the AI tool that holds most of your professional conversations. Copy the output and bring it into your main Leadership OS session.
03
Structured Reflection · 30–40 min
Answer the Six Reflection Prompts
Structured behavioral prompts — the same methodology as a behavioral interview, applied as a self-reflection instrument. These surface the specific stories and patterns that no assessment can reach. Answer them in writing, as a voice memo, or directly in conversation with your AI. Be specific. Real situations. Actual decisions. The more concrete, the more useful.
The six prompts
  • Peak performance — when were you at your best?
  • Decision process — how did you get there?
  • A decision you'd make differently
  • Recurring frustration — what keeps coming up?
  • Energy sources — what makes you lose track of time?
  • The misread — what do people get wrong about you?
Three ways to complete
  • Write responses directly in your AI tool
  • Dictate via voice memo, paste transcript
  • Have your AI interview you — use the guided interview prompt below
30–40 min · any format works
Guided Interview Prompt — let your AI conduct the reflection
The Starter Kit contains the complete guided interview prompt. Your AI conducts the six reflection prompts as a structured conversation — one question at a time, with follow-up for vague responses. The preferred method for most people. Open the Starter Kit → Section 3 → Guided AI Interview Prompt
This is the preferred method for most people. Conversational reflection surfaces more than writing alone. The AI will ask natural follow-ups.
04
Pattern Analysis · 10 min
Run the Leadership Pattern Synthesis
With all three inputs gathered — assessment results, corpus audit output, and reflection responses — you run a single synthesis prompt. Your AI analyzes across all three simultaneously, identifying where the sources converge, where they diverge, and what patterns are strong enough to anchor your Leadership OS.
What goes in
  • PrinciplesYou results (Step 1)
  • Corpus audit output (Step 2)
  • Reflection responses (Step 3)
What comes out
  • Convergent patterns — consistent across all sources
  • Tension points — where sources diverge
  • Governing questions extracted from evidence
  • Development edges identified
10 min · run in same session as Steps 1–3
Leadership Pattern Synthesis Prompt
The Starter Kit contains the complete synthesis and construct analysis prompts. These are the core engine of Leadership OS — the governed instruction set that produces evidence-based, confidence-labeled hypotheses across nine developmental constructs, including a required correction loop before document generation. Open the Starter Kit → Section 4 → Analysis Engine → Section 4b → Construct Analysis
Run this in the same AI session where you completed Steps 1–3. The AI needs all three inputs in its context window to synthesize effectively.
4b
Construct Analysis · 10 min
Build Your Leadership Profile
After the pattern analysis, a single construct analysis prompt asks your AI to evaluate all nine Leadership OS constructs across your three evidence sources. For each construct — like Decision Style or Self-Awareness — the AI identifies what each evidence source shows, where they agree or conflict, and what confidence level the evidence supports. The result is your Leadership Profile: the intermediate artifact that grounds all your output documents.
The Leadership Profile is private. It contains the full evidence reasoning — including tensions, low-confidence hypotheses, and constructs where the evidence was insufficient. The output documents (User Manual, Working-With-Me Guide) are the edited, shareable versions derived from this profile.
Nine constructs evaluated
  • Reflection Orientation
  • Systems Orientation
  • Learning Orientation
  • Decision Style
  • Communication Patterns
  • Leadership Identity
  • Adaptability
  • Self-Awareness
  • Development Readiness
What the profile contains
  • Evidence assessment per construct across all three sources
  • Confidence level: High / Moderate / Emerging / Insufficient
  • Tension points where sources contradict
  • Leadership Profile summary — 200–300 words
10 min · same conversation as Step 4 · Starter Kit has the full prompt
05
Document Generation · 15 min
Generate Your Three Documents
Three separate prompts — one per document. Run them sequentially in the same session. Review each output carefully. Correct anything that doesn't ring true. The AI is producing a first draft, not a finished profile — your job is to recognize what's accurate and push back on what isn't.
Document 1
  • Leadership User Manual (3–4 pages)
  • How you think, decide, and lead
  • Written in first person
  • Designed to be shared
Documents 2 + 3
  • Working-With-Me Guide (1 page)
  • Practical, shareable, under 3-min read
  • AI Calibration Document (1 page)
  • Onboards your AI to how you work
15 min · three separate prompts in sequence
Document Generation Prompts — run these in sequence
The Starter Kit contains the complete document generation prompts for all four outputs. Each includes a QA check before writing — verifying that all claims trace to the Leadership Profile and that confidence levels are preserved, not inflated. Open the Starter Kit → Section 5 → Output Generation
Review each output before moving to the next. Correct anything that doesn't feel accurate — this improves the subsequent documents.
06
Development Planning · 10 min
Build Your Development Roadmap
Not a list of things to fix. A structured view of where intentional practice would produce the highest return — given who you already are and what you're working toward. This document is private. It's for you, not for sharing.
What goes in
  • Development edges from Step 4
  • Your stated goals and context
  • Your flow conditions
What comes out
  • 3–5 development priorities
  • Specific practices for each
  • Triggers to watch for
  • A 90-day focus
10 min · private document
Development Roadmap Prompt
The Starter Kit contains the complete Development Roadmap prompt. It produces a private document with mechanistically specific development priorities, each labeled with the confidence level from the construct analysis. Open the Starter Kit → Section 5 → Document 4 → Development Roadmap
This document is for you, not for sharing. Be as honest as possible in the reflection steps — the quality of this output depends entirely on the quality of the inputs.
07
Ongoing · Your AI Companion
Keep It Alive
The Leadership OS is only as good as the evidence it's built on. The AI Calibration Document from Step 5 is the starting point — paste it at the beginning of any new AI conversation to establish context. Beyond that, the system gets better the more you use it. Return to it when something significant happens. Update the documents when something no longer rings true. Add new examples when they're fresh.
What persists long-term
  • Leadership User Manual — update annually
  • Working-With-Me Guide — update when role changes
  • Development Roadmap — update every 90 days
  • AI Calibration Document — update as you evolve
  • Governing questions — rarely change; worth noting when they do
What to discard
  • Raw reflection transcripts after synthesis
  • Corpus audit output once integrated
  • Earlier versions once superseded
  • Anything that no longer rings true
Ongoing · 30 min every 90 days to review and update
Ready to begin?
Open the Starter Kit.
Every prompt. Every instruction. All seven steps in one place. Complete Leadership OS without leaving the page — then save as PDF when you're done.
Open Starter Kit →
How reflection works

Three ways to
reflect.

The reflection step is the most underrated part of the process. Most people rush it. The people who get the most out of Leadership OS are the ones who slow down here — the quality of the synthesis in Steps 4 and 5 is almost entirely determined by the quality of the reflection in Step 3.

01
Be specific, not general. "I'm good under pressure" is not useful. "In the Q4 board presentation when the CFO challenged the numbers, I did X" is what produces a real profile.
02
The AI is an interviewer, not a coach. It should ask questions and identify patterns. It should not advise, evaluate, or tell you what to do.
03
Tension is data. When a reflection answer contradicts your assessment results, don't resolve the tension. Name it. That gap is often where the most interesting development work lives.
04
Return to it. The reflection prompts work better the second time. Come back six months later with new examples. The delta between versions is itself informative.
✍️
Written reflection
Type your answers directly into your AI tool, one prompt at a time. Works well for people who think clearly in writing. The AI can ask follow-up questions after each response. Best for detailed, precise thinkers.
🎙️
Voice-to-text
Record a voice memo answering each prompt, use your phone's transcription, then paste into your AI session. Works well for people who think better out loud. Often produces richer, less edited responses than writing.
💬
Guided AI interview
Use the guided interview prompt from Step 3 to let your AI conduct the reflection as a conversation. Ask one question, wait for your answer, ask a follow-up, move on. The preferred method for most people — conversational reflection surfaces more than writing alone.
Quality control

What this is.
What it isn't.

The Leadership OS is a self-knowledge methodology, not a psychological assessment. Understanding the boundaries keeps the outputs honest and useful.

Leadership OS can honestly claim
  • Synthesizing patterns across multiple data sources
  • Surfacing hypotheses about how you operate
  • Grounding insights in validated personality science as one input
  • Producing documents that reflect your own stated experience
  • Getting more accurate as evidence accumulates
  • Being a structured way to make implicit patterns explicit
Leadership OS does not claim
  • Validity or reliability in a psychometric sense
  • Normative comparison to any population
  • Predictive power for job performance or outcomes
  • Clinical or therapeutic conclusions
  • That AI observations are objective or unbiased
  • That the outputs are final or definitive
The honest framing
"This is a structured way to make your own patterns visible — using the best available inputs. The outputs are hypotheses, not facts. They're only as good as the evidence you bring. And they're most useful when you treat them as a starting point for reflection, not a finished description of who you are."
What stays, what changes

A living system
needs tending.

The Leadership OS gets better over time — but only if you maintain it. Here's what to keep, what to update, and what to let go.

Keep — long-term artifacts
  • Leadership User Manual — your primary reference
  • Governing questions — rarely change; note when they do
  • Working-With-Me Guide — stable unless your role changes significantly
  • AI Calibration Document — your onboarding doc for any new AI session
  • Previous versions — the evolution is itself informative
Update — regularly revisited
  • Development Roadmap — every 90 days
  • Flow conditions — as your role and context evolve
  • Development edges — as you work on them
  • Monitoring questions — when old ones stop being useful
  • Behavioral examples — add fresh ones while they're recent
Discard — don't carry forward
  • Raw reflection transcripts once synthesized
  • Corpus audit output once integrated into the profile
  • Anything that no longer rings true — outdated framing clutters the system
  • Superseded document versions after 2+ iterations
For the methodologically curious
Want to understand the underlying model?
The model page explains what Leadership OS is evaluating, how conclusions are formed, the developmental constructs it's designed to surface, and how it connects to established research in personality science, reflective practice, and leadership development.
View the model → See sample outputs →
About this framework

Built from an
experiment I ran
on myself.

I didn't set out to build a leadership methodology. I was trying to make my AI tools more useful at work.

Over 2.5 years as a VP of People Operations, I accumulated hundreds of working conversations with AI — workforce analytics, HR system design, organizational design, business cases, leadership decisions. At some point I realized I'd accidentally built something: a detailed record of how I actually think.

When I transferred that context to a new AI tool, I had to make my thinking explicit in ways it had never been before. What came out of that process was the most accurate leadership profile I'd ever received — more specific than any 360, more honest than most coaching engagements, and grounded in actual behavioral evidence rather than survey responses.

The Leadership OS is an attempt to make that process replicable for anyone, using whatever AI tools they already have, in about 90 minutes.

Background M.S. Industrial-Organizational Psychology, San Jose State University
Experience 15 years in People Operations, workforce analytics, and HR technology
Grounding Big Five / HEXACO science, I/O Psychology, Csíkszentmihályi's Flow model
The unexpected finding
"I was attempting to train an AI. The AI ended up training me — in a very practical sense. Making my thinking legible to a system that needed explicit context forced a level of self-reflection that accumulated organizational knowledge never demands."
The methodological difference
"Every existing leadership assessment asks you to describe yourself. The corpus audit asks the system that has watched you work to describe what it saw. That's a different kind of evidence — and a different kind of profile."
On what this is and isn't
"This is not a validated assessment. There's no normative sample, no inter-rater reliability. I want to be honest about what it isn't. But as a methodology for generating self-knowledge, it produced something I haven't gotten from any formal process."
Ready to begin

About
90 minutes.

Seven steps. Every prompt included. Works with whatever AI tool you already use.

Open the Starter Kit → See sample outputs

This framework is in beta. Feedback is genuinely welcome — mikejcilla@gmail.com