THE ARCHITECTURE

Four engines.
One intelligence system.

SENTINEL MAN is not a single AI responding to prompts. It is a coordinated system — four specialised engines working from your data to produce intelligence that improves the longer you use it.

01
Brief Engine
02
Decision Engine
03
Pattern Engine
04
Debrief Engine

Each engine has a distinct job. Each draws from the same data store — your check-ins, your decisions, your Operating Principles — and produces a different form of intelligence. None of them work in isolation. Together they build a model of how you operate that no single AI session can produce.

ENGINE 01 — DAILY

The Brief Engine.

Every morning, before you open your inbox, SENTINEL MAN produces your operational brief. Not a generic motivational message. A data-driven intelligence report, specific to your state on that specific day.

The brief begins with your mode assignment — COMMAND, RECON, or STANDBY — determined by the system from your check-in data and recent trend. Your mode sets the tone for everything that follows. A COMMAND mode brief is aggressive and directive. A RECON brief is observational, diagnostic. STANDBY is minimal — the system knows today is not the day to push hard.

Below the mode: your Readiness Score (0–100), your decision quality window (the hours your data says your judgment is sharpest), and three operational levers — specific, actionable moves for that day. No generic advice. Each lever is derived from the pattern the system has built about you.

THU 08 MAY — 06:34 AEST
▶ COMMAND MODE
84
READINESS SCORE — PERSONAL BASELINE
Sleep debt: 8 minutes. HRV elevated. Cognitive load: optimal. Your peak decision window opens at 06:34 and closes at approximately 12:00. Three levers identified.
Front-load decisions before 11am↑ DECISION
Physical output before first business action↑ CLARITY
Contact M. — 21 days elapsed◈ NETWORK
WHAT FEEDS THE BRIEF ENGINE

The daily check-in.

DAILY CHECK-IN — UNDER 90 SECONDS
MOOD VECTOR
Fog · Edged · Flat · [Solid] · Apex
SLEEP HOURS
7h ▮▮▮▮▮▮▮▯▯▯
PHYSICAL LOAD
[Rested] · Loaded · Crushed
MENTAL CLARITY
4 / 5 ▮▮▮▮▯
NETWORK PULSE
Degraded · [Stable] · Optimal
CARRY-FORWARD (OPTIONAL)
Board deck review before 1600 →

Five inputs. Under 90 seconds. No typing unless you choose to. The check-in is deliberately minimal — because a tool you do not use daily produces no intelligence at all.

The five inputs — mood vector, sleep hours, physical load, mental clarity, and network pulse — feed directly into your Readiness Score calculation. A sixth optional field, carry-forward, lets you log an open item in under ten words. That item appears in tomorrow's brief until you clear it.

From Day 7 onward, your scores are calculated against your personal baseline — not population averages. A Readiness Score of 71 means something different for you than for the man next to you. The system learns the difference.

ENGINE 02 — ON DEMAND

The Decision Engine.

When you face a significant decision, you submit it to the Decision Engine. Four AI models analyse it in parallel — each with a different mandate. Within 26 seconds, a synthesised assessment arrives. One voice. Four perspectives already resolved.

The Reasoner — checks the decision against your history and your Operating Principles. Has this pattern appeared before? What did your data look like on days you made similar choices?

The Contrarian — attacks the obvious choice. What are the specific kill shots? What is the worst-case outcome? What are you not seeing because you are inside the decision?

The Context Enhancer — finds the variables you are not considering. Second and third-order consequences. Relational ripples. What happens to the people adjacent to this decision?

The Predictor — estimates what you will actually do. Based on your behaviour patterns, are you genuinely evaluating this — or have you already decided and are seeking validation?

DECISION ASSESSMENT — 26 SECONDS
REASONER
Identical structure to April hiring decision. OP 1 conflict detected. Third path available — 14-day compressed trial.
CONTRARIAN
$180K with no trial period. If this fails, the referring client absorbs reputational damage. You are being pressured by your own calendar.
CONTEXT
Your best client is the referral source. A failure here doesn't only affect the contract — it implicates that relationship.
PREDICTOR
You are seeking permission for an exception you have already committed to internally — not genuinely deciding.
◈ SOVEREIGNTY CHECK
If this offer arrived with a 60-day start and standard trial structure — would you take it? That question isolates the opportunity from the pressure.
ENGINE 03 — LONGITUDINAL

The Pattern Engine.

PATTERN LEDGER — ACTIVE SIGNALS
SLEEP-DECISION CORRELATION
Decision quality drops 31% when sleep debt exceeds 45 min. Pattern consistent across 14 data points.
CONFIDENCE: HIGH · 14 DATA POINTS
AFTERNOON REACTIVE DECISIONS
Decisions made after 3pm on high-load days are 40% more reactive than baseline.
CONFIDENCE: MEDIUM · 8 DATA POINTS
NETWORK-CREATIVITY LINK
Strong social contact weeks correlate with higher clarity scores 2 days later.
CONFIDENCE: EMERGING · 5 DATA POINTS

Most tools show you how you felt today. SENTINEL MAN builds a model of how you operate over time — detecting the correlations that repeat in your data before you are consciously aware of them.

The Pattern Engine runs two scans. A daily light scan checks for emerging signals — possible correlations in your most recent data. It never surfaces a pattern until the evidence threshold is met. A weekly deep scan runs a full analysis across your history, confirming patterns, updating confidence scores, and retiring patterns that no longer hold.

The patterns that matter most are the ones that reveal your decision conditions — the physiological and situational states that predict your best and worst calls. "Decision quality drops 31% when sleep debt exceeds 45 minutes and physical load is high." That is not a population statistic. That is your data.

ENGINE 04 — WEEKLY

The Debrief Engine.

Every Sunday evening, the Debrief Engine synthesises your week. Not a mood summary. A performance review — the kind a serious athlete would review between training sessions.

The debrief covers what changed, what degraded, what improved, what your decision quality looked like, and which Operating Principle was tested during the week. It closes with your primary objective for the next cycle — a single actionable focus that carries forward automatically to Monday's brief.

By Week 12, your DEBRIEF tab is twelve weeks of operational history. Re-readable. The man who reads Week 3 at Week 12 and sees the same limiting variable is reading his own pattern — not a system report. That is what SENTINEL MAN is designed to produce.

WEEKLY DEBRIEF — WEEK 7
PERFORMANCE SUMMARY
Decision quality: 74% ▮▮▮▮▮▮▮▯▯▯
Readiness trend: +6% vs Week 6 ▮▮▮▮▮▮▯▯▯▯
Network health: Stable
PRINCIPLE TESTED THIS WEEK
OP 2: No hire decision without 72-hour cooling period. Two opportunities arose. Protocol held on one. The second was borderline — flagged for review.
◈ NEXT CYCLE OBJECTIVE
Reduce reactive decisions after 3pm — implement end-of-day decision cutoff protocol before Week 8.
THE DISTINCTION

Not what you have tried before.

Every tool claims to be different. Here is the specific difference.

OTHER PLATFORMS
  • Generic population data applied to your situation
  • Mood tracking with no decision intelligence layer
  • Single AI giving one perspective on every decision
  • Employer-purchased — your manager knows you use it
  • Wellness language designed for a different audience
  • Insights that reset every session, no longitudinal model
SENTINEL MAN
  • Your personal baseline builds from Day 1. Every score is yours.
  • Four AI lanes analyse every decision — including the contrarian kill shots
  • Pattern intelligence that accumulates across 90 days and beyond
  • Man-sovereign. You buy it. Nobody at HR knows. Your data.
  • Performance language — the system speaks the way you think
  • Operating Principles gate — every decision checked against your own values

See it working
on your data.

Seven days. No credit card. The system starts building from Day 1.

Begin your 7-day trial →