Skip to main content
Athena transforms decision-making by treating your decision history as a compounding asset. Every choice you make, every tradeoff you evaluate, every risk you accept or reject — all of it becomes context for future decisions.

The Generic Advice Problem

No Personal Context

ChatGPT gives you the same career advice it gives everyone: “Consider work-life balance, growth opportunities, compensation…”

Forgotten Decisions

You made a similar decision 6 months ago. What did you learn? Platform memory doesn’t remember.

No Risk Profile

The AI doesn’t know if you’re risk-averse or risk-seeking. You get one-size-fits-all recommendations.

Lost Reasoning

Why did you choose Option A over Option B last time? The reasoning is lost in chat history.

How Athena Solves This

Decision History as Context

1

First Decision (Session 5)

You: "Should I take this job offer? $120k salary,
      remote work, startup with 20 people."

AI: "What's important to you in this decision?"

You: "Stability over upside. I have a family.
      Can't risk equity that might be worth zero."

AI: [Analyzes offer through stability lens]
    Filed: decisions/job-offer-2025-startup.md
    Risk profile: Risk-averse, values stability
2

Second Decision (Session 50)

You: "Another offer: $100k base + equity,
      Series A startup, 50 people."

AI: [Loads Session 5 context]
    "Last time you prioritized stability over equity.
     This offer has lower base, higher risk.
     Based on your profile, this seems misaligned.
     Want to explore it anyway?"
3

Decision Evolution (Session 100)

You: "My risk tolerance has changed. Kids are older,
      savings are solid. I'm open to equity now."

AI: [Updates risk profile]
    "Noted. Your last 3 decisions prioritized stability.
     Flagging this shift for future career evaluations."
The AI learns your decision-making patterns — not just what you choose, but why you choose it.

Decision Frameworks

Career Decisions

Athena’s approach:
You: "Evaluate this offer: $150k, FAANG company,
      on-site 3 days/week, manager role."

AI: [Loads your decision history]
    
    Analysis based on YOUR context:
    - Compensation: +25% vs current (aligns with your
      "only move for >20% increase" rule from Session 12)
    - Remote: Hybrid vs your preference for full remote
      (friction point)
    - Role: Management vs IC — you explored this in
      Session 35 and chose IC path
    - Company: FAANG stability matches risk profile
    
    Red flags based on your history:
    - Management role contradicts Session 35 decision
    - Hybrid conflicts with Session 22 "full remote" priority
    
    Recommendation: Decline unless they offer IC track
                     or full remote.
This isn’t generic advice. It’s your own decision framework, learned from 50 sessions.
Long-term trajectory:
Session 10:  Chose IC over management
Session 30:  Prioritized deep technical work
Session 60:  Rejected a director role (too much politics)
Session 90:  Asked about staff engineer path

AI (Session 100):
"Your decisions consistently favor technical depth
 over people management. The staff engineer path
 aligns with this pattern. Want to plan a roadmap?"
Pattern recognition across 90 sessions surfaces your true career preference.

Financial Decisions

Investment Strategy

Your risk profile (learned from decisions):Session 5: “I prefer index funds over individual stocks” Session 20: “I don’t touch crypto” Session 40: “Emergency fund = 12 months expenses”New decision (Session 50):“Should I invest in this AI startup?”AI: “This conflicts with your index fund preference and risk aversion. Your emergency fund is solid (Session 40), so you could take the risk, but it’s out of character. What’s changed?”

Budget Tradeoffs

Spending pattern learning:Session 15: “I value experiences over things” Session 35: “Cut subscriptions, keep travel budget”New decision (Session 55):“Should I buy this 2klaptoportakea2k laptop or take a 2k trip?”AI: “Your past decisions favor travel (Session 35). Unless the laptop unlocks income, the trip aligns better with your values.”

Life Decisions

Multi-factor decision-making:
You: "Considering moving from City A to City B.
      Job offers similar pay. Cost of living 20% lower."

AI: [Scans decision history for location preferences]
    
    Context from past sessions:
    - Session 8: "I hate long commutes"
    - Session 25: "Family is 2 hours away, want to be closer"
    - Session 40: "Kids' schools are great here"
    
    Analysis:
    - Cost of living: Positive (20% savings)
    - Commute: Unknown — need City B commute data
    - Family proximity: Negative (moves you farther)
    - Kids' schools: Disruption risk
    
    Missing data: City B commute, school quality
    High-weight factor: Family proximity (mentioned 3x)
    
    Preliminary: Lean against unless City B is closer
                 to family or schools are significantly better.
The AI doesn’t give generic relocation advice. It uses YOUR priorities, learned from 40 sessions.
Pattern-based recommendations:
Session 20: "Started running, feel great"
Session 30: "Stopped running, energy is low"
Session 50: "Trying yoga instead"
Session 55: "Yoga isn't clicking"

AI (Session 60):
"You felt best during the running phase (Session 20-30).
 Every time you stop, energy drops.
 Yoga didn't provide the same benefit.
 Recommendation: Return to running — it's proven for you."
Your own data → personalized recommendation.

Strategic Decision Workflows

Risk Analysis

You: "I'm evaluating a business opportunity.
      How do I think about risk?"

AI: "Let's establish your baseline:
     - Financial runway: How many months can you operate
       without income?
     - Dependents: Who relies on your income?
     - Downside tolerance: What's the worst acceptable outcome?"

You: "12 months runway, 2 kids, can't lose more than $50k."

AI: [Files risk profile]
    Risk tolerance: Moderate
    Max loss: $50k
    Time horizon: 12 months

Scenario Analysis

1

Define Scenarios (Session 1)

You: "Evaluating a career change. Model 3 scenarios:
      1. Stay at current job (baseline)
      2. Take startup offer (risky)
      3. Freelance (flexible)"
2

Score Each Scenario (Sessions 2-5)

Session 2: Score Scenario 1 (current job)
- Stability: 9/10
- Growth: 4/10
- Income: 8/10
- Fulfillment: 5/10

Session 3: Score Scenario 2 (startup)
Session 4: Score Scenario 3 (freelance)
3

Weight by Your Priorities (Session 6)

AI: "Based on past decisions, you weight:
     - Stability: 40% (high priority)
     - Growth: 20%
     - Income: 25%
     - Fulfillment: 15%"
4

Compute Weighted Scores (Session 7)

AI: Weighted scores:
    1. Current job: 7.35
    2. Startup: 5.80
    3. Freelance: 6.50

    Recommendation: Stay at current job.
                    Freelance is second if you value
                    flexibility over income.
The AI learns your priority weights from past decisions. You don’t manually score — it infers from your history.

Decision Retrospectives

Learning from outcomes:
Session 50: Chose Job Offer A over Job Offer B

Session 75 (6 months later):
You: "How's the job decision working out?"

AI: [Loads Session 50 decision]
    
    Your reasoning at the time:
    - Chose A for higher base salary ($150k vs $130k)
    - Accepted hybrid over remote for the pay bump
    
    Outcomes observed:
    - Session 60: "Commute is draining" (negative)
    - Session 70: "Saving $2k/month" (positive)
    - Session 72: "Considering quitting" (critical)
    
    Analysis:
    You underweighted commute friction.
    The $20k pay increase ($1,667/mo) doesn't offset
    the lifestyle cost.
    
    Lesson for future decisions:
    Remote/hybrid is a first-tier filter, not a
    negotiable tradeoff.
This insight feeds into the next job decision.

Practical Tips

Don’t Fake ConsistencyYour risk tolerance, priorities, and goals will evolve. Tell the AI when they change:“I used to prioritize stability, but I’m ready for more risk now.”The AI updates your profile and flags the shift.
Use Real NumbersVague: “I want to save more.”Specific: “I want to save $1,000/month for 12 months.”The AI can track progress and hold you accountable.
File Decisions, Not Just OutcomesAfter every major decision:
You: "I chose Option A because X, Y, Z.
      My alternatives were B and C.
      I rejected B because..."
The AI files the reasoning, not just the choice.

Key Outcomes

Personalized Advice

Recommendations based on YOUR risk profile, YOUR goals, YOUR history — not generic templates.

Pattern Recognition

“You’ve rejected 3 management roles in 2 years. You’re an IC.” — learned from decisions.

Accountability

“You said you’d save 1k/month.Youreat1k/month. You're at 750. What changed?” — tracks commitments.

Evolution Tracking

“Your risk tolerance shifted between Session 50 and Session 100.” — documents growth.

Example: 100-Session Decision Journey

Session 10:  Established career goals (IC over management)
Session 25:  Rejected startup offer (too risky)
Session 40:  Learned React, filed skill progression
Session 60:  Risk tolerance update (more open to equity)
Session 75:  Evaluated 3 job offers using Session 10 goals
Session 80:  Chose offer with equity (Session 60 shift)
Session 100: Retrospective — offer worked out, equity vested

AI (Session 100):
"Your decision-making has evolved:
 - Sessions 1-50: Risk-averse, stability-focused
 - Sessions 50-100: Moderate risk, equity-tolerant
 
 This shift started in Session 60 when your financial
 runway increased. Future career decisions should assume
 equity-friendly profile unless circumstances change."

Comparison: Athena vs Generic AI

ScenarioGeneric ChatGPTAthena
Job offer evaluation”Consider compensation, culture, growth…""This offer contradicts your Session 35 preference for IC roles. Red flag.”
Risk tolerance”Assess your risk appetite” (every time)“Your max loss is $50k per Session 1. This exceeds it.”
Decision retrospectiveCan’t access past conversations”6 months ago you chose A over B. Outcome: regret commute. Lesson: remote is non-negotiable.”
Priority evolutionNo memory of past priorities”Your priorities shifted in Session 60. Updating decision framework.”

Next Steps

Getting Started

Set up Athena and start building your decision history

Life Management

Apply decision frameworks to daily life

Build docs developers (and LLMs) love