Outsource the heavy thinking. Keep the choosing. A tiny, repeatable loop beats infinite scrolling on a foggy day.

This guide helps you build a personal AI system to help you make choices when you’re feeling overwhelmed.

Quick Path ⚡

  • Pick one domain. Books, groceries, or shows. Start narrow.
  • List 20 real examples. Add why you liked it in 3–8 words.
  • Paste the Prompt Kit. Run Analyst → Evaluator → Summarizer → Ranker.
  • Choose one pick. Time-box 5 minutes. Stop after the first good answer.
  • Log the result. Save the pick + a one-line reason to your notes.

Phase 1 — Prepare Your Seed Data (10–15 min · Easy)

  • Choose a domain: streaming, books, groceries, or gadgets.
  • Gather 20–40 items you actually chose or enjoyed.
  • Add micro-reasons after each item: “reduced strain,” “fast weeknight,” “cozy mystery.”

Phase 2 — Run the Analyst (3 min · Easy)

  • Use the “Analyst” prompt from the kit below to find patterns in your data.

Phase 3 — Evaluate Candidates (4–6 min · Easy)

  • Collect 6–12 options you’re considering now.
  • Use the “Evaluator” prompt from the kit to score them against your patterns.

Phase 4 — Summarize & Rank (3–4 min · Easy)

  • Use the “Summarizer” and “Ranker” prompts to get your top 3 recommendations.

Phase 5 — Decide and Log (3 min · Easy)

  • Pick the top fit or the best comfort choice if energy is low.
  • Log one line: “Chose ___ because ___.”

The Prompt Kit 🧰

1) Analyst

You are my personal preference analyst.
From my history, infer 3–5 patterns with evidence and why each matters for me (MS/energy constraints included).
Return: Pattern | Evidence | Why it matters.

2) Evaluator

Score each candidate 1–10 against my patterns.
Add flags: comfort (C) vs novelty (N); physical/energy fit (Y/N).
Return: Item | Score | 1–2 Reasons | Flags.
Limit 25 words per row. Be blunt.

3) Summarizer

From items scoring ≥7, extract common themes in 3 bullets.

4) Ranker

Rank top 3 with trade‑offs and a 5‑minute starter step for each.
Return: Rank | Pick | Why it fits | Trade‑off | Starter step.
If nothing scores ≥7, say "No strong recommendation."

Filled Example

Seed Data:

The Bear (TV) — loved tight pacing; low emotional labor on weeknights
Kindle Paperwhite — reduces eye strain; reads in bed
Book: Project Hail Mary — propulsive; smart but warm

Ranker Output:

Rank Pick Why it fits Trade‑off Starter step (<5 min)
1 MX Master 3S Daily comfort + productivity boost Cost Try one‑hour test at desk
2 Slow Horses Pacing + wit; night‑safe Some violence Watch S1E1 tonight

Privacy & Redaction Reminder
  • Redact sensitive data before pasting. Use placeholders like [CLIENT], [ADDRESS], [LINK].
  • Prefer local tools for confidential material. Share only what you’re comfortable with.

Offline Backup (No-AI / Printable)
This workflow is AI-dependent and does not have an offline equivalent.

Troubleshooting
  1. Generic outputs.
    • Fix: Add your why after each history item. Specify constraints: budget, time, strain.
  2. Over-novel picks.
    • Fix: Add a comfort/novelty mix rule: 2 comfort to 1 novelty.
  3. Too many ties.
    • Fix: Break ties with daily comfort gain and setup friction scores.

Friction Fix 🔧

  • One automation: Text expander /arag → pastes the four prompts.
  • One simplification: Limit candidate lists to 9 items. Stop at first good answer.
Need help with single decisions? Use the BLUF Decision Prompt for a fast recommendation without the setup.

Next Action ▶️

Open a note titled “ARAG — Books”. List 20 titles you finished and add why you liked each in 3–8 words. Run the Analyst prompt.

Accessibility and Care ♿

  • Voice-only path: Dictate items and reasons; ask AI to clean the list.
  • Assistive tip: Use Do Not Disturb and a visible 5-minute timer during decisions.

Support & Further Resources 🙌

  • This system is self-contained, but can be used with any modern AI chat tool (ChatGPT, Claude, etc.).