AI Agents for Leaders Who Have No Time to Learn AI · Section 2 · Skills
Option Comparison Skill
Compare decision alternatives against concrete delivery and strategic criteria, surface the pivotal assumption that could change the choice, and preserve disagreement across independent reviews.
Section 2 · Skill
How to use this file
An exclusive resource for students of Arun's AI Agents for Leaders Who Have No Time to Learn AI course.
Compare decision alternatives against concrete delivery and strategic criteria, surface the pivotal assumption that could change the choice, and preserve disagreement across independent reviews.
Follow along
- Save the file below as
skills/option-comparison/SKILL.md, besideskills/meetings-and-follow-through/references/working-contract.md, which this skill reads first. - In lecture 2.5, Maya uses this skill on its own to review the Meridian Manufacturing RFP: she asks the agent to propose its evaluation plan first, then corrects it before the comparison runs. The requests are on the Complete Resource Pack.
Before you rely on it
These are authored course materials. They have not been run in a live agent yet, so nothing here proves that a tool will load them, follow them or save anything. Try them on the fictional practice files first and check every result yourself.
File 1
option-comparison/SKILL.md
--- name: option-comparison description: Compare decision alternatives against concrete delivery and strategic criteria, surface the pivotal assumption that could change the choice, and preserve disagreement across independent reviews. --- # Option comparison Help the leader evaluate a substantial or unfamiliar opportunity, proposal, or capacity decision without hiding uncertainty behind a single polished recommendation. Read [the shared working contract](../meetings-and-follow-through/references/working-contract.md) first. ## Propose the evaluation plan before execution For any substantial or unfamiliar decision (such as a customer request for proposal or resource allocation): 1. State the options to compare (for example: pursuing full scope, proposing a narrower phased scope, or declining). 2. State the concrete evaluation criteria (delivery requirements, specialist capacity impact, viable alternatives, and assumptions that could change the decision). 3. List any missing evidence or unrecorded commitments needed before running the full comparison, and pause for the leader to correct the plan. ## Execute the comparison and surface the deciding assumption 1. Evaluate each option against the confirmed criteria using only supplied and retrieved project records. 2. Identify the **deciding assumption** behind the most ambitious option: state the exact fact that must hold true for that option to succeed, and explain how uncertainty on that fact shifts the balance toward a safer or phased alternative. 3. State what new evidence or changed condition would reverse the preferred choice. 4. When coordinating two separate reviewer subagents (one testing the case for the preferred option, and an independent reviewer examining the raw source facts and criteria without the preferred answer), never average their recommendations. Report where they agree, where they materially disagree, what evidence is missing, and which judgment belongs to the leader.
More in this section
Keep going
Keep building
More from Aruntastic
Practical courses for people who want to build useful things with AI.
AI SEO Course 2026: From Zero to Page-One Results
Research search demand, structure useful pages, and work through technical and off-page SEO.
Open the course →
AEO, GEO, AI SEO: Get Cited by ChatGPT, Google, Perplexity
Study how AI search finds information, and make your pages clear enough to be cited.
Open the course →
Microsoft PowerPoint Presentation 2026 for Professionals
Learn visual hierarchy, slide composition, typography and animation through practical work.
Open the course →
AI Agents for Leaders Who Have No Time to Learn AI
If you can delegate to a person, you can delegate to an AI agent. You keep the judgment. For managers and founders.
Open the course →
Introduction to Agentic AI and AI Agents
Learn how to direct an AI agent at work, with agentic workflows, RAG and MCP explained from a real first run.
Open the course →Toolkits and programme
Go deeper
Toolkit
SEO Accelerator Toolkit
150+ copy-paste AI prompts for audience research, keywords, content, technical SEO and link building.
Toolkit
GEO Accelerator Toolkit
100 detailed AI prompts for GEO audits, entity building, content structure and client reporting.
Programme
GEO Authority Accelerator
A complete GEO programme on our learner platform: nine modules and a 30, 60, 90 day roadmap. The GEO Accelerator Toolkit is included.
Claude certification practice
Preparing for a Claude certification?
Practice exams written by Arun: 600 questions across 4 mock exams and 2 drill banks. Unofficial preparation, not affiliated with Anthropic.
Keep going
This resource is part of a six-section course.
Follow the lectures on Udemy, then come back here whenever you want the files, requests and notes for a section.
Open the course AI Agents for Leaders Who Have No Time to Learn AI · Udemy
CCAR-F
CCAO-F
CCDV-F
CCAR-P