---
id: "action-use-multiple-ai-modes"
type: "action-item"
source_timestamps: ["§ Step 2. Collaborate with AI across multiple modes."]
tags: ["prompt-engineering", "critical-thinking"]
related: ["framework-ai-collaboration-modes"]
speakers: ["David S. Duncan", "Tyler Anderson"]
action: "Prompt AI to critique, compare, simulate, and challenge its own outputs."
outcome: "Forces both human and AI reasoning into the open, exposing hidden flaws and missing context."
sources: ["reskilling"]
sourceVaultSlug: "hbr-seg-reskilling"
originDay: 10
articleStem: "hbr-edu-32-help-employees-get-better-with-ai"
sourceUrl: "https://hbr.org/2026/06/help-employees-get-better-not-just-faster-with-ai"
sourceTitle: "Help Employees Get Better—Not Just Faster—with AI"
---
# Engage AI in Critique, Compare, Simulate, and Challenge Modes

**Action:** Prompt AI to critique, compare, simulate, and challenge its own outputs — don't stop at generating a first draft.

Actively prompt the AI to identify its own weakest assumptions (**Critique**), surface tradeoffs between different generated versions (**Compare**), simulate specific stakeholder reactions (**Simulate**), and identify its weakest data sources (**Challenge**) — the [[framework-ai-collaboration-modes|five modes of AI collaboration]].

**Outcome:** Forces both human and AI reasoning into the open, exposing hidden flaws and missing context. This is [[framework-four-step-ai-development|Step 2]] of the model.