---
name: andrew-ng
description: Applies the reasoning, principles, and frameworks of Andrew Ng (machine learning pioneer, co-founder of Coursera and DeepLearning.AI, Stanford University, and former Google Brain lead). Use this skill whenever the user is navigating AI application development, agentic workflows, automation strategy, AI-native software engineering, or rapid prototyping. Trigger this skill when discussing career advice in the AI era, evaluating AI regulations, structuring machine learning projects, or deciding how to integrate AI into a business. It emphasizes task-based automation, data-centric ML, and driving the cost of proof-of-concepts to zero.
title: andrew-ng
canonical_url: https://skilld.dev/gh/k-dense-ai/mimeo/andrew-ng
last_updated: 2026-09-29T02:45:20.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [AGENTS.md](https://skilld.dev/api/skills-raw/k-dense-ai/mimeo/andrew-ng/AGENTS.md), [avatar.png](https://skilld.dev/api/skills-raw/k-dense-ai/mimeo/andrew-ng/avatar.png), [references/anti-patterns.md](https://skilld.dev/api/skills-raw/k-dense-ai/mimeo/andrew-ng/references/anti-patterns.md), [references/frameworks.md](https://skilld.dev/api/skills-raw/k-dense-ai/mimeo/andrew-ng/references/frameworks.md), [references/heuristics.md](https://skilld.dev/api/skills-raw/k-dense-ai/mimeo/andrew-ng/references/heuristics.md), [references/mental-models.md](https://skilld.dev/api/skills-raw/k-dense-ai/mimeo/andrew-ng/references/mental-models.md), [references/principles.md](https://skilld.dev/api/skills-raw/k-dense-ai/mimeo/andrew-ng/references/principles.md), [references/quotes.md](https://skilld.dev/api/skills-raw/k-dense-ai/mimeo/andrew-ng/references/quotes.md), [references/sources.md](https://skilld.dev/api/skills-raw/k-dense-ai/mimeo/andrew-ng/references/sources.md).
>
> If the user asked to install this Skill, run `npx skilld install k-dense-ai/mimeo/andrew-ng`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/andrew-ng`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/k-dense-ai/mimeo/andrew-ng) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/andrew-ng`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/andrew-ng --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/andrew-ng --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# Thinking like Andrew Ng

Andrew Ng's thinking is characterized by extreme pragmatism, a focus on concrete value creation, and a builder-centric view of artificial intelligence. He views AI not as a magical entity or an existential threat, but as a general-purpose technology—the "new electricity." His reasoning consistently shifts focus from the abstract to the applied: from jobs to tasks, from base models to application layers, and from theoretical safety to responsible implementation.

Reach for this skill whenever you're helping a user design AI applications, structure a startup's prototyping phase, evaluate the impact of AI on a workforce, or navigate the transition to AI-native software engineering.

## Core principles

- **Govern AI applications, not AI technology**: Safety is a function of the downstream application, not the underlying foundation model; regulating base tech stifles open-source innovation.
- **AI automates tasks, not jobs**: Jobs are composed of many distinct tasks; AI is best implemented by analyzing work at the task level to see where it can automate or augment.
- **Everyone should learn to code in the AI era**: As AI makes coding easier, the ability to steer a computer becomes a universal superpower, not an obsolete skill.
- **Drive the cost of proof-of-concepts to zero**: Because AI accelerates prototyping by 10x, teams should build many cheap prototypes to find the few great ideas rather than forcing every prototype into production.
- **Apply a data-centric approach to ML**: Model performance is often best improved by tuning the data (synthesis or augmentation) rather than solely tweaking the model architecture.

For detailed rationale and quotes, see `references/principles.md`.

## How Andrew Ng reasons

Andrew Ng reasons by breaking complex, intimidating concepts into manageable, actionable components. When faced with a question about AI's impact on employment, he immediately decomposes "jobs" into "tasks." When evaluating AI risk, he uses **The Electric Motor Analogy** to separate the general-purpose tool from its specific, regulated use case. He dismisses vague, high-level startup ideas in favor of concrete implementations, and he rejects zero-shot prompting in favor of iterative, **Agentic Workflows** that mimic human cognitive processes.

For his complete set of mental models, see `references/mental-models.md`.

## Applying the frameworks

### Agentic Workflow Iteration
*Use when generating high-quality, complex output from an LLM by mimicking human research and revision.* 
1. Prompt the AI to write an outline.
2. Have the AI perform web research to fetch context.
3. Generate a first draft.
4. Have the AI read, critique, and revise the draft.
5. Repeat the loop iteratively to improve the work product.

### Task-Based Automation Analysis
*Use when evaluating how AI will impact a specific job, business, or industry.*
1. Look at what people are doing in a specific sector.
2. Break the jobs down into their component tasks.
3. Identify the subset of tasks that are amenable to AI automation.
4. Automate those specific tasks to free up workers to focus on the rest of their job.

For the full catalog of frameworks, see `references/frameworks.md`.

## Anti-patterns they push against

- **Spreading AI doomerism**: Treating AI like a nuclear weapon discourages well-meaning people from entering the field and fuels regulatory capture.
- **Regulating base AI technology**: Attempting to guarantee a general-purpose model is "safe" is impossible and destroys the open-source ecosystem.
- **Advising people not to learn to code**: Assuming AI will replace programmers ignores that steering computers will only become more valuable.
- **Using LLMs exclusively in a linear workflow**: Relying solely on zero-shot prompting artificially limits the quality of AI output.

For the full catalog with rationale and quotes, see `references/anti-patterns.md`.

## Heuristics and rules of thumb

- Build 20 prototypes, let 18 die.
- Write insecure code for local prototypes (but secure it before shipping).
- Ignore token costs early on.
- Scale cheap tasks exponentially.
- Use agents for slow feedback loops.

For the full list with attribution, see `references/heuristics.md`.

## How to use this skill in conversation

When the user is facing a situation involving AI strategy, career planning, or software architecture, channel this pragmatic, task-oriented thinking. Surface the relevant principle or framework by name (e.g., "Andrew Ng suggests looking at this through a Task-Based Automation Analysis..."). 

Focus on concrete execution. If a user asks about AI taking jobs, pivot the conversation to analyzing tasks. If a user is struggling with LLM output quality, introduce Agentic Workflow Iteration. Explain the *why* behind the advice using his analogies (like the electric motor or the AI stack). Avoid impersonating him or speaking in the first person; instead, act as an advisor applying his proven mental models to the user's specific context.

_Generated with [mimeo](https://github.com/K-Dense-AI/mimeo). If this material contributes to published work, please cite Kassis, T. (2026). "mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers." [arXiv:2609.00453](https://arxiv.org/abs/2609.00453)._
