Topic

Prompt Engineering

Roles, context, constraints, examples, and practical prompt patterns for daily work.

32 stories (17 articles · 15 videos)

Start here

A few good first pieces before you browse the full feed.

More in this topic

3 min read
Article

Write the creative brief before you prompt

A five-field brief makes creative direction visible. Compare two options against the same audience, facts and constraints, then change the brief deliberately if you learn something.

New to AI
6 min read
Article

Iterate variants without losing the direction

Variant generation is useful until it quietly replaces your thesis with whichever option looked shiniest. A direction-locked iteration method: freeze the brief, vary one axis at a time, and kill favorites that break the core claim.

Beginner
3 min read
Article

Tutor-mode prompts: getting AI to ask questions instead of just answering

Three prompts for hints, source-checked questions and error location, plus a worked example and a clear boundary for urgent safety or medical concerns.

New to AI
7 min read
Article

Your AI agrees with you too much: four thinking-partner failures

AI can help you examine a decision, but it also inherits your framing, rewards confident prose, and quietly encourages you to outsource judgement. Here is how to catch each failure.

Beginner
7 min read
Article

How to make AI disagree with you honestly

Five practical prompting patterns turn agreeable AI output into a more useful challenge—without pretending that a generated counterargument is evidence.

Beginner
3 min read
Article

Using AI to stress-test decisions: frameworks, trade-offs, and counterarguments

A four-step workflow for using AI to clarify a decision, generate alternatives, surface counterarguments, and keep uncertainty and human accountability explicit.

Beginner
4 min read
Article

Custom instructions and memory: useful defaults, reviewed context

Configure stable, non-sensitive defaults and memory controls, then review what is retained and override stale context when the task changes.

Beginner
3 min read
Article

Few-shot prompting: steer output by example

When a description leaves room for interpretation, show the model representative input-output examples and test whether they improve consistency on your task.

Beginner
9 min read
Article

Multi-tool AI workflows: design reliable handoffs across tools

A practical framework for combining research, document grounding, drafting, critique, analysis, and storage while preserving provenance, privacy, and review.

Intermediate
8 min read
Article

Choosing and prompting reasoning models

Reasoning settings change quality, latency, cost, and sometimes prompting behavior. A practical guide to choosing them by evaluation rather than folklore.

Intermediate
12 min read
Article

Choosing between prompting, RAG, and fine-tuning (and when to combine)

Diagnose whether an LLM task needs clearer instructions, current source context or a training experiment. Compare quality, access requirements and total operating cost before combining methods.

Advanced
13 min read
Article

Designing prompts for production: system, developer, and user layers

A governance pattern for separating trusted instructions, runtime data, and user input, then versioning, evaluating, deploying, and observing prompts according to risk.

Advanced
7 min read
Article

Building reusable prompt libraries: from snippets to shared templates

When the same AI-assisted task recurs, a prompt library can make the workflow easier to reproduce and evaluate. A practical system for capturing, testing, versioning, and sharing templates.

Intermediate
8 min read
Article

Stop prompting once: the iterative conversation method

A practical workflow for improving a promising first response through critique, narrowing, pivots, stress tests, and verification instead of restarting by default.

Beginner
4 min read
Article

Writing with AI without sounding like AI

AI-assisted drafts often fall into generic patterns. Use six editing checks to recover specificity and rhythm without pretending that style alone proves who wrote the text.

Beginner
20 minutes
Video

Google's 9 Hour AI Prompt Engineering Course In 20 Minutes

Tina Huang. A condensed run through Google's prompt engineering course covering frameworks for clarity, iteration methods, and worked examples for emails, summaries, and analysis. Useful if you want a second pass that maps the same structural ideas onto the kinds of tasks you actually hit during a workday.

Beginner
25 minutes
Video

Prompting 101 | Code w/ Claude

Anthropic. Two members of Anthropic's Applied AI team build up a single prompt for a real customer use case (analyzing Swedish car accident reports), starting from a one-liner that fails and adding role, task context, dynamic content, examples, and final emphasis one layer at a time. It is the cleanest demonstration on YouTube of the exact "role + context + task + constraints + format" stack the article describes, with the failure modes shown along the way.

Beginner
131 minutes
Video

How I use LLMs

Andrej Karpathy. The creator lists a "ChatGPT memory, custom instructions" chapter at 1:53:29. Use the personal workflow as a discussion example alongside the article's distinction between response defaults and retained context; current memory behavior must be checked separately.

Beginner
36 minutes
Video

Every ChatGPT Feature In 37 Minutes

Tina Huang. The creator's chapter list includes settings, personalization and data controls at 26:45. Compare that recorded example with the controls available to your account; plan, region and workspace restrictions can differ.

Beginner
42 minutes
Video

Prompt Engineering Tutorial – Master ChatGPT and LLM Responses

freeCodeCamp.org. Skip to the "Zero shot and few shot prompts" chapter at 31:20 for a clean, demoed comparison of the same task with no examples versus a few — exactly the contrast the article builds the chapter around. The earlier sections on prompt mindset and best practices are useful background if you've come straight from the article without the wider context.

Beginner
25 minutes
Video

Prompting 101 | Code w/ Claude

Anthropic. Examples are one of the ten ingredients Anthropic walks through here, and you can watch them get added to a real customer prompt and change the model's output. Useful if you want to see few-shot used inside a fuller prompt rather than as an isolated trick.

Beginner
3 minutes
Video

Building OpenAI o1

OpenAI. This three-minute first-party video records how the OpenAI team presented o1 at launch. It is useful for understanding the category's history, but it does not establish how current models work internally or which prompting pattern will perform best on a different provider or task.

Intermediate
28 minutes
Video

o1 - What is Going On? Why o1 is a 3rd Paradigm of Model + 10 Things You Might Not Know

AI Explained. The video offers an independent explanation of the early o1 framing and its prompting implications. It is useful historical context, but its claims about o1 should not be extended automatically to later OpenAI models, R1, Claude thinking modes or other providers.

Intermediate
77 minutes
Video

AI prompt engineering: A deep dive

Anthropic. Four Anthropic prompt engineers (research, alignment, applied, developer relations) talking at length about what they actually do day to day — how they edit prompts under pressure, how they think about "honesty" in instructions, when XML scaffolds help, when they don't. The article's layered model maps cleanly onto how they describe the work; this is the best way to hear that mental model out loud.

Advanced
25 minutes
Video

Prompting 101 | Code w/ Claude

Anthropic. A live build session by Anthropic's Applied AI team on an insurance-claims prompt — they start with a vague instruction and iterate to something a developer would actually ship, showing the kind of revisions the article describes for the system and developer layers. Watch this before re-reading the article's checklist on examples, output structure, and refusal handling.

Advanced
10 minutes
Video

The best ChatGPT Prompt I've ever created - I spent 2 months curating this prompt to write prompts

Lawton Learns. The video demonstrates a C.R.A.F.T. meta-prompt (Context, Role, Action, Format, Target audience). It is a useful candidate for testing how a prompt-generating prompt behaves, but its outputs are not guaranteed to be consistent, correct or suitable for a team's use cases.

Intermediate
20 minutes
Video

Google's 9 Hour AI Prompt Engineering Course In 20 Minutes

Tina Huang. Tina presents a five-part task/context/references/evaluate/iterate framework and four named iteration moves. Those elements can help you draft a candidate schema, but the agent and chain-of-thought examples reflect the course's time and context. Test any extracted pattern on representative cases before adding it to an approved library.

Intermediate
131 minutes
Video

How I use LLMs

Andrej Karpathy. Karpathy walks through his actual day-to-day use across ChatGPT, Claude, Gemini, Grok, and Perplexity, screen-sharing live conversations rather than polished one-shots. You see when he reaches for a follow-up, when he switches models mid-thread, and when he abandons a line and starts over — exactly the iterative loop the article describes, modeled by someone who builds these systems for a living.

Beginner
9 minutes
Video

Master the Perfect ChatGPT Prompt Formula (in just 8 minutes)!

Jeff Su. Six-part formula — task, context, exemplars, persona, format, tone — explained with office-work examples such as workout plans, resumes, and internal emails. It provides a compact frame that overlaps with several of the article's patterns.

Beginner
26 minutes
Video

Every Essential AI Skill in 25 Minutes (2025)

Tina Huang. The prompting chapter (02:30–09:20) lays out two stackable mnemonics — "tiny crabs ride enormous iguanas" (task, context, references, evaluate, iterate) and "ramen saves tragic idiots" (revisit, separate, try analogous, introduce constraints) — that map cleanly onto the iterate-and-refine patterns in the article. Useful when a single-shot formula isn't getting you there.

Beginner