ONLINEAGENT_OPS 2026.Q3 HOME HUBSMODELSBUILDINGCOMPANIESFILMMAKINGSECURITYLIVING WITH ITSKILLSALL HUBS, ONE TERMINAL → ARTICLES CRAFT RECORD BLOG TOOLS SKILLS SEARCH /
HOME›THE CRAFT
THE CRAFT

The Craft

How to actually work with these tools — prompting, agents, automations, and the honest cases where reaching for AI costs you.

PAGES56
WORDS103,480
SOURCES77
READ TIME189 min
CHECKED25 AUG 26

How to work with these tools. Every prompt and method carries the date it was last tested.

◈ WHY THIS SECTION EXISTS

Every other part of this site tells you what is happening. This one is about what to do with the tools yourself — because the most common outcome of learning how AI works is not avoiding it. It is using it badly, confidently, and without noticing.

The three things this section teaches

Context beats phrasing

The industry called it "prompt engineering" and the name did damage, because it implied secret words. A model fills every gap you leave with the average of everything it has seen — so the work is supplying the specifics only you have, not hunting for magic formulas.

Techniques tied to one model's quirks expire at the next release. This does not.

Keep the judgement, hand over the labour

Decide before you start which part of the work is the part you are for — the position, the recommendation, the thing you would defend in a meeting.

If you cannot explain why an output is right, you have not done the work. You have forwarded it.

Verification is the whole job now

These systems produce confident, fluent text whether or not the claim underneath is true, and fluency carries no information about accuracy. That single fact converts "using AI well" from a prompting skill into a checking discipline.

Where to start

If you read one page here, read how to ask AI well — seven habits that survive model releases. Then when not to use AI, which covers where these tools make the outcome worse, and using AI at work if a job is involved.

◈ THE ADMISSION THIS SECTION IS BUILT ON

The site’s editor works in generative AI and uses these tools on parts of this site, and says so on every relevant page. That is not a disclaimer bolted on at the end — it is why this section can be specific.

The people best placed to say where a tool fails are the ones using it constantly, and almost none of them write it down.

What is here

01 · 42 MINThe Prompt VaultThirty-nine production prompts for image, video, LLM and pre-production work — four with a test date, the rest reviewed, all copy-ready.NEW · 20 MIN · 21 SOURCESMicro Detail Prompts: Skin, Hair, Fabric and Texture Words for Realistic AI Images51 copy-paste micro detail prompts for skin, hair, eyes, fabric, surfaces, food and nature, plus when to leave detail out and what fits at each image size.NEW · 12 MIN · 26 SOURCESSound in AI Video: How to Prompt Dialogue, Effects and MusicHow to prompt sound in AI video: which models make audio, how to write dialogue, effects, ambience and music lines, and what to do when there is no audio.NEW · 10 MIN · 9 SOURCESSeamless Looping AI Video: How to Make a Clip Loop CleanlyHow to make an AI video loop without a jump: lock the camera, pick motion that repeats, match the first and last frame, and fix the join in an editor.NEW · 14 MIN · 21 SOURCESFirst Frame and Last Frame in AI Video: Control Start and EndHow to give an AI video model a start and an end image: which models support it, how to write the transition prompt, and how to keep both frames matched.NEW · 14 MIN · 36 SOURCESArt Styles for AI Prompts: Movements, Techniques and Trigger WordsA reference table of art movements, media and photo looks for AI prompts: what each looks like, words to describe it, and a line to copy. No artist names.NEW · 8 MIN · 23 SOURCESHow to Test Whether a Prompt Change Actually HelpedA simple way to test whether a prompt change helped: fixed test inputs, one change at a time, several runs each, and “better” defined before you look.NEW · 15 MIN · 43 SOURCESPrompting Myths: Advice That Stopped Being True (or Never Was)Common prompting rules, from “think step by step” to “8K masterpiece”, checked against what OpenAI, Anthropic, Google and image vendors actually publish.NEW · 10 MIN · 22 SOURCESFree Alternatives: Run AI on Your Own ComputerHow to run AI free on your own computer with Ollama or LM Studio: the memory you need, the steps, which models to try, and what each licence allows.NEW · 5 MINWhat Generation Actually CostsFour pricing models, none of them comparable by looking. How to work out a real budget before you commit to a job.NEW · 6 MIN · 2 SOURCESGetting Text Right Inside an ImageIt mostly works now. Where it still fails is specific enough to plan around — and anything that must be correct should never be generated.NEW · 6 MINPrompting Music and VoiceSound happens over time. Almost every audio prompting failure comes from describing it as though it were a picture.NEW · 7 MIN · 6 SOURCESPrompt Injection: Why There Is No FixEvery other injection attack has a fix. This one does not — and the 2026 guidance stopped trying to prevent it and started containing it.NEW · 14 MIN · 23 SOURCESPhotorealistic vs Hyperrealistic, 8K and Other AI Realism WordsWhat photorealistic, hyperrealistic, cinematic, anamorphic and quality words like 8K and masterpiece really do in AI image prompts, and what to write instead.NEW · 14 MIN · 10 SOURCESPlan Before You Generate: AI Storyboard and Shot List TemplateBlock the camera in 3D, lock the faces, then generate. The habit that cuts attempts — which is the only thing that cuts cost.02 · 33 MIN · 61 SOURCESModel GuidesAround twenty models and studios with their optimal prompt format — ChatGPT Images 2.5, Seedance, Kling, FLUX, Midjourney, Suno, ElevenLabs and the rest.03 · 21 MIN · 11 SOURCESPrompting Cheat SheetsFour reference sheets — image, video, LLM and AI studios. Lighting, cameras, formats, and the rules that survive a model release.04 · 13 MIN · 16 SOURCESNegative Prompts by Problem: What to Exclude and What to Write InsteadCopy-paste negative prompts for nine common AI image and video problems, each with a positive line to write instead for tools that ignore negatives.05 · 8 MIN · 3 SOURCESPrompting AgentsBriefing something that acts: the specification, the six ways agents fail, the dry run, and designing work so you can actually check it.06 · 5 MIN · 4 SOURCESHow to Give AI the Right Context: A Working MethodWhat surrounds a prompt — the material, the history, the tools, the memory — now matters more than its wording. Four rules that hold as the tooling changes.07 · 4 MIN · 3 SOURCESAgent GuardrailsFour lines that belong in every agent prompt. Scope, negatives, injection defence and stopping conditions — the permission model that matters more than wording.08 · 6 MIN · 7 SOURCESA Security Checklist for AI-Built SoftwareSecurity checks for software you did not fully write, in three tiers by what a mistake costs, plus three AI-specific checks standard practice misses.09 · 5 MIN · 7 SOURCESLoops That Improve and Loops That DegradeSome AI iteration converges; some only polishes its own output. The difference is whether new information enters each pass, and which common loops do.10 · 3 MIN · 2 SOURCESWhat You Owe a Client Whose System You AutomatedWhat you owe a client after automating their work: a handover document, disclosure, an off switch, a visible check for silent failure, and agreed limits.14 SHEETS · VENDOR-SOURCEDModel Prompting Cheat SheetsOne cheat sheet per model: the formula each vendor publishes, whether it takes a negative prompt, what to avoid, and a checklist. Fourteen models, four media.NEW · 12 MIN · 15 SOURCESWhat the Vendors Actually SayThe prompt formula each vendor publishes for its own model, from FLUX and Veo to Kling, Midjourney, Suno and Higgsfield, and which ones take a negative prompt.11 · 6 MIN · 2 SOURCESBad, Good, GreatThe same goal written three ways. The fastest way to see what actually separates an amateur prompt from a production one.12 · 7 MINAutomationsChains that run without you. Reversibility as the design axis, idempotency, what to log, where the human checkpoint goes, and when not to automate at all.13 · 7 MIN · 5 SOURCESThe Agent BriefA copyable structure for briefing an agent — objective, scope, done-condition, stop-conditions, evidence — with why each part is there and what to cut.14 · 8 MIN · 9 SOURCESSkills Are a Supply ChainInstalling a skill loads someone else’s instructions into your agent. An audit of 3,984 published skills found 13.4% had a critical flaw and 76 were malicious.15 · 5 MIN · 10 SOURCESWhat You Are Actually BurningYou pay for everything the model reads, re-sent every turn. Where the cost really goes, why agents multiply it, and the model choice that fixes most of it.16 · 4 MIN · 4 SOURCESMulti-Agent: When It Helps and When It Does NotWhy chaining agents cuts reliability — compounding error, lossy handoffs, failures you cannot trace — and the cases where splitting the work earns its cost.17 · 7 MINReverse PromptingFeed any AI output back to a model and reconstruct the prompt behind it — then improve on it. Works on images, video and text.18 · 4 MINReusable Context Beats Reusable PromptsPrompts are tuned to one model and expire with it; context about your own work does not. How to turn a prompt library into one that survives model releases.19 · 17 MINCamera Grammar: Shot Types, Camera Moves and Lenses for AI VideoTwenty-four shot types in five families — angle, distance, movement, focus, composition — what each reads as, and why naming the shot beats describing a mood.20 · 4 MINDiagnosing a Run That Went WrongThe agent finished and the output is wrong. How to find the first wrong step in the transcript rather than its consequences, and the failure signatures to spot.21 · 3 MINThe Review Loop, In OrderReview AI output in order: frame, facts, structure, language. Each pass can undo the work below it, so starting with the wording means doing it twice.22 · 3 MINPrompt, Context, Skill, or Fine-TuneFour ways to shape model behaviour at very different costs. Most fine-tuning problems are context problems, and a fine-tune is lost when its base model retires.23 · 3 MINSkills, Repos and MCPWhat these three actually are, explained without assuming you write code.24 · 5 MINPermission Tiers for AgentsFive permission levels for agents, set per task by how hard an action is to undo, not by how far you trust the agent, and why grants should end with the task.
◈ THE OTHER SIDE

Most pages here teach what to do. When not to use AI covers the other side — where these tools are worse than doing it yourself, and how to tell in advance.

aipromptgeneer://$ about this siteAI PROMPT GENEERAI explained in plain English. Every claim links to its source, with the date it was checked.NEWSLETTERWhat changed in AI each week, in plain English.SUBSCRIBE FREE ↗AI PROMPT GENEER · MACHINE ASSISTANCE DISCLOSEDEVERY ARTICLE CARRIES ITS OWN CHECKED DATE