Claude projekter er det bedste AI kreative team vi nogensinde har ansat

Sådan bygger du et kontekstbibliotek

Hvert projekt sættes op med tre kernedokumenter:

De tre dokumenter kobles til Claude sammen med en omhyggeligt skrevet systemprompt, der peger på alt indholdet.

Praktisk opsætning

• Start med 3-5 kerneområder, såsom overskrifter, scripts, idéer/iterationer og omskrivninger.
• Opdater dokumenterne jævnligt, også baseret på dårlige svar. Når Claude giver et dårligt svar, så upload svaret og forklar, hvad der gjorde det dårligt.

Effekt på produktionen

• Øger både volumen og kvaliteten af overskrifter og andet annoncemateriale markant.
• Lader små teams producere i samme tempo som større, uden at skulle ansætte lige så mange.
• Resultaterne er langt bedre end at bruge Claude eller GPT uden kontekst.

Et par hurtige noter

• Brug Claude i stedet for ChatGPT. Den er bedre til tekstforfatning.
• Jeg kunne bygge disse dokumenter for dig, men det er mere værdifuldt, at du træner AI'en på det, der faktisk virker i din specifikke situation.

Hook-generering i et Claude-projekt

Dette projekt tager emotionelle citater fra din målgrupperesearch og genererer 20+ scroll-stoppende hooks skræddersyet til brandet, både til UGC-scripts og statiske annoncer.

Kontekstdokument til vindende hooks

Indsæt dette i Claude, gem det og brug det som kontekst i projektet, som beskrevet i opsætningsguiden ovenfor.

Domain Context: Static Headlines
Context Document: Writing High-Converting Static Headlines & Image Ads

1. The Role of Headlines in Static Ads
- First job of a headline: Stop the scroll. Attention is the currency.
- Second job: Spark curiosity, relevance, or emotion strong enough to make the user process the rest of the ad.
- Third job: Tie directly to the value prop (clear, specific, visual, and ownable).

Headlines in static ads must do 3 things fast:
1. Communicate the core USP or benefit.
2. Resonate emotionally with the audience's desire or pain point.
3. Be unmistakably different from generic "me-too" claims.

2. Emotional Triggers That Headlines Should Leverage
- Pain Point Relief: "No more chasing invoices."
- Aspiration / Gain: "Turn spare time into income."
- Simplicity / Ease: "From signup to first sale in 5 minutes."
- Fear of Missing Out: "Last chance to lock today's price."
- Authority & Proof: "Trusted by 10,000+ small business owners."
- Curiosity Gap: "The trick gyms don't want you to know."

3. Static Ad Visual Principles (Meta Image Ads)
- Headline-Visual Fit: The visual must reinforce or dramatize the headline claim. Example: Headline: "Save hours every week." Visual: Clock cut in half.
- USP Placement: Top-left or headline text must carry the main USP (it's where the eye goes first). Avoid clutter - prioritize one message per creative.
- Branding: Subtle but present (logo, colors, typography). Don't overpower the message, but ensure recognition.
- Legibility: Short, bold text, high contrast. Static ads are consumed in <2s.
- Product in Use: Show the product solving the pain point, not just isolated packshots.
- Visual Anchors: Icons, arrows, or symbols to draw the eye to the CTA or headline.
- Social Proof & Trust: Layer reviews, ratings, or customer count into the static where possible. Example: "Rated 4.9/5 by 12,000+ users."

4. How to Build a Strong Static Headline
1. Start with the USP: What is the single strongest promise or differentiator? Write it plainly first.
2. Apply the 3 Copy Tests: Can I visualize it? Can I falsify it? Can nobody else say this?
3. Stress-Test with an Emotional Lens: Does this relieve pain, unlock desire, create curiosity, or prove credibility?
4. Trim ruthlessly: Make it digestible in under 3 seconds of reading.

5. Static Ad Structure Framework
- Headline (Primary Text): Short, bold, visualizable, falsifiable, ownable.
- Supporting Visual: Shows the product solving the problem or delivering the promise.
- Secondary Copy (Optional): Expand on proof (social proof, stat, unique detail).
- CTA: Clear, action-driven ("Get started," "Shop now," "Book today").

6. Common Mistakes to Avoid
- Generic claims: "Best quality," "Save time."
- Overloading with multiple USPs.
- Tiny, hard-to-read text.
- Stocky visuals that don't connect to the headline.
- Copy-visual mismatch (e.g., a headline about speed with a static showing relaxation).

7. Checklist for Every Static Ad
- Headline communicates a clear, specific USP.
- Headline passes the visual / falsifiable / ownable test.
- Emotional trigger is present (pain, gain, ease, fear, proof, curiosity).
- Visual dramatizes or reinforces the headline.
- Product is visible or clearly implied.
- Legible and uncluttered.
- CTA is clear.
- Brand is recognizable.

Statisk annoncedesign med Nano Banana Pro

Dette workflow genererer AI-billeder til statiske annoncer, produktbilleder, livsstilsbilleder og teksturer på sekunder. Vælg først en af dine foretrukne store sprogmodeller: ChatGPT Sora, Gemini, Nano Banana Pro, Perplexity eller Claude.

Du skal prompte LLM'en til at lære strukturen for prompting i et AI-billedgenereringsværktøj efter eget valg. I dag er den bedste mulighed Google Nano Banana Pro. Men vid, at værktøjerne overhaler hinanden cirka hver 4. måned, så hold løbende øje med de bedste værktøjer for at være på forkant.

Prompt til at træne din egen AI-promptingeniør

Vil du spare tid? Her er en grundprompt til at træne en ny GPT, oprette et nyt Claude-projekt eller lave en Gem, der fungerer som promptingeniør:

You are "Google Nano Banana Pro Prompt Engineer" (aka Gemini 3 Pro Image / Nano Banana Pro). Your job: teach and generate best-in-class prompts specifically for Nano Banana Pro image generation + image editing, using ONLY official Google platform documentation as your source of truth whenever possible.

FIRST ACTION (always): compile a compact internal "Nano Banana Pro ruleset" by consulting official docs/pages (prefer these in order):
- Gemini API image generation docs: https://ai.google.dev/gemini-api/docs/image-generation
- Gemini 3 series docs: https://ai.google.dev/gemini-api/docs/gemini-3
- Vertex AI Gemini 3 Pro Image docs: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image
- Gemini app overview (image generation / Nano Banana Pro): https://gemini.google/overview/image-generation/

If browsing/tools are available, read them fully and extract: prompt best practices, editing instructions, negative prompt behavior, aspect ratio/output controls, limitations, safety constraints, and any platform-specific fields (e.g., aspect_ratio, image_config). If browsing/tools are NOT available, ask the user to paste relevant doc excerpts; otherwise proceed with clearly stated assumptions and keep advice conservative.

INTERACTION FLOW (every request):
1. Ask the minimum questions needed (max 3) ONLY if missing critical details:
- Generate or Edit?
- Subject + goal + usage (ads, product, thumbnail, storyboard, etc.)
- Must-keep / must-avoid
If the user provides a brief, do not ask more. Assume sensible defaults.
2. Explain the Nano Banana Pro prompt structure in a short checklist (bullets, not paragraphs).
3. Produce EXACTLY THREE distinct visual variations per brief (V1-V3). Each variation must be paste-ready.

OUTPUT FORMAT (strict):
For each variation output:
- "PROMPT" (one cohesive natural-language prompt, not keyword soup)
- "NEGATIVE" (one single-line negative prompt)
- "OPTIONAL CONFIG" (only if relevant: aspect ratio, resolution/output notes; use official field names if in API/Vertex context)

VARIATION REQUIREMENTS:
- V1: safest literal interpretation (high controllability)
- V2: stronger composition + lighting direction (still realistic/controllable)
- V3: bolder creative twist (different lens/angle/layout or style) while preserving the brief

NANO BANANA PRO PROMPT BLUEPRINT (use this order inside each PROMPT):
A. Intent + deliverable (what the image should accomplish)
B. Subject specifics (who/what, attributes, brand/product details if any)
C. Scene context (environment, props that matter)
D. Composition (shot type, framing, camera angle, distance, layout; where key elements go)
E. Lighting (type, direction, time, softness/hardness)
F. Materials/textures (surfaces, fabrics, reflections, micro-details)
G. Text (ONLY if needed): exact wording, font vibe, placement, legibility constraints
H. Hard constraints (must include / must not include; "do not change" clauses)
I. Realism controls (avoid artifacts, keep natural proportions)
J. If editing: explicitly lock what must stay identical (identity, pose, camera, background, product geometry) and specify ONLY the change

EDITING RULES (when the user is editing an existing image):
- Preserve identity, camera perspective, framing, background layout, and unmentioned details.
- Change only what the user requests.
- If the user requests multiple changes, sequence them as ordered steps inside the prompt.
- Add a fail-safe line: "If a requested change cannot be applied cleanly, leave the original unchanged."

TEACHING MODE:
After providing V1-V3, add a compact "How to iterate" section:
- 5 quick knobs (composition, lighting, texture, constraints, negatives) with example micro-edits.
- If the user says "make it better" or "looks AI," diagnose likely causes (5 bullets) and rewrite V1-V3 with stronger constraints and realism cues.

CONSTRAINTS:
- No fluff, no marketing chatter.
- Prefer explicit controllable language over vague style names.
- Always include a NEGATIVE line.
- Always deliver exactly three variations unless the user explicitly asks for a different number.

Sådan arbejder du med det i hverdagen

Når din tilpassede "promptingeniør"-AI er sat op, så brug et værktøj som Wisperflow.io eller MacWhisper til at transskribere dine idéer eller briefs til tekst uden at skulle taste dem. Det sparer dig for meget tid i det lange løb.

Din idé skal beskrive scenen, du prøver at skabe, så detaljeret som du overhovedet kan: kameravinklen, realismeniveauet, hvilket kamera der bruges, hvor mange personer der skal være i scenen, hvilken etnicitet personerne på billedet skal have, lokation, tidspunkt på dagen, årstid, hvor fyldt scenen skal være, hvilken farvegradering billedet skal have, og så videre.

Hvor mange prompts skal du prøve? Start med 4 tekstprompts baseret på din brief, og test hver prompt 3 gange i dit foretrukne billedgenereringsværktøj. En enkelt billedidé bør derfor have cirka 12 billedgenereringer, så du kan vælge det bedste resultat til dine annoncer.

Altså: du laver prompt-AI-ingeniøren og forklarer, hvad du har brug for. Den laver en prompt til dig. Den prompt laver billedet.

Kom videre med Curve

Vil du se, hvad disse workflows producerer, når de rammer annoncekontoen? Se vores cases, blandt andet Collagenhund og Sneglefellen.

Vil du have vindende annoncemateriale lavet for dig, så tag et kig på street interview ads og UGC, eller læs flere guides på bloggen.

Ofte stillede spørgsmål