Working with prompts

How to create and configure a prompt that instructs Aimée to write ad copy, AI-discovery content, or generate lifestyle images and videos for your products — including scoping, model choice, credit estimates, and why a prompt skips some products.

Updated October 3, 2026

Prompts instruct Aimée how to create content for each of your products — from ad copy and headlines to AI-generated lifestyle images and videos. After you connect a catalog, you'll typically have a few prompts already set up, which you can adjust as needed — for example to change the tone of voice, focus on different product aspects, or add a new content type.

Prompts live on a project. Open a project, go to its Creative tab, and use the Prompts section to create one or open an existing one. A prompt runs for every catalog in its project — if you want it to apply to only some of them, narrow it under Use as rather than looking for a per-catalog prompt list, which no longer exists.

Creating a prompt#

Click Create prompt and pick a Type of prompt to start from. Each type pre-fills instructions and sets a default content category, so you're rarely starting from a blank page.

Type of promptWhat it produces
Write descriptionsAd copy
Write descriptions by looking at the product imageAd copy, written from the product image rather than existing text
Write headlinesHeadline
Write reason to buysReason to buy
Write product titlesProduct name
Write text-to-voice scriptsVoice script
Write product highlights (AI discovery)Short benefit lines, tagged ai-highlights
Write enriched descriptions (AI discovery)A fuller factual description, tagged ai-description
Write use cases (AI discovery)Short "good for" phrases, tagged ai-use-cases
Generate lifestyle imagesAn AI-generated lifestyle image
Generate lifestyle videosAn AI-generated video
Animate lifestyle images to videoAn AI-generated video, using an existing lifestyle image as its source
Custom promptAd copy, starting from a blank instruction

The three AI discovery types write extra product content for Google's AI shopping surfaces. They work like any other text prompt — they only describe what your product data already says, and they're fact-checked — but their output comes pre-tagged, so a channel field can ask for exactly that content and nothing else. Because the tags keep them apart, adding them doesn't change or replace the copy your existing prompts already produce. These are one part of a three-part setup — see AI discovery on Google for the whole thing, including what it does and doesn't do for you.

The lifestyle image, lifestyle video and animate types are AI image and video generation — a newer capability alongside the text and image-captioning prompts. See AI image and video generation for how these work and how the result reaches your templates.

When prompts run#

Prompts execute automatically whenever Aimée processes a product:

  • The first time you set up a project, Aimée processes all its products.
  • When new products appear in your feed, they're imported, processed, and appear in your channels as soon as possible.
  • When a product changes — its description, images, price, and so on — Aimée reprocesses it and updates any affected channels.
  • When you publish a prompt — new or edited — every product in its scope is reprocessed within minutes, so the change reaches products that were already processed too. Publishing an active prompt spends credits on every product in scope.

Turn a prompt off with the Activate prompt toggle and publish, which stops it from running from then on.

Why a prompt skips some products#

A prompt can only write for a product that has the content it asks for. When a product doesn't have it — the field a placeholder reads is empty, or the prompt asks for a Product image and none of the product's images are processed — the prompt generates nothing for that product. Content the prompt generated for that product earlier is removed, so nothing it made from content the product no longer has stays in your ads. That includes images the prompt generated earlier, even ones you approved: an approval doesn't keep an image the prompt no longer produces. If the prompt later produces the same image again, it comes back approved. A skipped product spends no credits.

A product whose image is still downloading, or still being processed, isn't skipped: the prompt waits, and generates once the image is ready. The same goes for a feed image the prompt reads through Image link or Additional image link that Renable hasn't fetched yet: Renable fetches it the first time the prompt needs it, and the prompt generates for the product once it has arrived — see When a template or prompt first uses a feed image.

The warning on the prompt#

When a prompt skips products, it carries a warning titled Skips N feed items — prompt name (for example "Skips 1,204 feed items — Lifestyle headline"). You'll find it in the notes and events at the bottom of the prompt's page, in the dashboard's Needs attention queue, and as the prompt's status dot on the project's Overview and Creative tab. N counts feed items, not products: a feed item is one product in one catalog, so a product sold in three markets is three feed items. A prompt writes separately for each catalog, so a product can be skipped in one market while the prompt still writes for it in another — see Feed items and products.

The warning names each input the products are missing, how many feed items, and why — for example:

Product image — 1,180 feed items: None of this product's images are processed: neither the catalog's Image processing settings nor a Process images rule covers them.

Description — 24 feed items: The product has no value for this.

It lists up to five inputs, the one affecting the most feed items first, and ends with what helps for each reason — for example "Where images aren't processed, turn on processing for them in the catalog's Image processing settings or with a Process images rule. Or add a fallback to the placeholder: Product image, else Image link." The reason is worded the same way in the warning, here, and when you ask Aimée:

The warning saysWhat it means
The product has no value for this.The field the placeholder reads is empty for these products.
None of this product's images are processed: neither the catalog's Image processing settings nor a Process images rule covers them.The prompt asks for a processed image, and the catalog doesn't process these products' images.
This product has no Lifestyle image. (or whichever kind the placeholder asks for)Their images are processed, but none is in that category.
Categorize images is off for this product, so none of its images is categorized as a Lifestyle image.With Categorize images off, every processed image counts as a Product image.
This product has no images.The feed lists no images for these products.
The image could not be downloaded.Renable couldn't fetch the image from your website — see Why can't my images be retrieved?
The image host isn't answering Renable's downloads right now, so the image hasn't been downloaded yet.The website or CDN hosting these images has stopped answering Renable's downloads, and the catalog shows the warning Your image host isn't answering Renable's downloads — see that section.
The product has a matching image, but it was rejected, hidden by a tag, or left out by the placeholder's settings.An image of the right kind exists, but the placeholder isn't allowed to use it.
The source image did not resolve to one of the product's images.The prompt's source image must be one of the product's images.

How to fix it#

The warning's last lines say which of these fits each reason.

  • Process those images — when the products' images aren't processed. Turn on Categorize images or add a step in the catalog's Image processing settings, or add a Process images rule for these products. See Image background removal and classification. Or add a fallback to Image link if the feed's own photo will do: in a prompt, Image link is Renable's own copy of that photo, which Renable fetches the first time the prompt needs it.
  • Add a fallback to the placeholder — when the products have processed images but none the placeholder can use (another kind, rejected, or left out), or when a value is empty. Click the ⋮ menu at the end of the expression and choose Add fallback; for an image, Product image, else Image link uses the feed's own photo when there's no processed image of the right kind. Publish the prompt afterwards.
  • Fill in the missing value — in your source feed, or with a rule on the catalog.
  • Let the image download — an image that couldn't be downloaded is tried again automatically, and the prompt generates once it arrives. If it keeps failing, see Why can't my images be retrieved?
  • Wait for the image host — when the image host isn't answering. There's nothing to change in Renable: it keeps trying, and the prompt generates once the image downloads. A fallback to Image link doesn't help here, since that photo comes from the same host.
  • Leave those products out of the prompt — narrow the prompt's scope under Use as, for example to a product set without them.

Renable doesn't keep retrying skipped products. They're generated for as soon as they have what the prompt needs — after you publish the fix, or when the missing image or value arrives.

The warning keeps itself up to date: its count follows as products are reprocessed, usually within a minute or two, and it's re-checked once a day, so products that leave your feed or a catalog you archive drop out of it within a day. It ends on its own once no product is skipped, and when you switch the prompt off and publish. If you archive the warning, its status dot clears and it stays archived while the number changes; if it ends and then comes back, it can come back archived too. Tick Show archived events in the events filter to see it again.

Content generation blocked#

Content generation blocked — prompt name is a different warning: the prompt can't generate for any product, because of something in the prompt itself rather than in your products. Its text says what, for example "It is empty for every product, so the prompt cannot generate for any of them." (an instruction or step with nothing in it) or "This model needs a source image, and the prompt has none." Fix the prompt — or switch it off — and publish.

The prompt editor#

  • Description — a free-text note for your own reference; doesn't affect what Aimée does.
  • Instructions — the system prompt: tell Aimée what task to do, in natural language, much as you'd brief a freelance copywriter. Prompts default to English, but you can write in your own language — either way, include an instruction to write the output in the product's native language.
  • Steps — one or more input steps that supply the product information Aimée should use. Each step contains Product info placeholders (like Title or Description) rather than literal text — the actual values are filled in per product when the prompt runs. Click the icon on a step to toggle it between Input and Example response; use "Add prompt step" / "Delete prompt step" from a step's ... menu to build multi-step prompts. See Advanced prompting techniques for what multi-step prompts unlock.
  • What to avoid — a negative-prompt field, shown only when you've selected a video-generation model that supports it. Use it to steer the model away from unwanted elements (extra text, wrong setting, and so on).
  • Generated content — a live preview area that shows output as it streams in during a test run.

Fact-checking#

Aimée can sometimes write things that sound plausible but aren't actually backed up by the product's information. Turn on Automatically fact-check the results (in Advanced) to run every output through a second check that verifies claims against the product data before accepting it. You can customize the Fact-checking instructions, choose a Fact-checking model, and optionally supply a Regular expression to match for falsehoods (case insensitive) to catch specific red-flag phrasing.

Use as#

This accordion controls where the resulting content is used and how it's tagged — which catalogs, projects, product sets, languages, content categories, and tags it applies to. Use it to scope a prompt narrowly (for example, only for one product set) or to tag its output so a specific template placeholder or channel field can target it.

Advanced#

  • Model — choose which AI model runs the prompt. Renable offers a range of models across text, image, and video, from fast and economical options to more capable or premium ones. Pick a faster, cheaper model for high-volume, straightforward tasks, and a more capable model when quality matters more than cost. Which models are offered here changes over time as new ones become available — Renable keeps this list current for you.
  • Aspect ratio, Resolution, Duration, Looping video — shown only when the selected model generates images or video; the options presented depend on the specific model chosen.

Previewing and generating#

Use the Search for product to preview field to find a product and run the prompt against it before rolling it out. The button reads Generate while idle and Cancel while a run is in progress. For multi-step prompts, you can inspect the input and output of each step individually — useful for debugging why a prompt isn't producing what you expect.

Once a run completes, Renable shows an estimated cost — "It will cost about N credits to apply this prompt to the M products in the [scope]" — before you commit to running it at scale. Use this to sanity-check cost, especially for image- and video-generation prompts, which typically cost more per product than text prompts. See Understanding credits for how credits work.

Related articles#