How generation works
How the service turns a topic or a found item into a ready post: text, image, model and key selection.
1Two generation paths
“From sources” — the service takes a found item and rewrites it for your brand. “From the model’s knowledge” — a post is created on the day’s topic without an external source (facts, date references). Holiday greetings are generated separately.
2Choosing text and image models
In “Project info” → “Generation models” you pick the text model and the image model separately. Models are grouped by provider country. “Auto” picks the first available provider (by key availability).
3Keys: your own or the service
In “My keys” mode your personal API keys from the profile are used (stored encrypted). Subscription service keys are planned. If no suitable key is set, the service uses another available provider or the local mode.
4Custom model (OpenAI-compatible)
You can set your own endpoint, model name and token right in the project settings — for text and/or images. Any server with an OpenAI-compatible API works. Pick “Custom model” in the model list and fill in the fields in the project card.
5Context the model sees
The prompt includes: tone of voice, audience, forbidden topics, marketing context and extra instructions, the text of uploaded context files (.md/.pdf), the plan’s language and region, and — for “from the model’s knowledge” posts — the date, weekday and the day’s topic. The more precise your project settings, the better the result.
6Images and format
The image is generated in the channel’s social-network format (e.g. 1:1 for Telegram, 9:16 for Shorts). Your brand visual style from the project settings is added to every image prompt so all images stay consistent.
7If there are no keys or the model is unavailable
The service doesn’t fail: text is written by a local deterministic rewriter, and a gradient placeholder with a caption is used instead of an image. This way demos and tests work entirely without keys — only the quality will be template-like.
8Model request log
Every real call to a model (with the actual request and response) is visible in the “Model requests” section — handy to check exactly what was sent and what the model returned.
9Exact model name (Opus / Sonnet, etc.)
In “Project info” you can set the exact model name for text and images (e.g. claude-opus-4-… instead of Sonnet, or gpt-4o). Take the name from the provider console; empty means the current default model is used. Handy when a provider has several tiers (Opus/Sonnet/Haiku) or a new model ships — the list never goes stale.
10Generation limits (cost control)
To control model spend, the project settings let you set limits: a maximum number of drafts per 24 hours and per 7 days (0 = unlimited). When a limit is reached, generation (both manual and scheduled) pauses until the window passes; current usage is shown next to the fields. It counts generated drafts (from the worker log) — deleting a post does not refund the quota.
11Language of posts and images
The post language is set in “Plan”; the model is explicitly told to write the title and body strictly in that language, and the image prompt requires any lettering to be in the same language.
Didn't find an answer? Write to us — we'll help.
Contact support