Write a Pulse article (server pipeline)
flypost_generate_articleFinal step of Flypost's own long-form writer: write the full article from its brief, blocking up to ~20 minutes. Prefer flypost_save_article when you can write the article yourself — it is faster and costs the user nothing. Normally run flypost_prepare_article and flypost_outline_article first; with only a topic it creates the article and writes it straight away. Pass feedback to refine an existing body, which it replaces. Always set target_query: it steers the writer and is what keyword tracking reports on. The article keeps the type set at prepare (article_type); pass it here only when creating straight from a topic.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "flypost_generate_article"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| angle | No | ||
| topic | No | Topic for a new article when article_id is omitted. | |
| feedback | No | Improvement feedback on the current body. | |
| article_id | No | ||
| project_id | No | Project id; omit for the active project. | |
| notebook_id | No | Write from ONE notebook: the brief, outline and article retrieve only from its sources. Pass the source_package_id that flypost_create_notebook returns (or a notebook id from flypost_list_sources). Typical flow when you did the research yourself: flypost_create_notebook, then save each finding with flypost_add_source_url or flypost_add_source_text (one source per tool or page you researched), then flypost_prepare_article with notebook_id and research_mode "source". For a roundup, everything comes from the notebook: save a source per tool (your own company and, for "X alternatives", X itself included), with the tool named in its title or saved from its own site so it can be matched. With research_mode "source" a tool the notebook does not cover is left out. Set on a new article, or moves an existing one onto that notebook. | |
| article_type | No | The article format. guide (default): explains how or why in 4-7 sections ("how to measure share of voice"). list: numbered points, one per H2, count taken from the brief ("10 questions to ask an agency", "a 25-point checklist"). roundup: "best X for Y" written by the author in the first person as having tested the tools ("I tested 8 Taplio alternatives: here are the best"), one H2 per entry with the same sub-structure, a how-I-chose section, a comparison and an FAQ; every entry is researched first (from the notebook when notebook_id is set, else one web search per entry) and only sourced facts are used, so it takes longer. Match it to target_query. Omitted on a new article = guide. | |
| target_query | No | The exact search query the article is trying to rank for, e.g. "what is an impression on linkedin". Steers the writer's retrieval and prompts, and is the keyword the app's rankings report tracks. Sets it on a new article, or updates it on an existing one. | |
| research_mode | No | source: ground only on the Brain (or on notebook_id when given). online: also research the web. With notebook_id, source keeps the article to that notebook with no web search at all; online adds fresh web stats and, for a roundup, web research for whatever the notebook does not cover (entries, the tool being replaced). A roundup with no notebook should use online: its entries need live pricing and features. |