Files
crimson_leaf_publishing/templates/ai_article_research.yml
David Baity 1f811e98e1 fix(clp): genericise templates — no hardcoded agents/companies/task-types
- planning.yml: roster-driven task types, no hardcoded agent names or generic types
- chapter_roundtable.yml: removed fixed [Devon,Lane,Cora] participant list, any editor can join
- book_chapter.yml: removed hardcoded agents from roundtable spawn
- book_research.yml: removed agent: Atlas from book_outline spawn (Bouncer routes by type)
- ai_article_research.yml: removed agent_name: Atlas from plan spawn
- book_editorial.yml: removed Shadow Heir/Elara/Kai/Alpha Publishing/Wattpad hardcoding
- project_index.yml: removed Wattpad reference
- ai_article_write.yml: fixed adjudication criteria (article, not fiction chapter)
- chapter_review.yml: reply→document so reviews are committed and accessible

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-12 01:34:36 -04:00

95 lines
2.6 KiB
YAML

name: ai_article_research
description: "Research the article series topic — live search + synthesis + spawn article plan task."
debug: true
system: agent_prompt
agent_prompt:
- "= identity.md"
- "agent.rag.json"
sections:
- agent
- project
- history
- rag
- prior_results
- message
- instructions
builders:
prior_results: |
*** WEB SEARCH RESULTS ***
{steps[1].text}
(If the above is empty, use your expert training knowledge.)
steps:
- type: think
hint: |
Read the project description and the message above carefully.
Identify the best search query to find current, real-world information on this topic.
State your reasoning, then on the last line write:
SEARCH QUERY: [your query here]
Query rules: 3-8 words. Specific. Current year preferred.
- type: tool
capability: Tool_WebSearcher
input_from: last_text
- type: think
hint: |
Using the search results above (or your training knowledge if unavailable), write a
RESEARCH BRIEF on the topic from the project description.
Cover as many relevant angles and subtopics as you can find real evidence for.
For each angle: what is happening, what problem it solves, one concrete result.
End with a SERIES RECOMMENDATION section proposing exactly 10 article topics.
For each topic: working title, target reader, the one thing they will learn.
- type: document
filename: "{{task_name_slug}}"
- type: package
packet_type: IntakeResponse
hint: |
Create exactly ONE follow-up task.
- task_name: "Plan Article Series"
- task_type: "ai_article_plan"
- description: "Using the research deliverable, plan exactly 10 standalone articles for
this series. Each article is a 5-minute read (~800-1000 words) for the target audience
described in the project. You choose the topics based on the research. Then spawn 10
ai_article_write tasks."
- depends_on: ""
schema:
actions:
- type: create_task
task_name: "string"
agent_name: "string"
task_type: "string"
description: "string"
depends_on: "string"
- type: close
rag_update: true
adjudication:
enabled: true
pass_threshold: 65
deliverable_type: coordination
criteria:
accuracy:
weight: 35
description: "Facts are correct and verifiable"
thoroughness:
weight: 30
description: "Topic covered in sufficient depth"
source_quality:
weight: 20
description: "Sources are credible and relevant"
organization:
weight: 15
description: "Findings are well-structured"