research
continuous-research
Runs recurring research cycles in OpenAI, DeepSeek, Perplexity, or Tavily and maintains a scored knowledge base.
Run recurring research cycles against configurable domain configs. Each cycle discovers new entries, scores them through a weighted quality gate, compares against the previous knowledge base, and writes an updated KB with a change delta.
How it runs
- Load domain config + previous KB
- nlm-skill → deep research (50-70 sources)
- Import & query NotebookLM notebook
- Map entries → score with calibrated rubric
- Delta detection vs previous cycle
- Review findings, adjust weights
- Write KB + changelog + briefing
Why it matters
- 32× faster
- Change detection between cycles
- Weighted scoring surfaces what matters
What it needs
- domain-id — loaded from your vault context
- domain-id-changelog — loaded from your vault context
- domain-id-kb-latest — loaded from your vault context
What you get
- domain-config (markdown)
- kb-latest (markdown)
- quick-scan-results (markdown)
- reranked-results (markdown)
- research-all-report (markdown)
- research-cycle-report (markdown)
- research-report-pdf (pdf)
Ask it like this
- Run a research cycle for the procurement-ai domain
- Set up a new research domain to monitor competitor AI tools in logistics
- What's new in the procurement-ai knowledge base since last cycle?
- Run all overdue research domains
- Generate a PDF report from the latest procurement-ai KB
