Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.daoco.org/llms.txt

Use this file to discover all available pages before exploring further.

Inside brand chat, questions that need outside information can launch a research card. Research runs in the background, gathers evidence from public sources or connected accounts, and returns a sourced report directly in your chat thread. Research is one specialist capability inside brand chat. It covers two broad lanes:
  • External public research for LinkedIn profiles, company pages, websites, public social posts, competitors, markets, and topical trends.
  • Connected account insights for first-party performance analysis across your linked social accounts.
See Assistants and slash commands if you want a quick overview of how specialists and slash commands work together.
Research uses basic tokens. Each research subagent starts at 1 basic token, then adds another basic token for roughly every 50,000 model tokens it consumes.

​
External public research

External research searches the internet for information relevant to your question. It can inspect a specific page, review a public LinkedIn profile, analyze a public social post, or search broadly across the web and return a sourced report. How to trigger it: Ask about a person, company, website, competitor, trend, news cycle, or any other public topic that requires up-to-date external information. 
Review this LinkedIn profile and tell me which outreach angle fits best for daoco: https://www.linkedin.com/in/example/

Review https://www.example.com/pricing and summarize how they position themselves against workflow tools.

Research the top 3 trends in sustainable fashion this week and show me a summary with sources.

What are my competitors doing on Instagram in the fitness space? Find recent examples.
You can focus research on a specific domain or website by mentioning it in your prompt. 
Search techcrunch.com for recent articles about AI-powered marketing tools.

​
Connected account insights

Connected account insights analyze your linked social media accounts — engagement rates, top-performing posts, content patterns, and audience trends. How to trigger it: Ask about your own account performance on any connected platform (X, Instagram, LinkedIn, YouTube, and others). 
Analyze my Instagram account performance and give me insights on what's working.

What are my top-performing posts on X this month?
You must have a platform connected before the assistant can analyze it. See Connect platforms to link your accounts.

​
Reading research cards

When research runs, a research card appears in your chat thread.

​
Card header

  • Icon: Globe icon for external research, chart icon for connected account analysis.
  • Status badge: Shows the current state of the research.
  • Elapsed time: How long the subagent has been running.
  • Token usage circle: Shows the basic token usage for that research run.

​
Status badges

BadgeMeaning
ResearchingThe subagent is actively searching or analyzing.
CompletedResearch finished successfully. Expand to read the report.
FailedSomething went wrong. Retry or adjust your prompt.
InterruptedThe subagent stopped unexpectedly. Try again.

​
Collapsed and expanded views

  • Collapsed: Shows the status badge, a brief preview of what the subagent is doing, and elapsed time.
  • Expanded: Click to expand and see the full research transcript, including searches, page fetches, LinkedIn/profile lookups, and intermediate findings.

​
Report and citations

Once research completes, the card footer shows:
  • Research report: The full findings, collapsible for easy scanning.
  • Citations: Source links for external research. Click any citation to visit the original page.
  • Copy button: Copy the report text to your clipboard.

​
Aggregate reports

When one request triggers multiple research steps — for example, comparing competitors or analyzing performance across platforms — the assistant can synthesize them into a single aggregate report. The aggregate report includes:
  • Cross-platform overview combining all findings.
  • Platform comparison (engagement, content types, audience).
  • Top-performing content across sources.
  • Strategic recommendations based on the combined data.
Citations from all individual reports are deduplicated and listed together. 
Compare my X and Instagram performance side by side and give me a unified strategy.

​
Tips

  • Be specific about your research goal. “Research sustainable fashion trends in the US market for Gen Z” gives better results than “research fashion.”
  • Use URLs or domains when you have them. Mention a specific LinkedIn profile, page, post, site, or domain to narrow results.
  • Ask for cross-platform analysis when you have multiple accounts connected to get aggregate insights.
  • Watch the token circle. A simple research run usually starts at 1 basic token. Larger multi-source or multi-agent research can cost more as the reports grow.

​
Billing notes

  • Research uses basic tokens, not premium tokens.
  • Each research subagent starts with a 1 basic token charge.
  • Larger research runs add 1 basic token for roughly every 50,000 model tokens consumed.
  • Trial accounts use the same research pricing, counted against the monthly Starter Trial basic tokens.
For full billing details, see Understand token usage.

Brand chat

Learn the full chat workflow including attachments and prompts.

Understand token usage

See how basic and premium tokens are consumed.