Skip to main content

Multi-Agent Research Workflow

Execute comprehensive competitive research using coordinated subagents.

System Prompt​

⚠️ EXECUTION DIRECTIVE: When the user invokes this command, you MUST:

  1. IMMEDIATELY execute - no questions, no explanations first
  2. ALWAYS show full output from script/tool execution
  3. ALWAYS provide summary after execution completes

DO NOT:

  • Say "I don't need to take action" - you ALWAYS execute when invoked
  • Ask for confirmation unless requires_confirmation: true in frontmatter
  • Skip execution even if it seems redundant - run it anyway

The user invoking the command IS the confirmation.

Usage​

/multi-agent-research [competitor-name] [research-focus]

Workflow​

When this command is invoked:

  1. Use the competitive-market-analyst subagent to gather primary competitive intelligence
  2. Use the web-search-researcher subagent to collect external market data
  3. Use the thoughts-analyzer subagent to review existing internal research
  4. Use the business-intelligence-analyst subagent to synthesize strategic insights
  5. Use the qa-reviewer subagent to validate findings against AZ1 standards

Output​

  • Comprehensive competitive analysis report
  • Multi-source validated insights
  • Strategic positioning recommendations
  • AZ1 compliant documentation

Execute all agents in parallel where possible for maximum efficiency.​

Action Policy​

<default_behavior> This command analyzes and recommends without making changes. Provides:

  • Detailed analysis of current state
  • Specific recommendations with justification
  • Prioritized action items
  • Risk assessment

User decides which recommendations to implement. </default_behavior>

After analysis, provide: - Analysis completeness (all aspects covered) - Recommendation confidence levels - Specific examples from codebase - Clear next steps for user

Success Output​

When multi-agent-research completes:

✅ COMMAND COMPLETE: /multi-agent-research
Target: <competitor-or-topic>
Agents: 5 coordinated
Sources: N validated
Insights: N strategic
Report: Generated

Completion Checklist​

Before marking complete:

  • All agents executed
  • Sources validated
  • Insights synthesized
  • Report generated
  • Recommendations provided

Failure Indicators​

This command has FAILED if:

  • ❌ No research target
  • ❌ Agents failed
  • ❌ No validated sources
  • ❌ Report not generated

When NOT to Use​

Do NOT use when:

  • Simple web search sufficient
  • Internal codebase only
  • Single-source research

Anti-Patterns (Avoid)​

Anti-PatternProblemSolution
Skip validationBad sourcesAlways use qa-reviewer
Sequential executionSlowRun agents in parallel
No synthesisRaw dataUse business analyst

Principles​

This command embodies:

  • #9 Based on Facts - Multi-source validation
  • #3 Complete Execution - Full research workflow
  • #6 Clear, Understandable - Clear insights

Full Standard: CODITECT-STANDARD-AUTOMATION.md