Skip to content
Download for Mac

Built-in Agents

QARK ships with a default agent and a set of built-in agents organized into two tiers: orchestrator agents that you invoke directly, and tool agents that orchestrators dispatch as sub-agents.

Every conversation that has no explicit agent assigned uses the default agent. This is not a built-in agent in the gallery — it is a hardcoded system prompt that provides baseline behavior:

  • Responds with markdown formatting (headings, lists, tables, code blocks with language identifiers, LaTeX math)
  • Direct and concise communication — leads with the answer, matches depth to question complexity
  • Technical accuracy: working code examples (not pseudocode), version numbers, specific function names
  • Problem solving: numbered steps for complex problems, starts debugging with the most likely cause
  • Conversation-aware: references earlier messages, adapts when the topic changes

The default agent inherits whatever model, tools, and context strategy the conversation is configured with. To override its system prompt, either assign a custom agent or add a conversation-level system prompt override in the Config tab (append or replace mode).

Built-in agents carry an is_builtin flag:

  • Read-only — the system prompt, tool selection, model assignment, and parameters are locked
  • Persistent — built-in agents survive updates. They are never removed by an upgrade, but their definitions update automatically if the shipped configuration changes
  • Duplicatable — select any built-in agent and choose Duplicate to create an editable copy with all the original’s settings

To customize a built-in agent, duplicate it first. Your copy is fully editable — change the system prompt, swap the model, add or remove tools, rename it. The original remains untouched.

These are full agents you assign to conversations. Each dispatches specialist tool agents to complete multi-step workflows.

Icon / Color🔬 #dc2626 (red)
Toolsthinking, web search, web fetch
Sub-agentsQuery Decomposer, Web Researcher, Source Deep Diver, Fact Verifier, Comparative Analyst, Report Synthesizer

Breaks a research question into sub-queries, dispatches specialists to search the web, deep-dive into sources, verify facts, run comparative analysis, and synthesize a final report.

Icon / Color💼 #8b5cf6 (purple)
Toolsweb search, document search, image generation
Sub-agentsResearch Analyst

Coordinates research with document analysis. The Research Analyst sub-agent has its own sub-agent (Fact Checker), creating a two-level delegation chain.

Icon / Color📖 #0891b2 (cyan)
Toolsthinking, combine files, save paper PDF
Sub-agentsCodebase Analyzer, Web Researcher, Academic Researcher, Paper Outliner, Section Writer, Paper Editor, Citation Formatter

Analyzes a codebase, researches related academic work, and produces a structured paper with sections, citations, and PDF output.

Icon / Color📑 #7c3aed (violet)
Toolsthinking, combine files, save paper PDF
Sub-agentsWeb Researcher, Academic Researcher, Source Deep Diver, Paper Outliner, Section Writer, Paper Editor, Citation Formatter

Researches a topic across web and academic sources, then produces a review article with proper structure, citations, and PDF export.

These agents have agent_type: "tool" — they are designed to be called by orchestrators or other agents, not invoked directly. Each has typed input/output schemas and focused tool access. See Agent-as-Tool for how tool agents work.

AgentIconColorToolsPurpose
Query Decomposer🧩#6366f1thinkingBreaks complex questions into targeted sub-queries
Web Researcher🔍#0ea5e9web search, web fetch, thinkingSearches the web and synthesizes findings
Academic Researcher🎓#7c3aedweb search, web fetch, thinkingSearches for academic papers and scholarly sources
Source Deep Diver🤿#14b8a6web fetch, thinkingExtracts detailed information from specific URLs
Fact Verifier#22c55eweb search, web fetch, thinkingCross-references claims against multiple sources
Comparative Analyst⚖️#f59e0bweb search, web fetch, thinkingCompares alternatives across defined criteria
Report Synthesizer📝#8b5cf6thinkingCombines findings from multiple agents into a coherent report
Fact Checker🛡️#10b981web search, web fetchVerifies factual claims (used as sub-agent by Research Analyst)
Research Analyst🕵️#3b82f6web search, web fetch, document search, + Fact CheckerConducts research with built-in fact-checking via its own sub-agent
Codebase Analyzer🔎#06b6d4unix commands, document search, thinkingAnalyzes code structure and patterns via filesystem tools
AgentIconColorToolsPurpose
Paper Outliner📋#8b5cf6thinking, unix commands, document searchGenerates structured paper outlines from research material
Section Writer✍️#f59e0bthinking, unix commands, document searchWrites individual paper sections from outlines
Paper Editor📝#10b981thinking, unix commandsEdits and refines paper drafts for coherence and style
Citation Formatter📚#6366f1thinking, unix commandsFormats references and citations in proper academic style

Tool agents reference each other using the format agent_tool:@Agent Name. During seeding, these names are resolved to UUIDs. This means:

  • The Research Analyst has Fact Checker as a sub-agent — a built-in two-level chain
  • The Deep Researcher orchestrates 6 tool agents in a single workflow
  • The Codebase Paper Writer coordinates 7 tool agents across research, analysis, and writing phases

To create your own variant:

  1. Open the agent gallery
  2. Select the built-in agent
  3. Choose Duplicate — a new editable agent appears with “(Copy)” suffix
  4. Modify any field — system prompt, tools, model, parameters, icon, color
  5. Rename and save
Starting fromCustomizationResult
Deep ResearcherRemove comparative analysis, add document searchFocused Document Researcher
Codebase Paper WriterSwap Academic Researcher for custom internal-docs agentInternal Architecture Documenter
Web ResearcherAdd MCP tools for internal databases, restrict to company domainsInternal Knowledge Researcher
Report SynthesizerChange output format to executive summary styleExecutive Briefing Agent