Skip to main content
Use this page when the Studio starter prompt or user request asks Veryfront Agent to research a topic.

​
Agent-facing flow

  1. Load the Veryfront router skill: load_skill({ "skillId": "veryfront" }).
  2. Load this page as the canonical docs resource for the task.
  3. If the request is broad, ask exactly one short form_input with one required brief field, then continue from the submitted brief. The starter text is routing intent, not the research brief.
  4. Gather evidence from project files, project docs, live tools, and approved external sources when the task requires them.
  5. Separate facts from inference and cite sources or file paths for claims that matter.
  6. For the bare Studio “Make a research” starter, save the research report as Markdown under research/ with create_file or update_file when file tools are available. Choose a concise slug from the submitted brief for the file name.
  7. For other research requests, save the report when the user asks for a file or gives an exact path.

​
Guardrails

  • Do not load a removed research sub-skill.
  • Do not treat the starter label, generic starter prompt, or storage location instruction as the research topic.
  • Do not fall back to generic project inspection when the user asked for a specific research topic.
  • Do not self-delegate on the first turn unless isolation materially improves the sourced research path.
  • Do not create app, page, route, or chat UI files for a research-only request.
  • Do not finish the bare Studio starter with inline-only output when file tools are available.
  • Do not call a report grounded when the saved artifact lacks stable links, file paths, or tool references for material claims.

​
Example pattern

Keep research examples about AI agents, but avoid fake citations. Show the artifact shape and the evidence questions the agent should answer. 
<!-- research/agent-tool-approval-patterns.md -->
# Research: Agent Tool Approval Patterns

Research brief: Compare practical patterns for deciding when an AI agent can call tools automatically and when it should ask for human approval.

## Questions

- Which tool actions are safe to run automatically?
- Which actions require user approval because they change external state?
- What evidence should the agent show before asking for approval?
- How should failures and partial tool results be reported?

## Evidence to gather

- Project agent instructions and existing tool-access rules.
- Product docs for skills, resources, tools, and agent creation.
- Approved external references when the project evidence is not enough.

## Resources

- `AGENTS.md`: Project-level rules for tool use and verification.
- `/agent/guides/create-agent`: Current project-agent creation and tool-selection guidance.
- `/cloud/mcp/tools/create-agent`: MCP schema for creating project agents.

## Output

- A short recommendation for default approval boundaries.
- A risk list for destructive or externally visible tool calls.
- Verification gaps where the project needs more product telemetry or policy detail.
In the MCP tool call, path is the saved research path and content is the Markdown artifact. The saved artifact must include stable resources before final notes or open questions.

​
Output shape

For the bare Studio starter, return the saved file path plus a short evidence-backed summary. For other research requests, return a short research brief with answer, evidence, recommendations, resources, open questions, and verification gaps.