Skip to main content
reopt Handbook
reopt Handbook
Vercel Enterprise AI Platform

Platform Foundation

Platform ArchitectureAI SDK RuntimeAI Gateway Control Plane

Execution Runtime

Workflow Durable ExecutionSandbox Tool RuntimeMCP Enterprise DataQueues and Async Jobs

Prompt and Quality

Prompt Engineering and GuardrailsRAG and Retrieval-Augmented GenerationObservability and Evaluation

Operations

Security GovernanceCost and ReliabilityDeployment and AI CI/CD

Scenarios

Customer Support Agent ArchitectureInternal Research Agent ArchitectureApproval Backoffice AutomationCoding Orchestration

Orchestration Patterns

Graph-Centric OrchestrationPractical Orchestration PlaybookMulti-Agent Architecture

Appendix

Migration GuideReferencesVerificationUpdates
Handbook›Vercel Enterprise AI Platform›Internal Research Agent Architecture
한국어English

Internal Research Agent Architecture

Build internal research agents for long analysis, artifacts, approval, and source tracking.

Key takeaways

  • Internal research agents work best when they produce inspectable artifacts, preserving sources, assumptions, intermediate steps, and final recommendations.
  • The design pattern moves through brief, plan, collect, analyze, artifact, and review stages.
  • Use Workflow for long-running research and Sandbox for file generation or code analysis.
  • Use MCP for permission-aware internal sources and Gateway routing for cost and quality classes.
  • Store artifacts with stable IDs and source references so outputs stay traceable.

Internal research agents are best when they produce inspectable artifacts, not just long answers. They should preserve sources, assumptions, intermediate steps, and final recommendations.

Design Pattern

StageOutput
BriefQuestion, scope, sources, deadline
PlanResearch steps and assumptions
CollectSource notes and extracted facts
AnalyzeComparison, synthesis, risks
ArtifactMemo, table, deck outline, or dataset
ReviewHuman comments and follow-up tasks

Runtime Choices

  • Use Workflow for long-running research.
  • Use Sandbox for file generation or code analysis.
  • Use MCP for permission-aware internal sources.
  • Use Gateway routing for cost and quality classes.
  • Store artifacts with stable IDs and source references.

Related docs

Workflow Durable Execution

Use Workflow for long-running, resumable, and approval-oriented AI tasks.

Ch14. Enterprise Patterns

Enterprise Eve Agent Development · Combine Eve features into support, research, code, back-office, analytics, and incident-response agent patterns.

References

Source categories for adapting the Vercel enterprise AI platform handbook.

Sales Agent Playbook

AI-Era GTM · Attach sales agents to CRM and seller workflows with clear autonomy and quality controls.

Ch5. agent.ts, Models, Compaction

Enterprise Eve Agent Development · Interpret defineAgent configuration as runtime policy for models, output schemas, compaction, and experimental flags.

Customer Support Agent Architecture

Design customer-facing support agents with retrieval, escalation, fallback, and audit.

Approval Backoffice Automation

Automate backoffice work with explicit approval events, identity, and side-effect controls.

On this page

Design PatternRuntime Choices