Skip to main content
Difficulty: 🔴 Advanced | Prerequisites: Comfortable with Claude Code, understand cognitive blueprints and MCP servers

​
From Prompting to Orchestration

Most AI-assisted research follows a simple pattern: you write a prompt, get a response, iterate. This works well for individual tasks but breaks down for complex, multi-stage research projects. Agentic workflows change the model. Instead of one researcher talking to one AI, you design a system of specialized agents that collaborate under your direction — each handling what it does best while you maintain strategic control. 
Traditional:   Researcher ↔ Single AI Model
Agentic:       Researcher → Orchestration Layer → Specialized Agents
                                                    ├── Analysis Agent
                                                    ├── Critical Challenge Agent
                                                    ├── Synthesis Agent
                                                    └── Memory System

​
The Agentic Research Stack

We’ve built and use an integrated stack for agentic research. Each component addresses a different limitation of single-model prompting.

​
Interpretive Orchestration Plugin

Problem: AI can automate analysis, but automation without theoretical grounding produces shallow results.Solution: A Claude Code plugin that enforces methodological rigor through three stages:
  1. Solo Practice — You build theoretical sensitivity manually before AI touches the data
  2. Side-by-Side Collaboration — Parallel human + AI analysis streams with visible reasoning
  3. Synthesis — Human-led integration examined through craft tradition frameworks
Four specialized agents (@stage1-listener, @dialogical-coder, @research-configurator, @scholarly-companion) handle different aspects of the research process.Key insight: The plugin deliberately creates friction. If it stops you, it’s asking you to think.→ Full guide

​
How the Stack Works Together

A concrete example of the integrated workflow for a systematic literature review:

​
Phase 1: Foundation Building

  • Interpretive Orchestration enforces solo coding of initial documents
  • Memex captures your emerging framework and theoretical sensitivity
  • Vox lets you consult multiple models about methodological choices

​
Phase 2: Collaborative Analysis

  • Interpretive Orchestration activates @dialogical-coder for parallel analysis
  • Vox enables multi-model triangulation on key findings
  • Kimi K2.5 (via Vox) stress-tests your emerging theory
  • Memex preserves the evolving analysis across sessions

​
Phase 3: Synthesis and Writing

  • Memex /memex:synthesize surfaces patterns across all sessions
  • Interpretive Orchestration @scholarly-companion examines work through epistemological lens
  • Claude Opus 4.6 (via Vox) helps break frames and find insights beyond local optima

​
The Broader Agentic Landscape

The tools above are what we’ve built and use, but the agentic research ecosystem is broader:

​
CLI-Based Agents

  • Claude Code — Anthropic’s agentic coding environment (our primary workspace)
  • Gemini CLI — Google’s terminal agent with 1M token context and agent skills
  • OpenCode — Open-source, model-agnostic terminal agent (95K+ GitHub stars)

​
MCP Ecosystem

The Model Context Protocol has grown to 1,000+ community servers, now managed by the Linux Foundation. Research-relevant servers include:

​
Research Platforms

  • Research Scanner — Literature surveillance pipeline balancing exploitation and exploration
  • OpenInterviewer — AI-powered qualitative interviews at scale

​
Getting Started with Agentic Research

1

Start Simple

Use Claude Code with MCP servers (Sequential Thinking, MinerU) for enhanced single-model workflows. This is where most researchers should begin.
2

Add Multi-Model Access

Install Vox MCP to access multiple models from your Claude Code workspace. Experiment with model comparison and triangulation.
3

Add Persistent Memory

Install the Memex Plugin when your research spans multiple sessions. Let it capture your collaborative journey automatically.
4

Full Orchestration

Adopt the Interpretive Orchestration Plugin for a complete qualitative research infrastructure. This is the most opinionated tool — it will change how you think about AI-assisted research.
You don’t need the full stack to benefit from agentic workflows. Each component is useful independently. Start with what addresses your biggest pain point and expand from there.