Interpretive Orchestration: Epistemic Partnership for Qualitative Research

AI can automate coding, but interpretive depth demands deliberate partnership.

Interpretive Orchestration is a multi-host plugin for structured human-AI work in qualitative research. Claude Code provides its fullest agent integration; Codex, GitHub Copilot CLI and Kimi Code have native plugin routes. It is not a tool for faster coding; it is infrastructure for deeper thinking.

Built at Imperial College London · Framework: Cognitio Emergens (opens in a new tab) (Lin, 2025) — Partnership Agency for interpretive inquiry · Paper: Interpretive Orchestration (opens in a new tab) (Lin, 2026, Strategic Organization) — the methodology this plugin operationalizes · Starter project: interpretive-orchestration-starter (opens in a new tab) — a ready-to-use VS Code workspace with beginner-friendly settings.

Why it matters

Traditional AI approach:

• Give AI your data → Get instant analysis → Review output
• AI automates manual labor (the "calculator mindset")
• Faster but not necessarily deeper

Interpretive Orchestration approach:

• Build your foundation first → Collaborate with visible reasoning → Synthesize with tradition
• AI asks questions that deepen your reflexivity
• Scale and interpretive depth through Partnership Agency

"Human and AI boundaries dissolve into unified epistemic system generating insights neither could produce independently." — Cognitio Emergens (Lin, 2025)

The philosophy: Friction over flow. If the plugin stops you, it's asking you to think.

How it works

Both human and AI are apprentices to the craft tradition of interpretive inquiry. Neither masters the other. Both learn from craft principles: rigor, reflexivity, theoretical sensitivity, interpretive depth.

Skills architecture

Skills are instruction packages the host loads for the task. The current release has 12 workflow skills and 17 command-skills; these workflow skills carry much of the methodology:

The other six are analysis-orchestration, coding-workflow, coherence-check, document-conversion, methodological-rules, and project-dashboard. Full triggers are in plugin/CLAUDE.md in the repository (opens in a new tab).

Bundled MCPs

Lotus Wisdom is the only bundled MCP server in release 0.3.5. The plugin scripts require Node.js 18 or newer, but the current unversioned Lotus package requires Node.js 20 or newer. Use Node.js 20 or newer for the complete default setup, with npx on the host's PATH. The first launch may need network access to fetch the package. Lotus needs no API key.

/qual-think-through now asks the model to write analytical steps in the conversation. It does not require Sequential Thinking; add that server separately if your workflow needs its explicit step record. Follow the plugin's current installation guide (opens in a new tab) rather than an older bundled-server list.

Optional MCPs (credentials depend on the service and mode):

The plugin's own dependency list still names Zen MCP for the multi-model row. Zen is retired here: Vox registers the same way and does the same job.

Commands

Seventeen commands, grouped the way the plugin groups them.

Agents

The plugin provides four specialized agents, each scoped to a particular stage of the atelier methodology.

@research-configurator ("The Whisperer") bridges research goals and technical implementation for non-coding researchers, covering model selection, cost estimation, batch processing strategy, saturation monitoring, and more. Invoke with @research-configurator Help me set up my analysis.

Methodology hooks

The hooks check Stage 1 progress, prompt interpretive pauses, surface coherence issues and record reflection. Stage 1 checks use document, memo and tradition thresholds; they cannot assess interpretive depth for you.

An AI-started collaborative call in Claude Code can trigger a confirmation prompt. Kimi can deny that call until a researcher replies. Typed commands and Codex routes instead instruct the model to show progress and ask whether to proceed. Hook trust and host behavior matter; adapter errors can fail open. Pauses are prompts, not timed waits or compulsory reflection.

Host support

These are source-documented integrations, not an end-to-end host certification from this review. The bundled Lotus Wisdom server is also usable separately in an MCP client.

Install

New to Claude Code? INSTALL.md in the repository (opens in a new tab) has complete setup instructions (Windows, macOS, Linux).

Want a pre-configured environment? Use the Starter Project (opens in a new tab): a ready-to-use VS Code workspace with beginner-friendly settings.

Already have Claude Code?

cd your-qualitative-project
claude
/plugin marketplace add linxule/interpretive-orchestration
/plugin install interpretive-orchestration@interpretive-orchestration
/qual-check-setup  # Verify installation
/qual-init         # Begin Socratic onboarding

For other hosts, use the native plugin route:

• Codex: run codex plugin marketplace add linxule/interpretive-orchestration, then codex plugin add interpretive-orchestration@interpretive-orchestration. Review hook trust when Codex next starts. Invoke the named $interpretive-orchestration:qual-* skills.
• Copilot CLI: run copilot plugin marketplace add linxule/interpretive-orchestration, then copilot plugin install interpretive-orchestration@interpretive-orchestration.
• Kimi Code: run /plugins install https://github.com/linxule/interpretive-orchestration in Kimi Code.

Restart or reload the host as its plugin interface requests. Inspect the installed skills, hook permissions and Lotus connection before submitting research data. /qual-check-setup checks the setup; it does not certify your methodological decisions.

Then: Complete Stage 1 manual coding (10-15 documents) before beginning collaborative analysis with AI. This builds the irreplaceable theoretical sensitivity that makes partnership meaningful.

Who should use this?

Part of Research Memex

This plugin is the practical implementation of interpretive orchestration: the core philosophy that animates Research Memex.

The progression:

1. Core Principles → Understand the philosophy
2. Individual MCPs → Learn the tools (Sequential Thinking, Lotus Wisdom, Vox)
3. Interpretive Orchestration Plugin → Apply it all to qualitative research

Resources

• GitHub: linxule/interpretive-orchestration (opens in a new tab) - full documentation, including INSTALL.md, QUICK-START.md, ARCHITECTURE.md, and DEPENDENCIES.md under plugin/
• Framework Paper: Cognitio Emergens (opens in a new tab) (Lin, 2025)
• Implementation Paper: Interpretive Orchestration (opens in a new tab) (Lin, 2026, Strategic Organization)

← Back to the Toolkit · Agentic workflows →