# Map of Content — Interpretible Context Methodology & The Future of AI Dialogue

This vault distills a talk by [[entity-jake-van-clief]] (with [[entity-k-kumar]] and [[entity-david-mcdermott]]) arguing for **folder-and-markdown agent architectures** over framework-driven multi-agent orchestration, and forecasting a future of real-time voice-driven AI collaboration.

> **Start here:** read `_AGENT_PRIMER.md` for the full distilled context. This MOC is the navigational index.

---

## Core Reading Order

1. **Headline thesis** → [[quote-absurdities]]
2. **The methodology** → [[concept-icm]]
3. **The philosophical centre** → [[concept-dialogue-structure]] (+ [[quote-dialogue-theme]])
4. **The maturity ladder** → [[concept-three-levels-ai]]
5. **The forward-looking finale** → [[concept-voice-collaboration]] (+ [[quote-voice-control]])

---

## Concepts

- [[concept-icm]] — Interpretible Context Methodology
- [[concept-three-levels-ai]] — Three Levels of AI Use (L1 / L2 / L3)
- [[concept-dialogue-structure]] — Dialogue as Workflow Structure
- [[concept-voice-collaboration]] — Real-Time Voice-Driven AI Collaboration
- [[contrarian-frameworks]] — Contrarian: Multi-Agent Frameworks are Over-Engineered

## Claims (with validation)

- [[claim-icm-superiority]] — ICM outperforms multi-agent frameworks *(high confidence in source; partially supported by literature)*
- [[claim-l2-roi]] — The L1→L2 jump yields highest ROI *(high; well-aligned with practitioner consensus)*
- [[claim-voice-future]] — Real-time voice AI is the future of workflows *(medium; plausible prediction)*

## Frameworks

- [[framework-skill-creation]] — Skill Creation via Dialogue Extraction (5 steps)

## Entities

**Speakers**

- [[entity-jake-van-clief]] — primary speaker
- [[entity-k-kumar]] — collaborator, built the decision-tree mapping tool
- [[entity-david-mcdermott]] — co-participant

**Organizations**

- [[entity-anthropic]]

**People (cited)**

- [[entity-andrej-karpathy]]

**Products & Tools**

- [[entity-claude]] — primary LLM
- [[entity-langchain]] — contrast example
- [[entity-semantic-kernel]] — contrast example
- [[entity-11labs]] — voice cloning provider (ElevenLabs)

## Quotes

- [[quote-absurdities]] — folders over frameworks
- [[quote-l2-roi]] — ROI of Level 2
- [[quote-dialogue-theme]] — dialogue as the core theme
- [[quote-voice-control]] — voice controlling local AI

## Action Items

- [[action-implement-folders]] — structure context as folders + markdown
- [[action-move-to-l2]] — standardize prompts and skills
- [[action-codify-voice]] — write a `voice-and-tone.md`

## Prerequisites

- [[prereq-llm-context]] — LLM context windows and token economics
- [[prereq-markdown]] — basic markdown literacy

## Open Questions

- [[question-icm-scaling]] — does ICM scale to enterprise codebases?
- [[question-voice-security]] — security of real-time voice access

---

## Suggested Traversal Paths

**For an engineer evaluating ICM:** [[concept-icm]] → [[claim-icm-superiority]] → [[contrarian-frameworks]] → [[action-implement-folders]] → [[question-icm-scaling]]

**For an org leader planning AI adoption:** [[concept-three-levels-ai]] → [[claim-l2-roi]] → [[action-move-to-l2]] → [[action-codify-voice]]

**For a prompt engineer:** [[concept-dialogue-structure]] → [[framework-skill-creation]] → [[action-codify-voice]]

**For a futurist / strategist:** [[concept-voice-collaboration]] → [[claim-voice-future]] → [[question-voice-security]]