Michi - Branch-native workspace

What the company appears to be: Michi is a branch-native workspace for AI interaction, designed to support non-linear thinking by enabling users to create, manage, and visualize parallel conversations with AI agents. The product allows branching of thought processes within a single chat session, with features like merging, digesting, referencing, and mapping branches.

What changed: The author describes building Michi from an MVP that only supported one runtime with no data persistence, through iterative development adding multiple runtimes, SQLite support, real-time Markdown rendering, and various UI/UX enhancements. It evolved from a personal tool to a more structured workspace with persistent storage and collaborative features.

Single most important open question: Does the author's self-reported vision of solving "real problems" translate into actual user demand or adoption beyond personal usage?

Analysis basis: This report is based entirely on the self-reported project description provided by the author. No external verification, revenue data, customer information, or traction metrics are available.

The description states that Michi is a "branch-native workspace" for AI interaction where users can:

• Start a chat with an agent
• Select text from responses and branch off to create parallel panes
• Interact with branches in real-time while continuing to read the parent node
• Merge, digest, reference, and map branches
• Manage workspaces and artifacts (files, links, code, images)
• Support multiple runtime tools including Codex, Claude Code, Kiro-CLI, and Pi-agent

The product is described as a web-based application built with React, Node.js, Express.js, SQLite, and other technologies. It includes features like:

• Real-time Markdown rendering with typewriter streaming
• Frosted glass UI effects
• Branch visualization and mapping capabilities
• Artifact management across different panes

Evidence: The author's own write-up describes the functionality in detail, but no external validation or demonstration is provided.

The author positions Michi as a tool for "divergent thinking" that addresses limitations of linear AI chat interfaces. Key claims include:

• Inspired by Wikipedia's "wiki rabbit hole" phenomenon
• Addresses the need for branching in AI conversations beyond side chats
• Offers equal treatment of branches within a main chat
• Provides persistence and interactivity between different branches

The positioning evolved from a personal solution to a tool that supports complex, multi-directional thinking processes. The author emphasizes:

• "Non-linear mind" support
• "Branching as core feature"
• "Root cause analysis reports and travel plans"
• "Beautiful report generation"

Evidence: All claims are self-reported by the author; no third-party validation or market positioning data is available.

The description does not clearly identify a specific customer segment or ideal customer profile (ICP). The author mentions:

• Personal use cases involving AI interactions
• Need for "deep dives and design questions" requiring human judgment
• Work scenarios involving branching across different directions within larger scopes
• Users who value "divergent thinking"

However, there is no explicit mention of:

• Specific industries or job functions
• Size or type of organizations
• Customer personas or user types

Evidence: The author's own account lacks specific targeting information; the product appears to be aimed at individuals using AI for creative or analytical tasks.

There is no evidence in the description regarding:

• Revenue model
• Pricing structure
• Monetization strategy
• Customer acquisition costs
• Unit economics

The author focuses entirely on the technical and conceptual aspects of the product without addressing commercial viability.

Evidence: Not evidenced. No business model or pricing information provided.

Technical signals from the description include:

• Built with Electron, React, Node.js, Express.js, TypeScript, SQLite
• Uses AI tools like Claude Code, Codex, GPT-5.6, Kiro-CLI, Pi-agent
• Real-time Markdown rendering with typewriter streaming
• Support for multiple runtimes (Codex, Claude Code, etc.)
• Runtime support across mainstream CLI tools
• Custom-built Markdown renderer module

Delivery signals:

• MVP approach with iterative development
• Use of worktrees for feature development
• Project-level reviews and code cleanup practices
• Focus on reducing cognitive load for AI agents

Evidence: The author describes technical implementation details but provides no evidence of scalability, performance metrics, or production deployment status.

The description contains no traction or maturity indicators such as:

• Revenue figures
• Customer base or user numbers
• Adoption rates
• Market feedback or testimonials
• Product usage statistics
• Growth trajectory

The author mentions:

• "A lot of people have came to me and told me how much they loved the product"
• "I'm proud that I'm solving real problems"
• "Share Michi on more platforms"

But these are subjective statements without quantifiable evidence.

Evidence: Not evidenced. No traction or maturity data provided.

The description does not mention:

• Direct competitors
• Market positioning relative to existing tools
• Competitive advantages or differentiators
• Market size or opportunity assessment

It references ChatGPT's side chat functionality as a comparison point but does not elaborate on the competitive landscape.

Evidence: Not evidenced. No competitive analysis provided.

Key risks and red flags identified from the description:

1. Lack of commercial traction - No evidence of revenue, customers, or adoption beyond personal use
2. Single-person development team - Limited capacity for scaling or rapid iteration
3. Technical complexity without architectural review - Early lack of attention to architecture may lead to scalability issues
4. Dependency on AI quality - Reliance on AI judgment for UI/UX decisions, which can be expensive and error-prone
5. Limited user feedback - Only self-reported appreciation from others, no objective validation
6. Mobile support pending - Mobile platform support is described as "hanging there for quite a long time"
7. Unproven market demand - The author's claim of solving "real problems" lacks external corroboration

Evidence: These are inferred from the self-reported description; no independent validation available.

1. What specific user problems are you trying to solve, and how do you know they exist?
2. How many users have you engaged with beyond personal testing?
3. What is your plan for monetization and customer acquisition?
4. Can you demonstrate measurable improvements in productivity or thinking quality?
5. How do you plan to scale beyond a single developer?
6. What are the key technical challenges that remain unresolved?
7. How do you intend to validate the market demand for this product?
8. What is your roadmap for mobile support and platform expansion?

Inference: These questions are based on gaps in the self-reported description.