Everything is a Neuron

Everything is a Neuron

Thesis: DigitalBrain does not compare things to neurons. It is a workspace of Neurons. Buttons, Login, Gmail, Salesforce, Chat, Features, Connections, Approvals — each is a Neuron identity you can name, see, drive, and (when needed) approve. How something is built may differ; what it is in the product does not.

For product managers: Think of a Neuron as “a real object in the user’s brain,” not a developer class. If users and agents cannot share the same object, the idea does not fit.
→ Practical PM guide: For Product Managers · Pictures: Home

Why this is the product

If Login is only a “screen,” Chat only a “session,” Gmail only an “integration,” and Features only “packages,” the product shatters into five mental models. Humans learn one UI; agents learn another; connectors hide in settings; approvals feel like chores.

When everything is a Neuron:

• One language — the same thing humans see and agents drive
• One workspace — not a UI copy and an agent copy
• One trust story — outside changes are Effects you can approve, not silent side effects
• One growth story — new skills enter as Features/Neurons you approve, not free shell

What maps to a Neuron (everyday → product)

Product nouns map to Neurons. How they are built varies — that is not a second product type system:

You encounter…	Exists as…	Built how (detail, not a new category)
Login	Login / Session Neurons	Sign-in + durable session
Chat	Chat + Operation Neurons	Conversation state, optional AI, live view
Gmail-style actions	Abilities on a mail-backed Neuron	Connection-backed reads/writes
Salesforce update	Effect Neuron waiting for a decision	Prepared change + approval
Google / Salesforce link	Connector Neuron	OAuth + health
Feature / skill	Feature Neuron	Approved installable module
Activity row	Observation of work / Effects	History the user can trust
App screen	Surface / UI Neuron	Live projection + actions
Agent action	Same Neuron, agent client	Doorway into the workspace

Do not invent product categories for “Agent,” “RFW surface,” “tenant shell Feature,” or “external MCP package.” Those are non-products (What We Delete).

What stays one identity

A Neuron has a stable address in the workspace (Owner/Actor space + Neuron id). Session transport, access tokens, Flutter routes, MCP connection IDs, and server replicas are caller context, not the product thing.

Two clients can hold different sessions and still resolve the same Chat Neuron. That is why MCP can light up Flutter: same address, same revision line, same surface feed.

Scenes (product feel)

• You open Ask: you are looking at the Chat Neuron’s live projection, not a local message list Flutter invented.
• An agent runs ino_interact (or later neuron_invoke on Chat): the Chat Neuron advances; Activity and Ask surfaces revise; Flutter redraws.
• You connect Google: a Connector Neuron becomes healthy; capability faces unlock — not “MCP tools got installed.”
• A Feature wants to write Salesforce: an Effect Neuron appears for approval; nothing external mutates without that moment.

Implementation is allowed to be boring

Orleans grains, pure functions, OAuth adapters, LLM budgets, and Flutter widgets are how. The product sentence stays:

This is a Neuron in the shared workspace.

flowchart LR
  subgraph Workspace["One Owner/Actor workspace"]
    L[Login / Session]
    C[Chat]
    F[Feature]
    G[Connector Google]
    E[Effect]
    A[Activity]
  end
  Human[Human via Flutter] --> Workspace
  Agent[Agent via MCP] --> Workspace
  Workspace --> Surfaces[Surfaces / projections]
  Surfaces --> Human

Loading

---

In one line: Everything addressable is a Neuron; traits change execution, never the product story.