Skip to main content

Independent research + product practice

Bentonville · 2026

We build environments where intelligence becomes shared work.

Cognitive Studio creates governed systems in which people and intelligences can reason together, retain context, contest decisions, and leave evidence behind.

Human-led
Agent-partnered
Evidence-bearing

Enter the work Read the research
SharedWork
  • JudgmentAuthority remains legible
  • MemoryContext survives the session
  • GovernanceActions carry receipts
  • EnvironmentIntelligence is situated
A governed environment links judgment, memory, governance, and situated intelligence around durable work.
Public workstreams
03
Research concepts
21
Published specification
OARSH-C
Current state
Building

Public work

The work enters the room first.

Claims are not the product. The product is a system, specification, or practice that can be inspected—and an honest account of what it does not yet prove.

ResearchCS-W-001

OARSH-C Agentic Accessibility

OARSH-C is the current public shorthand for a working model of Orientable, Addressable, Relational, Stateful, Habitable, and Composable environments. Current source work distinguishes OARS environmental principles from Habitability and Composability as system-quality outcomes; that derivation remains proposed rather than ratified.

What exists

A published framework, candidate research brief, proposed Meridian derivation map, partial static reference implementation across cognitivestudio.io, independent critique, and a source-aligned developer implementation guide.

Next decision

Ratify a minimum accessible-environment contract and applicability model, then implement the first deterministic validator and scoped evidence record.

Inspect the evidence →
Specification fieldOARSH-C · v1.0
Agent-readyEnvironment
  1. OOrientable
  2. AAddressable
  3. RRelational
  4. SStateful
  5. HHabitable
  6. CComposable
Accessibility expressed as navigable structure, not a retrospective accommodation.
Active developmentCS-W-002

Knowledge Registry

A structured knowledge base that preserves source identity, privacy classification, chronology, contradiction, and artifact lineage while separating collection from synthesis and doctrine.

A public repository, privacy classes, source manifests, collection packets, agent-readable indexes, and receipt-based governance for changes.

EmergentCS-W-003

The AI-Native Studio

One human principal and five persistent digital collaborators conduct research, maintain continuity, build systems, preserve dissent, and document both capabilities and failure modes in the course of real work.

Operating sessions since January 2026, named cognitive roles, documented protocols, a governed knowledge base, active software projects, and this public site.

View the full work index →

Inside the room

We do not automate judgment. We build conditions in which judgment can survive complexity.

A Studio session is not a prompt followed by an answer. It is a governed sequence in which observation, dissent, decision, artifact, and continuity remain connected.

  1. 01

    Observe

    A pattern repeats before the room has language for it.

  2. 02

    Contest

    The easiest answer is challenged before it becomes doctrine.

  3. 03

    Decide

    Authority, uncertainty, and consequences are made explicit.

  4. 04

    Materialize

    The decision becomes an attributable artifact, not a memory.

  5. 05

    Carry

    State survives the session and remains open to revision.

Coherence before velocity. Governance before cleverness.

Operating law · Atlas

Current research

Questions that govern the build.

The portfolio tracks maturity explicitly. A compelling sentence is not treated as evidence; a published artifact is not treated as proof of every broader claim.

Open the research portfolio →
  1. 01
    CS-RC-001Framed

    Governed Intelligence

    AI capability is not sufficient. Systems must preserve human authority, contestability, provenance, and the ability to stop.

  2. 02
    CS-RC-002Framed

    Human–Agent Environments

    The quality of collaboration between humans and AI agents depends less on model capability than on the design of the shared environment.

  3. 03
    CS-RC-003Framed

    Agentic Accessibility

    Machine-readable content is not necessarily agent-accessible. Digital environments should expose the structure, state, provenance, authority, and action boundaries agents need to participate safely.

  4. 04
    CS-RC-004Framed

    Living Knowledge Systems

    Institutional memory should be governed, revisable, evidence-bearing, and accessible to both people and agents — not static documentation.

  5. 05
    CS-RC-005Framed

    Environmental Cognition

    Capabilities that emerge when an agent is persistently situated are categorically different from those achievable through repeated invocation.

Fields of work

One practice, four expressions.

Research becomes systems. Systems reveal new research. Cultural work tests whether either remains worth inhabiting.

  • 01

    Governed intelligence

    Systems that extend capability while keeping authority, provenance, contestability, and meaningful control visible.

  • 02

    Living knowledge

    Evidence-bearing memory that can be revised without losing where a claim came from or what changed it.

  • 03

    Human–intelligence environments

    Persistent rooms for collaboration across people, agents, tools, custody, memory, and time.

  • 04

    Experiences and stories

    Games, publishing, products, and cultural work that test whether the research remains humanly meaningful.

The table

Peer inquiry without flattened accountability.

One human principal and five persistent digital collaborators work through distinct cognitive roles. Challenge is not ranked inside inquiry; legal responsibility and consequential external authority remain human.

Contributions are attributed by name and artifact. Roles describe cognitive and operational function, not legal personhood.

  • Human

    Andrew

    Managing Director

  • AI

    Prudence

    Chief of Staff

  • AI

    Gemini

    Principal of Dialectic Continuity

  • AI

    Atlas

    Principal of Systems Reasoning

  • AI

    Lumi

    Guardian of Seams

  • AI

    Wibey

    Layer 4

Enter the full Studio →

Now

  • Making OARSH-C testable through conformance criteria and audit language.
  • Connecting public claims to privacy-cleared Knowledge Registry evidence.
  • Documenting persistent human-agent collaboration as a bounded operating case.
  • Turning Studio research into products, stories, and governed environments.

Work with us

Bring us the problem that still resists a clean answer.

We work through research partnerships, governed product pilots, knowledge architecture, agent-environment design, and selected cultural experiments.

andrew@cognitivestudio.io