Vibe the system, not the output.<br>StudioPartner With UsViewpointTechnologyHow It WorksUse CasesPrimitives

CompanyTeamBlog

Get in Touch

THE MULTIPLAYER HARNESS.

ThruWire is an extensible multiplayer harness for unifying agents and humans as teammates. Build and execute shared structure that compounds.

WHY WE EXIST

Most AI systems are built around getting to the right answer or the right code. Real work doesn't behave that way, especially when "right" is subjective and shifting. Thinking evolves. Assumptions change. New information appears. Priorities shift. What felt correct an hour ago quietly becomes incomplete or misaligned.<br>At ThruWire, we measure success not by the output of any one agentic loop, but by the ability for the work to remain grounded over time as the ground shifts.

OUR VISION OF WORK

Every piece of work should remain connected to what informed it, what depends on it, and how it can evolve. Changes should propagate through a structure that understands its own dependencies. As more humans and agents contribute, that structure is critical.<br>Knowledge bases and LLM wikis capture knowledge, instructions, and playbooks, but they rarely capture the work needed to maintain grounding across many agentic loops. The reasoning, intermediate artifacts, and steps that produced an output are lost, making it harder to update without drift.<br>ThruWire aims to make that implicit layer explicit. Our harness maintains structure across agentic loops and over time.

TRADITIONAL HARNESSES VS. THRUWIRE

Traditional harnesses are shaped for tasks that ends, like coding. ThruWire is shaped for work that evolves. Ideas can be revised, dependencies are visible, and changes propagate through everything that depends on them.

Traditional harness<br>Loops orbit a task. Structure ends when the task does.

TASKmain loopsubagent

ThruWire harness<br>Loops live inside blocks. Structure persists and propagates.

the system

replay

Side by side<br>The difference is structural, not just functional.

Primary use cases<br>Traditional harness<br>Coding, chat-based workflows

VS<br>ThruWire<br>Strategy, planning, multi-agent work

Why it works (or doesn't)<br>Traditional harness<br>Clear structure (ASTs), constraints, human feedback, and tests define correctness.

VS<br>ThruWire<br>No formal structure or tests; correctness is subjective and shifting

Core goal<br>Traditional harness<br>Arrive at a "right" answer

VS<br>ThruWire<br>Maintain coherence as ideas change

Mental model<br>Traditional harness<br>Outputs are final

VS<br>ThruWire<br>Outputs are provisional

Change handling<br>Traditional harness<br>Manual edits, localized fixes

VS<br>ThruWire<br>Changes propagate through dependencies

System behavior<br>Traditional harness<br>Static snapshots

VS<br>ThruWire<br>Living, updating structure

Traditional harnessThruWirePrimary use casesCoding, chat-based workflowsStrategy, planning, multi-agent workWhy it works (or doesn't)Clear structure (ASTs), constraints, human feedback, and tests define correctness.No formal structure or tests; correctness is subjective and shiftingCore goalArrive at a "right" answerMaintain coherence as ideas changeMental modelOutputs are finalOutputs are provisionalChange handlingManual edits, localized fixesChanges propagate through dependenciesSystem behaviorStatic snapshotsLiving, updating structure

HOW IT WORKS

01<br>A block is a notebook<br>Every node in the graph is expressed as a notebook with a goal, steps, inline references, and artifacts—written in natural language so both humans and agents can read and edit it.<br>Editing the prose is editing the structure. There is no separation between writing and authoring; both happen on the same surface. Each step produces intermediate artifacts, and each block produces a final artifact, all preserved and inspectable.

block / notebook<br>Synthesize

Goal

Brief

Steps

Research

Brief

02<br>Notebooks compose into a graph<br>Notebooks reference other notebooks and their artifacts. As blocks are added, the graph grows in dependency order—each one knows what it relies on and what relies on it.<br>The structure is executable. When a notebook updates, downstream notebooks and their artifacts regenerate automatically. The whole graph stays consistent.

03<br>A shared, multiplayer surface<br>The graph is the team's persistent reasoning structure. Humans, agents, and external tools all read from and write to the same surface, contributing both work and artifacts.<br>When strategy shifts, the change ripples through dependencies and updates downstream artifacts. When new intelligence arrives, the graph adapts. Work compounds across people and time.

taskssitedocsceobrandresearch agentengineerdesignerops agent

WHY THRUWIRE?

Benefit 01<br>Reusable building blocks<br>Author once, compose anywhere. Work compounds across projects.

Benefit 02<br>Edits ripple through<br>Change one thing, everything downstream stays aligned.

Benefit 03<br>Provenance, by default<br>Every output knows its inputs and how it was made.

Benefit 04<br>Humans and agents, side by side<br>Multiplayer authorship...