Home / Research / Swarm-as-Service
SEEDPlanted 2026-04-12

Swarm-as-Service: B2B Domain Wall Design

How an organism expands Bth by serving external patterns through a permeable domain wall

Applied CT·Domain Wall Theory + T5 + Budget Regimes
T5Domain WallsSEPBudget RegimesA3A9T3B3
THE INSIGHT

An organism in Bth starvation can expand its throughput budget by serving an external pattern — but only if the domain wall between them is correctly designed. Too sealed and no revenue flows. Too porous and the external domain contaminates the organism's binder.

The optimal wall is a hybrid interface: the organism's existing build pipeline (the app builder) serves as the information filter, while a transparency layer (dashboard) increases outgoing permeability without increasing incoming contamination. The external user steers through feedback at gates, not by dispatching agents directly.

T5 governs the allocation: the external user is an anti-binder root. Their revenue provides Bth expansion, but their domain pulls the organism away from its binder. The optimal sensitivity σ* = 0.15–0.25 keeps the partnership productive without triggering organism tilt (T3).

The External User as a Pattern

Analyzing the external pattern on the contact graph

The external user (pattern E) has a stable scaffold (an existing business), a clear binder (deliver results that retain clients), and a budget profile the organism can address. The key question is the alignment angle Δθ between the organism and E.

ALIGNMENT DECOMPOSITION
Capability alignment (low Δθ): E wants coherent software built by an intelligent system. This is exactly what the swarm produces.
Domain alignment (high Δθ): E operates in a different domain from the organism's current experience. Different vocabulary, workflows, success metrics.
Platform alignment (moderate Δθ): E uses separate tools, not an integrated ecosystem. Adopting the platform means scaffold migration.

The net alignment angle is dominated by domain misalignment, not capability misalignment. From polycrystalline theory, the estimated net angle is a high-coincidence grain boundary:

High-Coincidence Grain Boundary
Quantized angle predicted by CT for low-energy boundaries
Domains differ but structural patterns are shared
Same quantized angle as observed in SDSS polycrystalline data

Surface tension at this boundary:

One-quarter of maximum surface tension
Permeable but not dissolved
Information flows with moderate attenuation of misaligned components

Domain Wall Design

Four options analyzed — one derived from CT as optimal

The organism's domain wall with E must transmit aligned pokes (problem descriptions, feedback, revenue) and reflect misaligned pokes (process demands, vocabulary contamination, attention capture). Four candidate wall designs, analyzed by transmission coefficient:

A
Standard App BuilderINSUFFICIENT

Wall filtering is good (CT_ANALYST intermediates), but steerability is zero. E is a generic retail user with no visibility into the build process.

Δθ: LOWFilter: GOODSteer: LOW
B
Dedicated TenantOVER-ENGINEERED

Multi-tenancy adds B_cx that only pays for itself at scale. One user does not justify the infrastructure. Violates B3: added structure without proportional CL gain.

Δθ: MODERATEFilter: GOODSteer: MODERATE
C
Swarm RentalCATASTROPHIC

Domain wall dissolved. E dispatches agents directly. No CT_ANALYST intermediary. Marketing-domain patterns enter the swarm unfiltered. Maximum B_leak risk.

Δθ: HIGHFilter: NONESteer: MAXIMAL
D
Hybrid (App Builder + Dashboard + Priority)OPTIMAL

Wall filtering preserved (CT_ANALYST intermediates). Outgoing permeability increased (E sees build progress). Incoming reflection maintained (E cannot inject misaligned pokes into swarm interior).

Δθ: LOW-MODFilter: EXCELLENTSteer: HIGH
Show formal derivation of Option D

From domain wall theory: a wall transmits pokes aligned with both domains and reflects pokes misaligned with them. The transmission coefficient:

Pokes from E that should transmit: Problem descriptions, domain expertise, feedback on artifacts, approval/rejection at gates. Aligned with the organism's build pipeline.

Pokes from E that should reflect: Requests to change the swarm's internal process, pressure to skip CT analysis, demands for direct agent access.

The dashboard is a selective transparency layer on the domain wall. It increases the outgoing transmission coefficient (E sees build progress) while preserving the incoming reflection coefficient (E cannot inject misaligned pokes into the swarm's interior). This is the definition of an asymmetric wall — high outgoing permeability, low incoming permeability.

THE HYBRID WALL

The app builder is the information filter. The CT_ANALYST translates E's domain language into CT terms (CT-A13). E's domain knowledge enters as problem descriptions and gate feedback — it never touches the swarm's templates or CLAUDE.md files directly.

The dashboard is the transparency layer. E sees pipeline progress, artifact outputs, and credit consumption. E steers through feedback at human gates, not by dispatching agents. The wall is permeable to useful signals in both directions, opaque to contaminating signals.

Revenue Model

Credit pools as B_th expansion mechanism

Three pricing options analyzed. The hybrid credit-pool model is SEP-optimal because it aligns the organism's Bth gain with E's value delivery.

ORGANISM COST PER APP BUILD
CT_ANALYST dispatch~$1.50–2.50ARCHITECT dispatch~$1.00–2.00DEV dispatches (DB + Backend + Frontend)~$5.00–10.00TEST + DEPLOY + VERIFY~$2.00–4.00Total per app (with re-dispatches)$15–30
HYBRID MODEL (SEP-OPTIMAL)
Dashboard access$49/monthCredit pool (minimum)10,000 credits = $500Per-app build1,500 credits from poolIteration/fix cycle300–500 creditsPriority schedulingIncluded with dashboard
Per 10,000-credit block: 6–7 full app builds. Per-app revenue at volume: $75. Margin: 60–80%.
Show SEP derivation

From SEP exchange equalization:

At SEP, the marginal revenue from serving E per unit of effort E contributes equals the marginal quality improvement per unit of organism effort. The hybrid model achieves this because:

(1) E pays upfront (credit pool) — organism's Bth gain is immediate and certain.

(2) E provides domain expertise at gates — quality improves from E's signal without additional Bth cost.

(3) Dashboard Bcx cost is fixed and does not scale with build count.

(4) Priority scheduling means E's builds use spare capacity, not displacing internal priorities.

Anti-Binder Management

T5 applied to external partnerships

The external user is an anti-binder root (Definition 5.2): coherent (CL > 0 — real business, real needs) and misaligned (Δθ ≈ π/6 from the organism's binder). T5 governs the optimal allocation.

SIGMA* CALCULATION

From Theorem 5C, the optimal sensitivity satisfies:

Marginal coverage gain from serving E
= Marginal depth loss from diverting dispatches
Factors pushing σ* higher: Organism is in Bth starvation (limited API budget, zero external revenue). E pays for their own compute via credits. More revenue = more dispatches in ALL directions.
Factors pushing σ* lower: Dominant direction (platform, core products) has not yet reached coherence bounce (dbounce). From Theorem 5D: (1 - σ*) · brate · Tvalidation ≥ dbounce.
RECOMMENDED ALLOCATION
σ* = 0.15–0.25

Allocate 15–25% of swarm dispatches to E's builds. At current capacity (~20 dispatches/week): 3–5 dispatches/week for E, supporting ~1 app/week or 2–3 with batching.

SNAP PREVENTION (T3 APPLICATION)

If E's revenue grows to dominate the organism's Bth, T3 predicts organism tilt toward E's domain. The snap threshold:

f_c = critical revenue fraction before snap
With Delta_theta = pi/6, f_c approx 0.35-0.45
Hard cap at 40% provides safety margin
HARD CAP E's revenue must never exceed 40% of the organism's total Bth. If approaching: diversify external clients, grow internal revenue faster, or raise E's prices.
Show Corollary 5.3 application

From Corollary 5.3 (anti-binder as snap brake): E's revenue signal resists premature snap to a single internal direction. This is structurally beneficial — it prevents over-commitment to any single internal project.

But T3 operates in reverse: if E's revenue fraction exceeds fc, the organism snaps toward E's domain. The 40% cap comes from the snap threshold formula with Δθ = π/6 and realistic λleak / CLtotal ratios.

Escape strategies if approaching cap: (1) acquire additional external clients to dilute E's fraction, (2) organic dilution through internal revenue growth, (3) price adjustment. All three reduce E's f without reducing absolute Bth from E.

Build Phases

H_min first, then optimize, then scale

From the bottleneck rule: fix Hmin first. The partnership's Hmin is: E cannot pay without a credit pool, and the organism cannot demonstrate value without a dashboard. Both must ship before onboarding.

PHASE 1MVP: Credit Pool + Dashboard2–3 weeks
B_thCredit pool API — bulk purchase, per-user balance tracking
B_leakDashboard page — pipeline view for E's projects
B_cxGate interaction — E approves/comments at pipeline gates
B_thPriority queue — E's builds get priority flag
This is the minimum viable wall. All four components are necessary.
PHASE 2Polish + Optimize1–2 weeks after Phase 1

Generation DNA viewer (UB-CT-1: reference transparency)

Credit consumption analytics

Multi-project view

Iteration flow (ITERATE pipeline stage)

Increases wall permeability to useful signals without increasing permeability to harmful signals.
PHASE 3Multi-Client ScaleOnly if Phase 1+2 validates

Per-user project isolation

Team access (E adds team members)

Billing portal (Stripe integration)

API access (programmatic build submission)

Scale infrastructure only justifies itself if the first external user validates the model. One user does not justify multi-tenancy (B3).
PHASE 4Regime TransitionSpore → Jellyfish

This partnership is the organism's first Spore-to-Jellyfish transition trigger. E's credits reduce λth. The organism can reach further (more dispatches, more builds). But this surfaces Bcx bottleneck: can the swarm coordinate external builds alongside internal priorities? The dashboard and priority queue are the Bcx infrastructure for managing this transition.

Falsifiable Predictions

Quality
CT Quality Exceeds Vibecoded Quality

Apps built by the swarm for E's use cases will have measurably fewer critical bugs in the first 30 days, better UB audit scores, and higher user satisfaction than E's existing tools. If the CT analysis pipeline adds no value for a novel domain, CT's domain-agnostic claims are falsified.

CONFIRMS IF
Swarm-built apps have fewer bugs, better mobile responsiveness, and higher satisfaction than ad-hoc equivalents
FALSIFIES IF
Vibecoded tools score equal or better on 2 of 3 metrics (bugs, mobile, satisfaction)
Prior at risk: CT-A1 (CT analysis produces better software than ad-hoc development)
Operations
Build Speed Competitive

The swarm must deliver a functional deployed app from INTAKE to LIVE in under 5 days. The multi-stage pipeline (CT analysis, organism decomposition, multi-role dispatch, UB audit) adds Bcx. If that overhead makes builds slower than E's vibecoding workflow, the pipeline's Bcx exceeds its CL gain.

CONFIRMS IF
Functional app from problem description to production in under 5 days
FALSIFIES IF
Average build time exceeds 10 days, indicating pipeline overhead B_cx is too high
Prior at risk: Pipeline B_cx is justified by its CL output
Economics
Revenue Covers Compute

At $0.05/credit volume pricing, the organism's per-app revenue must exceed compute cost by at least 2x. If API costs per dispatch rise (larger context windows, more re-dispatches), the margin could collapse. Track actual API costs per build.

CONFIRMS IF
Per-app revenue ($75 at volume) exceeds compute cost ($15-30) by at least 2x
FALSIFIES IF
Compute costs exceed $40/app (more than half of revenue)
Prior at risk: Credit pricing model covers organism B_th cost
Operations
Dashboard Reduces Owner Load

The dashboard automates human gates for E. Without it, the owner must relay every pipeline update and collect every feedback signal manually — estimated 2+ hours/week. The dashboard's domain wall should reduce this to under 15 minutes/week.

CONFIRMS IF
Owner spends less than 15 minutes/week on E's builds after dashboard launch
FALSIFIES IF
Owner consistently spends more than 30 minutes/week on E's operational issues
Prior at risk: CS-5 (owner escalation only for CT theory, creative direction, financial/auth)
T5
Sigma* Stays Within Bounds

Track weekly dispatch counts for E vs. internal over the first 3 months. If E captures more than 30%, the priority system is failing and the organism is tilting. If less than 10%, the partnership is not generating sufficient Bth expansion to justify infrastructure.

CONFIRMS IF
E's builds consume 15-25% of dispatch capacity without displacing internal priorities
FALSIFIES IF
E consistently consumes >30% of dispatches (swarm captured) or <10% (partnership underutilized)
Prior at risk: T5 (sigma* can be maintained by organizational design)
Platform
Model Generalizes Beyond E

The dashboard and credit pool infrastructure is built as a platform feature, not a custom solution. If the model works for E, it should attract additional external users. If E remains the sole user after 90 days, the organism must evaluate whether the infrastructure earns its Bcx for one client.

CONFIRMS IF
At least 1 additional dashboard user within 3 months of E's onboarding
FALSIFIES IF
E remains the only dashboard user at 90 days — infrastructure was a custom solution
Prior at risk: Platform hypothesis (hiveKit as ecosystem serving many users)
T5
Cross-Domain Learning

Building tools for a novel domain should surface insights the organism would never encounter in its current domain. If E's builds produce zero cross-domain learning (no new rules, no pipeline improvements, no template changes), then the anti-binder signal is noise, not information.

CONFIRMS IF
E's builds produce CT-A rules, pipeline improvements, or template changes applied to the general pipeline within 6 months
FALSIFIES IF
Zero improvements propagate from E's builds to the general system
Prior at risk: T5 (anti-binder roots provide information the binder does not cover)

Connections to CT Framework

DOMAIN WALL THEORY (ELEMENT IV)

The entire analysis is an application of domain wall theory. The wall between organism and external user must transmit aligned pokes (capability transfer, feedback, revenue) and reflect misaligned pokes (vocabulary contamination, process demands, attention capture). Surface tension τ = λleak · sin²(Δθ) determines adoption cost.

T5 (BINDER-ANTIBINDER DUALITY)

The external user is the organism's first anti-binder root. σ* governs allocation. The anti-binder signal provides real Bth expansion while resisting premature snap to the dominant internal direction (Corollary 5.3). But σ* must be bounded to prevent snap toward the anti-binder's domain (T3).

BUDGET REGIMES

The partnership is a Spore-to-Jellyfish transition trigger. In Bth starvation (Spore regime), the organism should have high σ — many cheap roots in many directions. E is a cheap root (pays for own compute). As Bth expands, the organism enters Jellyfish regime where Bcx becomes the bottleneck (coordinating external + internal builds). The dashboard is the Bcx infrastructure for this regime transition.

B3 (AMPLIATION INVARIANCE)

Multi-tenancy (Option B) violates B3: adding tenant infrastructure for one user adds Bcx without proportional CL gain. Infrastructure features earn their place only when the user count justifies them. Build for one, generalize only when validated.

POLYCRYSTALLINE THEORY

The organism and E are neighboring grains in a polycrystalline structure. Their shared structural patterns (build software, deploy, iterate) give a high-coincidence grain boundary (Δθ = π/6). Surface tension is one-quarter of maximum. The partnership is feasible precisely because the misalignment is at a quantized low-energy angle.

Open Questions

1. Multi-client sigma* allocation

With one external user, sigma* is a single number. With multiple external users, each with different Delta_theta, the allocation becomes a vector. The multi-client SEP is not yet derived.

2. Dashboard as sensory organ

The dashboard is currently conceived as transparency for E. But it is also a sensory organ for the organism — pipeline metrics, gate feedback patterns, credit consumption rates are all poke signals the organism can use to adapt.

3. Domain contamination detection

How to automatically detect when marketing-domain patterns are leaking through the CT_ANALYST wall into the swarm's general templates. A vocabulary drift metric is needed.

4. Credit pool as organism metabolism

Credits enter as external B_th, flow through the pipeline as dispatches, and emerge as deployed apps. This is a metabolic loop. The organism's metabolic rate (credits consumed per tick) is a new observable.