DUNIN7 · LOOMWORKS · RECORD
record.dunin7.com
Status Current
Path standing-notes/loomworks-standing-note-skill-method-vocabulary-v0_6.html

Standing note — skill, method, and the customization vocabulary — v0.6

Version 0.6
Date 2026-06-11
Status Standing note. Settles the three-way "skill" distinction the manifest carried as open, and names the layering of customization vocabulary (the personal side, method, vertical) that a discussion of custom Companions surfaced. Operator-facing. HTML primary to follow; this Markdown source alongside.
Change from v0.5 One addition: a new §9 names a dependency of the interaction surface (§8.1), surfaced and then honestly bounded in discussion on 2026-06-11. The installed method gives an engagement its interaction character (how it asks, confirms, recalls, pitches answers); that character is not improvised — it references an interaction/personality domain (a typed body of knowledge: personality frameworks, interaction styles), the way any method references its domain (seed §37; queued §8.1). This domain is not yet present in the canon, and the substantive typology work cannot be driven from a single discussion session — it needs the personality/interaction domain present as sourced Memory with provenance, per the vocabulary-deference discipline (defer to the domain's settled structure; do not substitute reasoned-from-memory typologies). §9 records the structural finding and defers the substance. It also connects to the standing Companion (queued §10): one invariant personal identity (§2.1) carried across engagements, each engagement's installed method supplying its referenced-domain-grounded interaction character. All v0.5 content preserved.
Change from v0.4 One addition: a new §8 names the two surfaces a method drives, from discussion on 2026-06-11. A method applied to the engagement at install drives the interaction surface — the Companion's behavior, how Q&A is delivered, how the engagement behaves when talked to (drawn from the method's interaction components: capability families, conversational voice). A method named at Shaping drives the production surface — how a specific render is created: unique styles, structure, arrangement (drawn from the method's production components: shaping logic, render specialists). One method can drive both surfaces, or different methods can drive each; the installed method shapes the conversation, the Shaping methods shape the artifacts. Cardinality follows function (few installed — one coherent interaction; many referenced — composed production), echoing the seed's membership/reference split (§37). Voice stays Operator-governed across both surfaces (§7); composition conflict among referenced methods inherits the deferred scope-composition resolution (seed §85). All v0.4 content preserved.
Change from v0.3 One addition: a new §7 settles how an engagement's voice is owned and learned, from discussion on 2026-06-11. The engagement speaks in one voice, governed by the Operator; the Contributors' registers live in Memory, attributed, as written — preserved as input, not erased; whether the engagement's voice is the Operator's own register, an adopted house voice, or a deliberate blend drawing in a Contributor's register is the Operator's choice, never an automatic average of who wrote most. A method can learn the available registers from accumulated assertions and surface them; the Operator governs which voice the engagement speaks in (learning informs, the Operator decides). §6.2 #1 is rewritten to reflect this (voice as learned-and-surfaced, Operator-governed, singular at output) rather than the earlier "carried as a set asset" framing. This is the third instance this session of the source-is-acknowledged / authority-is-granted principle (after §2.1 and §5), strengthening it as a v0.21 consolidation candidate. Also corrects a stale marker: the v0.3 document title line read "v0.2" while filename and footer read v0.3; v0.4 brings title, version field, and footer into agreement. All v0.3 content otherwise preserved.
Change from v0.2 Two additions, both from continued discussion on 2026-06-11. (1) A new §5 resolves the propose-versus-carry edge §4 left open: a method cannot carry a delegation contract — a contract is identity-and-engagement-bound while a method is identity-and-engagement-agnostic, so carrying is structurally impossible, not merely disallowed. A method carries an inert contract proposal; installing the method drafts a held contract from it; the Operator commits through the standing held-then-commit ceremony. Propose, never carry. (2) A new §6 answers "what does a method actually hold, and how does it push customization past a skill file": the grounded component layers plus five boundary-pushes (voice-as-asset, shaping logic, proactive triggers, cross-method composition, and accumulation-from-use), unified by the recognition that a method is content living inside the architecture and so inherits provenance, composition, Shaping, proactivity, and accumulation — none of which a skill file can reach. §4 is updated to mark the propose-versus-carry edge resolved. All v0.2 content preserved.
Change from v0.1 One correctness fix to the central claim. v0.1 §2.1 said "a custom Companion is the personal scope populated," which let the personal base be re-based per user and collapsed being-yours with being-specialized. v0.2 corrects this: the personal side is a property of the person, bound to identity (the UUID), always present, following the person across every Companion, driver, and specialization. Specialization (a method, a vertical) is content laid over the personal side, never a replacement for it. This re-reads the architecture's own UUID-binding (foundation note §1; functional spec §3) and four-facet separation (foundation note §5; functional spec §8) faithfully, where v0.1 under-read them. A fourth correction is added to the trajectory (§3) recording the fix. All other content preserved from v0.1.
Author posture Discovery posture: the corrections that produced the final layering are preserved alongside the conclusion, so a later reader can reconstruct how it was reached, not only where it landed.
Source grounding Grounded against candidate seed v0.12, Companion architecture foundation note v0.2, Companion functional spec v0.2, current-status manifest v0.50 (the open residue), and queued-directions v0.26 (§1.2 the Loomworks-skill definition, §8.1 supplied-Memory reframe). Settled in discussion 2026-06-11; nothing here is built.

Plain-language summary

The word "skill" was carrying three different jobs in the Loomworks canon, and the manifest flagged the ambiguity as unsettled. This note gives each job its own word: skill (a bounded transform in the engine), skill file (an Anthropic-platform instruction package, kept at arm's length), and method (a practitioner's encoded way of working). It then settles how customization vocabulary stacks. The load-bearing point: your personal side — your identity, your personal Memory, your continuity — is bound to you (your UUID), is always present, and follows you across every Companion you use. It is never swapped out. A method is optional specialization laid over your personal side. A vertical is a method aimed at a domain and sold as an offering. When you use someone's vertical, you are still you, with your personal side intact; their method is content running for you, as you. The personal side is invariant; method and vertical are optional content over it.


1. The three-way "skill" distinction (settled)

The manifest (v0.50) carried: "Skills" terminology three-way distinction unsettled. Carried. This note settles it. Three architecturally distinct things wore the one word; each now has its own.

1.1 Skill — a bounded transform (Sense 1, keeps the word)

The canon definition (queued-directions §1.2): a bounded structural transformation; no registered actor, no instruction set. A strict input/output contract — known input shape to known output shape, single-shot, no agency.

Phase 53 settled a sharp point: the discipline that survives is bounded contract, not no-LLM. A skill may call an LLM internally; what makes it a skill is the strict contract wrapping it and the absence of any will of its own. The value is the constraint.

Worked cases already in canon, all Sense 1: the Discovery-to-seed skill (Discovery record in, candidate seed out, conforming to R-A5–R-A11), the ExtractionSkill protocol, shaping skills, the materializer registry.

Keeps "skill." It is the canon definition, it is built, it is load-bearing. Qualify as Loomworks skill or bounded skill only where context needs the disambiguation.

1.2 Skill file — the platform artifact (Sense 2, kept at arm's length)

The Anthropic-platform SKILL.md artifact: an instruction package plus assets a model loads to do a task well. This project carries several (candidate-seed, foray, forge-spec, ogilvy-writing-audit).

This is an instruction set — exactly the thing a Loomworks skill (1.1) is defined not to be. The collision is direct and worth naming: the candidate-seed skill file (guides a model in a chat to author a seed) and the Discovery-to-seed skill (a contracted engine transform) do overlapping work from opposite sides of the architecture. Same domain, same old word, different kind.

Named "skill file" when it must be named, and otherwise kept out of Loomworks architecture vocabulary — it is an Anthropic-platform tool DUNIN7 uses to do its own work, not a Loomworks primitive.

1.3 Method — a practitioner's encoded way of working (Sense 3, new word)

What the sales-lens session called "purpose-built skills, the core of customization": a customer's method — their way of working a domain — encoded as reusable, delegable capability. The executive coach's intake sequence; the litigator's discovery-review discipline.

The key architectural recognition: a method is not a primitive — it is a bundle. It is composed from lower mechanisms the canon already names:

So "method" names a commercial-and-product bundle, not an engine primitive. The sales instinct ("purpose-built skills are the moat") was right; the word was wrong. The moat is not "we serve your vertical" — it is your method, encoded: the way a specific expert actually does the work, which a competitor cannot copy by serving the same domain.

"Method" chosen over "vertical" for this sense because it names the content (the encoded practice), not the market position; and because it composes grammatically downward — "a method uses these skills" reads correctly, where "a vertical uses these skills" stacks a category on a category. No canon collision: "method" is not in the seed's protected vocabulary.

1.4 The three, at a glance

TermLayerAgencyInstruction setLives
SkillEngine substrateNoNoIn the engine, in the pipeline
Skill fileModel-guidanceNo (guides a model)YesOutside the engine (SKILL.md)
MethodCommercial / productNo (a bundle)(a bundle)Sold to / built for a customer; composed from primitives

No two share a word.

2. The customization layering (settled)

A discussion of "how do we create custom Companions" surfaced that customization vocabulary stacks in a specific way. The layering was reached through four corrections (§3); this section states the destination.

2.1 The personal side is invariant — bound to the person, present across every Companion

Your personal side is a property of you, not of any Companion. It is bound to your identity (your UUID), it is always present, and it follows you across every Companion you use. It is never swapped out, never re-based, never replaced by specialization.

The personal side is three of the four personal facets the architecture already names (foundation note §5; functional spec §8): personal Memory (your content — what is held about you and your world), personal continuity (your identity — the persistent, named presence with your shared history), and personal capabilities (your function — your interface to the system). All three are yours and travel with you. The architecture already binds the Companion identity to the person's UUID (foundation note §1; functional spec §3, the built companion-kind actor bound to the person's UUID); the personal side is the content and continuity that binding carries.

This is the load-bearing correction over v0.1. v0.1 said "a custom Companion is the personal scope populated," which quietly allowed the personal base to be whoever's Companion this is — re-based per user. That is wrong. The personal side is not the base of a Companion; it is a property of a person, and it rides along no matter which Companion they are using.

2.2 Specialization is content laid over the personal side — never a replacement

The fourth facet — specialization (a method, or a vertical) — is content, and unlike the personal side it can be anyone's: yours, or a coach's method you are using, or a domain vertical you bought. Specialization is added and removed; the personal side never is.

A method (§1.3) is optional encoded practice laid over the personal side. It can be aimed two ways:

When you run a method — your own or someone else's — your personal side stays present underneath it. The method changes what the work looks like and how it is done; it does not change whose Companion this is. It is yours, running their content.

2.3 Vertical is a method aimed at a domain and sold

A vertical is a method pointed outward: aimed at a domain, packaged as an offering, sold. "Vertical" names the market position (the offering aimed at a domain); the method is the substance inside it that makes it work. You sell a vertical; the method is the moat inside it.

The invariance in §2.1 settles what happens when someone uses your vertical: they are still themselves. When you use a coach's vertical, you bring your own personal side; the coach's method is content running for you, as you. You do not become a guest in the coach's Companion — you bring your Companion, and it puts on the coach's method. Your personal Memory is present; your continuity is intact; the coach's method supplies the specialization. Two things in play, cleanly separated: your identity (yours, invariant) and the method (content, borrowed).

This preserves the architecture as written: foundation note §5.4 and functional spec §8.4 keep "vertical" untouched. The §8.4 phrase "personal vertical" is now read as the specialized corner of the personal side — the facet where a method aimed outward would live — not as the whole of customization, and not as something that displaces the rest of the personal side.

2.4 The shape, stated once

Your personal side — identity, personal Memory, continuity — is bound to you (your UUID), always present, and follows you across every Companion. It is never swapped out. A method is optional encoded practice laid over your personal side; it can be yours or someone else's, and you stay yourself while running it. A vertical is a method aimed at a domain and sold as an offering. The personal side is invariant; method and vertical are optional content over it.

Bound, as everything Companion is, by the founding axiom (functional spec §1.1): the Companion never reaches further than the raw Engine API. Customization shapes how the access layer behaves — voice, vocabulary, which capabilities surface, what is pre-authorized — never what the Engine permits. A custom Companion cannot be a fork; the Engine is the product and governs every caller equally.

2.5 Why this reinforces the agent driver

The invariance also sharpens the agent case (Axis 2, the agent driver). If the personal side follows the person, then when an agent runs your method, the identities stay cleanly separated: you are the principal (your personal side, your UUID, your Memory — the agent acts for you); the method is the content the agent runs; the agent is the driver, carrying OVA authorization to act as you under your personal identity, not its own. The agent has no personal side — it borrows yours, by authorization. This is exactly what OVA proves: "authorized to act for the person without being the person" (functional spec §9.1). The personal side stays the principal's across every driver and every specialization.

3. Trajectory — four corrections (Discovery record)

The §2 layering was not reached in one step. It took four corrections, each loosening an assumption the prior one still carried. Preserved so the path is walkable.

Start — Decision B. Vertical is the offering; method is the substance inside it. Settled in discussion as the first clean split of the overloaded "vertical." Assumption it carried: customization is always domain-aimed (every custom Companion has a vertical).

Correction 1 — "I have engagements across many subject areas; this is not really a vertical." The Operator's own desired Companion spans many domains, so it is not domain-aimed and has no vertical. Result: method lifted out of vertical and named the primitive; vertical became method-aimed-at-a-domain; the personal scope became method-aimed-at-you. Assumption still carried: every custom Companion has a method (is specialized in some encoded way).

Correction 2 — "the 'my Companion' example is a generalist." A generalist Companion serves the Operator across everything with no encoded method at all. Result: the requirement that customization means specialization fell away. The personal scope became the base (customization-to-you by default, no method required); method became optional specialization on top; vertical stayed as method-aimed-at-a-domain. Assumption still carried: the personal scope is the base of a Companion — which let the base be re-based per user.

Correction 3 — "have we preserved the personal side across all types? It is associated with our identity, so it should follow us across Companions." The personal side is not the base of a Companion that could vary per user — it is a property of the person, bound to the UUID, always present, following the person across every Companion, driver, and specialization. Result: the personal side is invariant; specialization (method, vertical) is content laid over it, never a replacement. When a person uses someone else's vertical, they keep their own personal side and run the other's method as content. This is the destination in §2.

Why the destination is right and not merely last. The architecture already bound the Companion identity to the person's UUID (foundation note §1; functional spec §3) and already listed the four personal facets with specialization (vertical) as a separate, fourth facet (foundation note §5; functional spec §8). The first three facets — Memory, continuity, capabilities — are the person; the fourth is specialization. Correction 3 recovers that separation, which v0.1 had collapsed by treating "populate the personal scope" and "specialize the Companion" as one operation. The corrections did not invent structure; they recovered the structure the architecture already implied, and freed it first from the domain-aimed assumption ("vertical"), then from the specialization-required assumption ("method"), then from the per-Companion-base assumption (v0.1 §2.1) that obscured identity-invariance.

4. What this settles, and what it leaves open

Settled.

Open (named, not decided here).

5. Propose, never carry — how a method relates to authority (settled)

§1.3 lists "the delegation contract" among a method's components, which raised a tension: the delegation contract is the sole locus of Companion authority (functional spec §9.3), so if a method contained a contract, installing a method would install authority — a back door around Operator-final-authority. This section settles it.

5.1 A method cannot carry a contract — structurally

A delegation contract is identity-and-engagement-bound: it authorizes a specific agent to act for a specific Operator (their UUID) in a specific engagement, and it is recorded as assertions that persist with that engagement (functional spec §9.3). A method is identity-and-engagement-agnostic: it is portable content that travels across engagements and across people (you can use a coach's method; the coach can sell it to many).

These are incompatible. A contract is bound to one UUID and one engagement; a method is bound to neither. A method therefore cannot carry a contract — not as a matter of policy, but structurally. This is the same invariance principle that settles the personal side (§2.1): authority binds to the person and the engagement; content does not. A method is content. Content cannot carry authority.

5.2 A method carries a contract proposal — inert, portable

What a method carries is a contract proposal: a description of what authority the method would need to run — which operations it needs included, which it recommends excluding (requiring explicit approval), a recommended autonomy rule (per_action / pre_authorized), a recommended scope and duration. The proposal is inert. It describes a shape; it grants nothing.

5.3 Installing drafts a held contract; the Operator commits it

When a method is installed into one of the Operator's engagements:

  1. The method's content becomes available — capability families, supplied Memory, render specialists, skills. No authority yet.
  2. The contract proposal drafts a held contract — conservative by default (§9.3), bound now to the Operator's UUID and this engagement, and held, exactly as every contribution entering Memory is held under held-then-commit (functional spec §1.2). Still no authority — it is held, shown, not granted.
  3. The Operator commits the contract — deliberately, as a separate act; or narrows it, or declines it. Only at commit does authority exist, recorded as assertions per §9.3.

Installing the method (step 1) and authorizing the agent (step 3) are two separate, deliberate acts, with the held contract (step 2) as the visible checkpoint between them. Propose, never carry — and the proposal becomes authority only through the same held-then-commit ceremony that governs all of Memory.

5.4 Why this is forced, not chosen

5.5 The one open sub-question

What the proposal is recorded as, and where it lives, is not settled. The contract is assertions in an engagement; the proposal is portable content that exists before any engagement adopts it — a portable, inert authority-shape the spec does not yet name. Two candidate homes: (a) the proposal is part of the method's own definition (a "recommended contract" block alongside capability families) — simplest, the working lean; (b) the proposal is a separate declared artifact the method references, reusable across methods — more flexible, more machinery, likely premature. This is a spec-level representation decision, left to the eventual Companion-spec revision, not settled here.

6. What a method holds — and how it pushes past a skill file

A common first instinct is that a method is "like a SKILL.md." This undersells it by an order of magnitude. A skill file is instructions a model loads — it shapes how a model behaves in one session, and it lives outside the engine, inheriting none of the engine's disciplines. A method is content that lives inside the architecture, persistent, with provenance, bound by the Engine's disciplines, laid over the Operator's invariant personal side. A skill file is a prompt; a method is a populated slice of the architecture.

6.1 The grounded component layers

From §1.3, a method is composed from primitives the canon already names — the floor:

6.2 The five boundary-pushes

Where a method becomes more than the sum of those parts — each possible because the method lives inside the architecture, and each beyond what a skill file can reach:

  1. Voice as a learned, surfaced, Operator-governed asset — not a style note. A skill file can say "be warm and concise." A method does something different in kind: it fills the vocabulary wall (functional spec §1.2) for its domain — the coaching method makes "session / client / intake" the surface words; the litigation method makes "matter / privilege / production" the surface words — and it can learn the domain's register from the engagement's accumulated assertions rather than have it hand-set, because the register is already present in how the engagement is written. Every assertion is a voice sample. The learned voice is correctable with provenance (refinements recorded as corrections, not overwrites) and inspectable (it traces to the assertions it was learned from). Crucially, learning informs but does not decide: the engagement speaks in one voice the Operator governs (see §7). The method surfaces the available registers; the Operator sets what the engagement says and how it says it.
  2. Shaping logic — how the domain arranges knowledge for a reader. The most underexploited. Shaping arranges organized knowledge for a specific reader (seed §73–85). A method carries the domain's characteristic shaping — the coach's summary leads with the client's stated goal, then progress, then homework; the litigator's assessment leads with exposure, then theory, then gaps. This is not format; it is the practitioner's judgment about what matters in what order for which reader — which is the expertise itself. A skill file has no concept of Shaping; it produces output. Encoding shaping logic is the closest thing to bottling the practitioner.
  3. Proactive triggers — what the domain watches for. The Companion has proactive behavior (Phase 44). A method carries domain-specific relevance triggers: the coaching method surfaces a goal set three sessions ago ("you wanted to revisit this"); the litigation method flags a new document that contradicts a prior assertion (a changed premise). This is the memory=recall reframe (queued §18.5) made domain-specific — which premises, in this domain, matter when they change. A skill file is reactive (runs when invoked); a method makes the Companion notice, on the domain's terms, unprompted. This is where "more than Siri" (queued §9) becomes domain-specialized.
  4. Composition with other methods and scopes. Because a method is content laid over the personal side (§2.2), and Shaping composes across scopes (seed §81, §99), methods stack. An Operator can run their generalist personal side + a coaching method + a jurisdiction's compliance scope; Shaping composes all three — the Operator's voice, the coach's shaping logic, the jurisdiction's required disclaimers — into one rendered artifact with full lineage. A skill file does not compose (two skill files fight for the prompt); methods compose because the architecture composes scopes. A customer can buy three methods and they layer, not collide.
  5. Accumulation from use (speculative — flagged). Because a method's components are Memory, and Memory accumulates with provenance, a method could improve from its own use: patterns that recur across many runs promote via the knowledge-elevation pathway (engagement knowledge promoting to a shared scope), admitted by the scope's trusted core. The method that emerges after forty uses knows more than the one that started — not re-written, but deposited-into. This is the compounding thesis (seed §151) applied to customization itself, and it turns "method as moat" from a switching cost into a widening one. Flagged speculative: it leans on the knowledge-elevation pathway and the trusted-core admission gate, both real but C5/domain-layer matters the seed defers.

6.3 The unifying recognition

All five are possible because a method is content living inside the architecture, so it inherits everything the architecture does — provenance, composition, Shaping, proactivity, accumulation, the vocabulary wall, scope-reach. A skill file lives outside the engine and inherits none of it. The boundary a method pushes past is exactly the boundary of "instructions to a model." A method is not instructions about the work; it is the work's accumulated, composable, provenance-bearing shape, laid over the Operator's invariant personal side. A skill file is at most the seed of a method's capability-and-voice layer; the Memory, composition, proactivity, and accumulation are architecture a skill file cannot touch.

7. Whose voice the engagement speaks in (settled)

A method can learn voice from accumulated assertions (§6.2 #1). That raised the real question: when an engagement speaks — in its Shaped and Rendered output — is that the Operator's voice, or a blend of the Operator and the Contributors? This is a governance question, not an attribution one (Contributors are always acknowledged; every assertion carries its contributor unforgettably — that is not in question here).

7.1 One voice, governed by the Operator

The engagement speaks in one voice, and that voice is the Operator's to govern. Two reasons:

7.2 The Contributors' registers are preserved as input, unified at output

The Contributors' voices do not vanish. They live in Memory, in the assertions, as written and attributed. They are simply not the engagement's outward voice by default. The mapping is room-shaped:

The engagement reads from many registers and speaks in one. Contributors' writing stays exactly as written in Memory; the Operator chooses one coherent register for what the engagement emits.

7.3 A blend is possible — as a deliberate Operator choice, never an automatic average

"The Operator's voice" names the default ownership, not a fixed register. Whether the engagement's voice equals the Operator's own register is itself an Operator decision:

The point: the engagement's voice is singular and Operator-governed; a blend is something the Operator commits to, not an automatic averaging of whoever wrote most.

7.4 Why automatic blend is the wrong default specifically

Blend-by-default — averaging Contributors' registers into the engagement's voice automatically — would make the voice drift with who wrote most lately, ungoverned: hire a verbose new Contributor and the engagement starts sounding verbose, with no one deciding it. That is an automatic state transition on something the Operator has authority over, which the architecture names a category error (seed §165: the system surfaces and signals; the Operator approves). The voice must not move on its own.

So the learned-voice machinery serves the Operator, never replaces them: the Companion learns the available registers from accumulated assertions and surfaces them ("your Contributors write in these registers; here is what an engagement voice could draw from"); the Operator governs what the engagement's voice actually is. Learning informs; the Operator decides.

7.5 The same principle, a third time

This is the source-is-acknowledged / authority-is-granted shape again: the Contributors' registers are supplied (in Memory, attributed); the engagement's voice is granted (the Operator decides what it is). It is the third instance this session, after the personal side (§2.1 — identity binds to the person; content laid over) and propose-never-carry (§5 — a method proposes; the Operator commits). Three instances of one principle — the source is acknowledged; the authority is granted — strengthen it as a candidate for naming as a first-class methodology principle at v0.21 consolidation.

7.6 The clean answer

The engagement speaks in one voice, governed by the Operator. The Contributors' registers live in Memory, attributed, as written — preserved as input, not erased. Whether the engagement's voice is the Operator's own register, an adopted house voice, or a blend that draws in a Contributor's register is the Operator's deliberate choice — never an automatic average of who wrote most. Learning surfaces the available registers; the Operator governs which one the engagement speaks in.

8. The two surfaces a method drives (settled)

A method can relate to an engagement in two ways, and the distinction is not lifetime (persistent vs. transient) but function — which surface of the engagement the method drives. The engagement has two surfaces, and a method's components sort to one or the other.

8.1 Installed → the interaction surface

A method installed into an engagement drives the interaction surface: the Companion's behavior — the conversational surface, how Q&A is delivered, how the engagement behaves when it is talked to. This is the live, in-the-moment experience of working with the engagement. It is driven by the method's interaction components: capability families (which operations the Companion initiates, in the domain's terms) and conversational voice (how it speaks in dialogue). The installed method shapes the conversation.

This is squarely the Companion's behavioral contract (functional spec §1.2) — gather, confirm, converse, deliver — populated for the domain. A coaching method installed makes the Q&A behave like a coach: it asks the coach's intake questions, surfaces goals the coach's way.

8.2 Referenced at Shaping → the production surface

A method named at Shaping drives the production surface: how a specific render is created — its unique style, structure, arrangement. This is the artifact, not the conversation. It is driven by the method's production components: shaping logic (how the domain arranges knowledge for a reader — §6.2 #2) and render specialists (domain-specific production — §6.1). The Shaping methods shape the artifacts.

This is squarely the Shaping room (seed §73–85), which already composes across sources for a particular reader. Naming a method at Shaping is the room reaching for exactly the kind of asset it is built to use: a method's shaping logic is a Shaping-room asset. Methods are named at Shaping the way scopes are — "shape this for this reader, using these methods' structures and styles."

8.3 One method, two surfaces — or different methods per surface

A method is a bundle (§6.1) whose components naturally sort to one surface or the other. So a method is not either installed or referenced — it is an object whose interaction components light up when installed and whose production components are drawn on when referenced at Shaping.

This makes the two surfaces independently choosable. A custom Companion can be installed with one method (so the Q&A experience behaves a certain way) and reference different methods at Shaping per render (so outputs are produced in other styles). Worked case: a Companion installed with a coaching method talks like a coach, and at Shaping references a brand-styling method for the client summary and a compliance method for the disclaimer — three methods, two surfaces, one Companion. The conversation and the artifacts are shaped independently.

8.4 Cardinality follows function

Because the interaction surface has one coherent behavior, an engagement normally has few installed methods (often one). Because a render can compose several styles, Shaping normally references many. This echoes the seed's two relationships to scopes (§37): an installed method is like membership (normally one — defines what the engagement is); a method referenced at Shaping is like reference (normally many, peer to one another — drawn on for a need, none defining the engagement). The cardinality is not a separate rule; it follows from which surface the method drives.

8.5 What carries over, and what is deferred

8.6 The clean statement

A method drives one of two surfaces of the engagement. Installed → the interaction surface (the Companion's behavior, how Q&A is delivered) — driven by the method's interaction components, normally few. Referenced at Shaping → the production surface (how a render is created, its unique style) — driven by the method's production components, normally many. One method can drive both, or different methods can drive each: the installed method shapes the conversation, the Shaping methods shape the artifacts. Cardinality follows function; voice stays Operator-governed across both (§7); referenced-method conflict inherits the deferred scope-composition resolution (seed §85).

9. The interaction surface references a personality domain (dependency named; substance deferred)

The interaction surface (§8.1) is where the installed method gives an engagement its interaction character — how it asks (elicitation), how heavily it confirms, what it proactively recalls mid-conversation (§6.2 #3), and how it pitches answers (register and depth). This is what makes one engagement feel like a coach and another like a litigation associate, even though both are the same Companion over the same Engine.

9.1 The character is referenced, not improvised

That interaction character is not a set of free-floating style choices. Interaction style is itself a typed domain — there are established frameworks and taxonomies of personality and interaction (personality typologies, interaction-style models, and the like), each with its own structure, vocabulary, and settled distinctions. A method's interaction character would be grounded in that domain, the way a litigation method's content is grounded in legal doctrine.

In the architecture's terms, this is a referenced domain (seed §37, the reference relationship; queued §8.1, supplied domain Memory). The interaction surface does not invent its character; it references an interaction/personality domain held as Memory with provenance. So §8.1 is sharpened: the installed method's interaction components are its conversational components grounded in referenced knowledge about interaction itself.

9.2 The domain is a dependency not yet in the canon

This interaction/personality domain is not present in the canon today — not built, not seeded, not referenced anywhere. It is a referenced-domain dependency the interaction surface needs and does not yet have. Naming the dependency is the finding of this section.

9.3 The substance is deferred, deliberately

The substantive typology work — which interaction styles exist, how they map to elicitation/confirmation/recall/delivery behaviors, how a method selects and composes them — cannot be driven from a single discussion session and is deliberately not attempted here. Doing it from reasoned-from-memory typologies would violate the vocabulary-deference discipline: defer to a domain's settled structure rather than substituting a default reconstruction of it. The right home for that work is a session — or an engagement — where the interaction/personality domain is actually present as sourced Memory, typed, with provenance, governing the substance rather than being narrated.

Open direction (for a domain-present session): bring an interaction/personality domain into the canon as referenced Memory, then do the interaction-surface typology work against it. Until then, §8.1's interaction character is structurally located but substantively ungrounded.

9.4 Connection to the standing Companion

This composes with the standing Companion (queued §10), the Operator-bound mode that runs across all engagements. The picture: the personal side is invariant (§2.1), carried by the standing Companion across every engagement; each engagement's installed method supplies its interaction character, grounded in the referenced personality domain; so a person moving between engagements moves between interaction characters (coach-mode here, litigation-mode there) while their identity stays constant underneath. One identity everywhere; per-engagement character. This is a distinctive product property — most assistants are one personality everywhere; Loomworks would be one identity everywhere with per-engagement character — but it rests on the deferred domain (§9.3) before the character half can be done justice.

A tension noted, not resolved (it waits on the same domain): where an engagement's method-supplied interaction character pulls against the Operator's standing personal preferences (the personal side prefers terse; the installed method asks open and waits), which governs? The working lean, consistent with §7 and §5: the personal side sets the floor, the method shapes within it, and genuine conflicts are surfaced for Operator decision, not auto-resolved (seed §165). This would be the fourth instance of the source-supplies / Operator-governs principle (after §2.1, §5, §7).