← Portfolio
jakelawrence.xyz / process

The Prompt Architecture Behind The Beautiful Unfinished

How a layered system of meta-prompts, discipline bibliographies, a creative brief, a ten-phase editorial pipeline, and a formal acceptance gate turned a single observation about planning into a 38,000-word interdisciplinary essay — using AI as instrument, not author.

10 Disciplines132 Sources10 Audit Prompts10 Pipeline Phases38,158 Words
Scroll
00 — The Premise

Why document this at all?

Most discussions of AI-assisted writing treat the tool as a black box: put a question in, get an answer out. The Beautiful Unfinished was built differently. The AI was never the writer — it was a research partner, structural auditor, and production instrument embedded within a deliberate, human-designed prompt architecture that governed every stage from initial ideation through formal publication acceptance.

The full pipeline spans ten phases across two major arcs: five diagnostic audit phases that evaluate the manuscript, and five remediation phases that move it from “complete draft” to “accepted for publication.” What follows is a complete account of that architecture.

“The essay investigates why the plan feels better than the thing, why that might not be a malfunction, and what it costs to love a garden you can never walk through.”— Creative Brief, §1
01 — The Pipeline

From Observation to Accepted Manuscript

The project moved through distinct stages, each governed by its own prompt logic. Later stages were structurally dependent on the outputs of earlier ones — a directed acyclic graph of constraints ensuring coherence across 38,000 words and ten academic disciplines.

Pre-Production

01

Creative Brief

35-page master document defining thesis, audience, tone, register, narrative arc, AV specifications, editorial constraints, and research foundation.

02

Bibliography Meta-Prompt

Template prompt run ten times — once per discipline — generating annotated bibliographies with load-bearing designations and cross-disciplinary bridges.

03

Discipline Bibliographies

Ten structured bibliographies (132 sources, ~50 load-bearing) with annotations, relevance notes, AV opportunities, and gap analyses.

Drafting

04

Section Drafting

Six narrative sections plus introduction, each drafted with forward-reference to the brief and backward-reference to completed sections.

05

Formal Bibliography

Chicago Manual of Style bibliography compiled from all ten discipline sources, reconciled against actual text citations.

The Ten-Phase Editorial Pipeline

I

Structural Audit

Thread-tracking, pivot stress test, pacing & proportion. Are the bones right?

II

Coverage Audit

Claim-source mapping, discipline balance, bibliography reconciliation. Are the claims honest?

III

Integration Audit

AV set piece anchoring, transition surgery. Do the pieces connect?

IV

Voice Audit

Voice calibration, constraint compliance. Does it sound right?

V

Polish Audit

Opening-closing resonance, sentence-level polish. Is every sentence earning its place?

VI

Triage

Findings deduplicated, classified, prioritized, and assembled into a Revision Manifest with dependency ordering.

VII

Revision

Section-by-section execution of the Manifest. Each change logged with finding reference, word count delta, and rationale.

VIII

Re-Audit

Targeted verification that revised passages resolve flagged issues without introducing new problems.

IX

Acceptance Gate

Ten publication-readiness criteria evaluated. ACCEPTED, ACCEPTED WITH CAVEATS, or RETURNED FOR REVISION.

X

Production Handoff

Assembled manuscript, reconciled bibliography, AV-cued narration text, editorial archive, format-converted files.

Each stage produces artifacts that become required inputs for subsequent stages. The bibliography meta-prompt cannot run without the creative brief. The audit prompts cannot run without the completed sections. The revision manifest cannot exist without the audit reports. The acceptance gate cannot evaluate without verified revisions.
02 — The Creative Brief

The Master Document That Governs Everything

Before a single word of the essay was written, the creative brief established the structural, tonal, and argumentative parameters that every subsequent prompt would inherit.

What It Specifies

The creative brief is not a vague project description. It is a formal specification document that defines the one-sentence version of the essay, the problem it addresses, the precise audience (primary, secondary, assumptions), the tonal register with positive and negative exemplars, the three core arguments, the six-section narrative arc, two structural pivots, ten non-negotiable audiovisual set pieces, and nine editorial constraints that bind every word.

The Three Core Arguments

The brief defines three interwoven arguments that must remain distinct but braided across all sections. No section may advance all three equally — that produces “mush, not synthesis.”

F
Formal (Double Bind). The plan simultaneously holds low Kolmogorov complexity and high Shannon entropy. Execution destroys both. Grounded in information theory and algorithmic complexity.
H
Historical (Moral Genealogy). Protestant ethic → industrial discipline → achievement society → self-optimization culture. The shame of the unfinished is not timeless — it is culturally constructed across five centuries.
P
Phenomenological (Loss/Grief). Every execution is an elimination. The plan holds all futures. Execution collapses possibility to singularity. Chronic planning is a form of anticipatory grief.

Tone Calibration — Positive and Negative

Rather than describing the tone abstractly, the brief specifies it through comparable registers: Sarah Manguso’s reflective thinking-about-thinking, James C. Scott’s academic rigor made accessible, Oliver Sacks’s neuroscience that honors the human, Jenny Odell’s productivity criticism that refuses to become a productivity book, and Borges’s ideas rendered as images that outlast the argument.

It then defines what the essay is not: not self-help, not confessional, not ironic, not a survey. These negative constraints proved more powerful than the positive ones — they prevented the essay from collapsing into familiar registers that the topic constantly invites.

Key Design Decision

The creative brief includes Constraint #5: “No productivity advice. If a reader finishes the essay and feels motivated to ‘finally start that project,’ the essay has failed.” This single constraint shaped every prompt that followed — the AI was instructed to flag and remove any passage that drifted toward exhortation. It was also what caught the essay’s original closing in Phase V and sent it back for surgery.

03 — The Bibliography Meta-Prompt

One Template, Ten Executions

The bibliography meta-prompt is a reusable template that generates a comprehensive, annotated bibliography for one discipline at a time — then bridges it to all the others.

The meta-prompt specifies a six-part output structure for each discipline: 15–30 sources spanning foundational texts through recent meta-analyses, full citations with 2–4 sentence annotations, explicit relevance notes connecting each source to the essay’s argument, cross-disciplinary bridge flags, 3–5 load-bearing source designations, 2–3 audiovisual opportunity flags, and a gaps-and-tensions analysis acknowledging where the literature is contradictory or thin.

The Cross-Cutting Themes

Every discipline bibliography was generated against a shared set of cross-cutting themes: anticipation versus consummation, possibility space and its collapse, identity and narrative, the social performance of planning, and loss, grief, and the death of alternatives. This ensured that each discipline’s bibliography was pre-mapped to the essay’s argumentative axes before a single section was written.

10
Disciplines
132
Sources
~50
Load-Bearing
~45
AV Opportunities
5
Cross-Cutting Axes

The Discipline Map

D1
Neuroscience
18 sources · 4 load-bearing
D2
Cognitive Psychology
15 sources · 4 load-bearing
D3
Behavioral Economics
15 sources · 4 load-bearing
D4
Philosophy of Action
14 sources · 4 load-bearing
D5
Phenomenology
13 sources · 3 load-bearing
D6
Creativity & Design
13 sources · 3 load-bearing
D7
Clinical Psychology
12 sources · 3 load-bearing
D8
Sociology & Cultural Studies
10 sources · 4 load-bearing
D9
Organizational Theory
9 sources · 3 load-bearing
D10
Information Theory & Complexity
7 sources · 3 load-bearing
04 — The Narrative Architecture

Six Sections That Mirror the Phenomenon They Describe

The essay’s structure is not an arbitrary container. The six-section arc — Spark, Build, Plateau, Turn, Drift, Reflection — mirrors the phenomenological cycle of planning and not-executing that the essay investigates.

Section 01
The Spark
D5 Phenomenology · D6 Creativity & Design
Opening of possibility space. Husserl’s protention, Heidegger’s Entwurf, the “groan zone.” Contains a planted seed for Chaitin’s undecidability.
Section 02
The Build
D1 Neuroscience · D2 Cognitive Psychology
Dopamine escalation. Prediction error, wanting versus liking, affective forecasting. The brain rewards you most for the thing that gets least done. Seeds the historical thread.
Section 03
The Plateau
D4 Philosophy of Action · D10 Information Theory
The perfect plan and its formal limits. Shannon, Kolmogorov, Borges. Contains Pivot 2 (Chaitin’s Limit): the optimal compression of a project into a plan is formally undecidable.
Section 04
The Turn
D3 Behavioral Economics · D7 Clinical Psychology
The emotional pivot. Loss aversion, option value, procrastination, perfectionism + Chaitin aftermath. The turn is not a moment of motivation — it is a moment of loss.
Section 05
The Drift
D9 Organizational Theory · D8 Sociology
Institutional and cultural forces. Weber → Han → Rosa → Berlant. Contains Pivot 1 (Weick’s Inversion): plans are retroactive sense-making, not blueprints.
Section 06
The Reflection
Synthesis — All Ten Disciplines
Ten disciplines in conversation. The garden metaphor held — not as answer but as richer understanding. Compassion and openness, not exhortation. The dopamine system does not read essays.
The Two Structural Pivots

Chaitin’s Limit (Section 3): the optimal plan is formally undecidable — planning must stop not because the plan is good enough, but because “good enough” is unreachable. Weick’s Inversion (Section 5): the causal arrow is reversed — people act first and construct plans retroactively. The Phase VII revision strengthened the Chaitin thread to run a clean five-beat arc across S1, S3, S3–Borges bridge, S4, and S6 — making it structurally non-removable.

05 — The Drafting Protocol

How Each Section Was Actually Written

Each of the six sections was drafted in a separate conversation, with a specific prompting protocol that embedded the creative brief’s constraints into the writing process.

The drafting prompt provided the AI with the complete creative brief, all relevant discipline bibliographies, and all previously completed sections as context. It then specified the section’s primary and secondary disciplines, the argument threads to foreground, the voice constraints, and any structural requirements such as pivot delivery.

The Forward-Backward Reference System

Each section was composed with forward-reference to the creative brief and backward-reference to all previously written sections. This created a one-directional dependency chain: Section 3 was drafted knowing Sections 1 and 2 but not Sections 4–6. This asymmetry is precisely why the full editorial pipeline exists — only retrospective analysis could verify that the accumulated text delivered what the brief specified.

The Nine Editorial Constraints (Enforced at Draft Time)

1
No discipline under 2,500 or over 5,500 words. Interdisciplinary, not mono-disciplinary with guests.
2
Every claim is sourced. The bibliography is not decorative — a genuine literature review across 132 sources.
3
AV components planned from outline stage. The ten set pieces are structural, not decorative.
4
The essay acknowledges its own position. Does not pretend to objectivity, but pursues rigor.
5
No productivity advice. If a reader feels motivated to “finally start that project,” the essay has failed.
6
Technical terms introduced through examples before being named. Builds mathematical intuition.
7
Historical argument avoids teleology. Weber → Han is illuminating, not causal.
8
Three arguments distinct but interwoven. No section advances all three equally — mush, not synthesis.
9
The essay does not resolve. It arrives at the garden. Compassion and openness, not exhortation.

The Diagnostic Arc

Phases I–V · 10 Prompts · 5 Sequential Passes

06 — Phases I–V: The Audit

A Custom AI Skill for Pre-Publication Review

The audit system is a full Claude Project skill — a structured workflow with ten distinct prompts, organized into five sequential phases, each with defined inputs, evaluation criteria, severity ratings, and output formats.

Phase I — Structural

Are the bones right?

Thread-tracking maps where each of the three core arguments is planted, developed, and interwoven — flagging orphaned seeds, unplanted pickups, redundancy, and the “no equal weight” constraint. Pivot stress testing evaluates whether Chaitin’s Limit and Weick’s Inversion achieve their required destabilizing effect. Pacing and proportion verifies word counts, argumentative density, and whether the emotional pivot arrives at 55–65% of total length.

1A Thread-Tracking3 Pivot Stress Test8 Pacing & Proportion
Phase II — Coverage

Are the claims honest?

Claim-source mapping walks through every attributed claim with accuracy flags (✓ accurate, ~ simplified, ✗ misrepresented, ? absent). Discipline balance estimates word counts per discipline and calculates source utilization ratios. Bibliography reconciliation is the final cross-check: every name has a source, every load-bearing source is cited, ghost sources identified, orphan references flagged.

2A Claim-Source Mapping2B Discipline Balance6 Bibliography Reconciliation
Phase III — Integration

Do the pieces connect?

AV anchoring audits the ten non-negotiable audiovisual set pieces for textual grounding, argumentative weight, and modality independence. Transition surgery evaluates each section-to-section transition on closure, anticipation, and tonal modulation (rated 1–5), with alternative drafts for any score below 3.

4 AV Anchoring1B Transition Surgery
Phase IV — Voice

Does it sound right?

Voice calibration identifies register breaks — passages where the prose shifts between academic, conversational, lyrical, and clinical registers unintentionally. Constraint compliance runs a systematic check against all nine editorial constraints, referencing outputs from earlier phases.

5 Voice Calibration9 Constraint Compliance
Phase V — Polish

Is every sentence earning its place?

Opening-closing resonance evaluates whether the closing transforms the opening image rather than merely repeating it — testing for “phantom resolution” where the essay smuggles in the productivity-morality it spent 37,500 words dismantling. Sentence-level polish hunts verbal tics, hedging accumulation, over-explanation, rhythm monotony, italics overuse, and paragraph length imbalances.

7 Opening-Closing Resonance10 Sentence-Level Polish

What the Audit Found

Across all five phases and ten prompts, the audit surfaced zero critical issues, eight major issues, and twenty-two minor issues. The most significant findings shaped the entire remediation arc.

FindingPhaseSeverityResolution
S2→S3 transition misdirects reader (promises social performance, delivers philosophy)IIIMajorS2 closing rewritten; verified Phase VIII
Closing’s phantom resolution — “the path is real / the garden is not” declares a winner the essay hasn’t earnedVMajorFinal five lines revised; Chaitin callback added
Verbal tic accumulation — “genuine” (35×), “not merely” (29×), “not because” (30×)VMajor~55 instances removed in global pass
Productivity system time-lapse AV set piece completely unanchoredIIIMajor210-word passage written; set piece anchored
Zeigarnik referenced 8 times, absent from bibliographyIIMajorAdded to formal bibliography
Chaitin thread removable without breaking downstream sectionsIMinorSeeds added in S1 and S4; now non-removable
Historical thread absent for first 56% of essayIMinorSeeded in S2’s revised closing
S3 italics density 12.3 per 1,000 wordsVMinor73 → 58 italics; 15 removed
Full Pipeline DAG
Diagnostic Arc — Evaluate
I
Structural
1A Thread-tracking
3 Pivot stress test
8 Pacing / proportion
II
Coverage
2A Claim-source map
2B Discipline balance
6 Bibliography recon
III
Integration
4 AV anchoring
1B Transition surgery
IV
Voice
5 Voice calibration
9 Constraint compliance
V
Polish
7 Open/close resonance
10 Sentence-level polish
Remediation Arc — Fix & Verify
VI
Triage
Revision Manifest
deduplicated, prioritized, dependency-ordered
VII
Revision
Section-by-section change log
finding ref + word count Δ
VIII
Re-Audit
Targeted verification
of revised passages
IX
Acceptance Gate
10 criteria evaluated
ACCEPTED / RETURNED
X
Production
Final deliverables assembled
The Pivot
“The path is real. The garden is not. And the choice — which is not really a choice but a grief — is yours.”

These were the essay’s final lines. They sounded like wisdom. The Phase V audit identified them as a phantom resolution — three sentences that smuggled in the productivity-morality the essay had spent 37,500 words carefully dismantling.

“The path is real / the garden is not” declares a winner in a contest the essay argued has no winner. “The choice is yours” re-individualizes a problem the sociology section proved is structural. “The plan cannot make it for you” ends the essay on a line indistinguishable from a commencement address.

The audit caught what a human reader might have applauded. The constraint caught what taste might have missed. The closing was sent back for surgery, and the essay’s most honest contribution — its refusal to resolve — was restored.

The Remediation Arc

Phases VI–X · From Findings to Accepted Manuscript

07 — Phases VI–IX: From Findings to Acceptance

The Pipeline’s Second Half

The five diagnostic phases produce findings. The five remediation phases transform those findings into a revised, verified, and formally accepted manuscript. This is where most AI-assisted writing projects stop — and where this one kept going.

Phase VI — Triage

The Revision Manifest

All findings from Phases I–V are deduplicated, classified by revision type (structural, textual, factual, mechanical), grouped by section, and prioritized into a single dependency-ordered action list. Each finding gets a number (F-01 through F-22), a severity rating, and a specific remediation recommendation. Critically, the Manifest specifies revision order — structural changes before textual ones, because surface polish on a passage that needs structural surgery is wasted effort.

DeduplicationClassificationDependency OrderingSection Grouping
Phase VII — Revision

Section-by-Section Execution

Revisions executed in Manifest order (Introduction → S1 → S2 → S3 → S4 → S5 → S6 → Bibliography), with each change logged against its finding number, including exact word count deltas. The S2→S3 transition was rewritten, the S6 closing’s phantom resolution replaced with held tension, the Chaitin thread strengthened with seeds in S1 and S4, two AV set pieces written from scratch in S5, ~55 verbal tic instances reduced, and three bibliography entries added. Net: 37,505 → 38,158 (+653 words). 18 of 22 findings addressed in one revision cycle.

18 / 22 Findings+653 Words~55 Tics Removed1 Revision Cycle
Phase VIII — Re-Audit

Did the surgery take?

Targeted re-checks organized by priority. High: the rewritten S2→S3 transition, the revised S6 closing. Medium: the two new AV set pieces, the Chaitin thread. Low: historical seed, bibliography additions, verbal tics. All seven targets passed. Two were rated strengthened relative to pre-revision state. Zero issues introduced by revisions.

7 Targets7 / 7 Passed2 Strengthened0 New Issues
Phase IX — Acceptance Gate

Is this publication-ready?

A holistic ten-criterion evaluation. Each criterion evaluated independently with a PASS / FAIL / PASS WITH CAVEATS rating. The essay passed all ten — structural continuity, transition quality, claim-source integrity, discipline balance, pivot effectiveness, AV anchoring, voice consistency, bibliography accuracy, opening-closing resonance, and pacing. Three minor caveats noted; none sufficient to warrant return. Verdict: ACCEPTED.

10 / 10 Passed0 Critical3 CaveatsACCEPTED

The Ten Acceptance Criteria

01
Structural Continuity — three arguments planted, developed, interwoven
Pass
02
Transition Quality — all six transitions scored 3+ on closure, anticipation, tonal modulation
Pass
03
Claim-Source Integrity — zero unattributed major claims across ~90 attributed claims
Pass
04
Discipline Balance — all ten disciplines within 2,500–5,500 word constraint
Pass
05
Pivot Effectiveness — both pivots create conceptual vertigo
Pass
06
AV Anchoring — all ten set pieces textually anchored and modality-independent
Pass
07
Voice Consistency — all nine editorial constraints met
Pass
08
Bibliography Accuracy — 132 sources, no orphans, no ghosts
Pass
09
Opening-Closing Resonance — recognition, transformation, emotional shift, openness
Pass ↑
10
Pacing and Proportion — turn at 55%, synthesis at 12.4%, no section drags
Pass
08 — Design Principles

What Makes This System Work

The prompt architecture follows six principles that distinguish it from naive AI-assisted writing.

01

Constraint Propagation, Not Instruction

The system never tells the AI what to write. It defines the space of acceptable outputs through cascading constraints. The brief constrains the bibliographies. The bibliographies constrain the drafts. The audit verifies constraint adherence retroactively.

02

Separation of Generation and Evaluation

Drafting and auditing happen in different prompts, different conversations, different contexts. The audit evaluates text without access to the original drafting instructions. The AI never grades its own homework.

03

Closed-Loop Verification

Problems must be fixed (VII), fixes must be verified (VIII), and the complete manuscript must pass holistic evaluation (IX) before acceptance. A finding that fails re-audit loops back. The pipeline has no exit that bypasses verification.

04

Finding-Level Traceability

Every revision traces to a finding number. Every re-audit target traces to a revision. Every acceptance criterion traces to an audit phase. The provenance of any sentence can be traced backward through the entire pipeline.

05

Negative Constraints as Primary Controls

“No productivity advice.” “Does not resolve.” “Not confessional.” These eliminate failure modes rather than prescribing successes. The phantom resolution was caught because Constraint #5 was defined negatively.

06

The Meta-Recursive Quality

An essay about the rewards of planning, built through an elaborate planning system. The architecture is the phenomenon, observed from within. Constraint #4 requires the essay to acknowledge this without winking about it.

09 — The Ten AV Set Pieces

Visual Arguments That Carry Weight

The creative brief specifies ten audiovisual set pieces. Each must be textually anchored, carry argumentative weight rather than merely illustrating text, and satisfy modality independence — the text works without the visual, the visual could work without the text.

Information-Theoretic Cluster
Set Piece 01
Entropy Cloud Collapse
D10 Shannon · S3
The shimmering cloud of possibility collapsing to a single point as execution proceeds. Makes the beauty of the high-entropy state viscerally felt.
Set Piece 02
Seed to Tree
D10 Kolmogorov · S3
The tiny elegant plan and the massive sprawling reality it implies. The information-theoretic asymmetry between compression and decompression, made visible.
Set Piece 03
Garden of Forking Paths
D10 Borges · S3/S6
The essay’s signature image. Overhead garden with infinite forking paths darkening one by one as execution proceeds. The central node around which all other visuals orbit.
Neuroscience Anchor
Set Piece 04
Reward Prediction Error
D1 Schultz · S2
Three panels: unexpected reward (dopamine burst), predicted reward (silence), omitted reward (dip below baseline). The brain’s reward system as prediction machine, not pleasure meter.
Sociological Cluster
Set Piece 05
Protestant Ethic Montage
D8 Weber→Han · S5
Five centuries, one guilt. Monastic scriptoriums → Calvinist workshops → Victorian factories → open-plan offices → a person alone at 2 AM with a project management app.
Set Piece 06
Front Stage / Backstage
D8 Goffman · S5
Split screen. Left: person excitedly describing the project at a dinner party. Right: same person staring at a blank document at 11 PM. The simultaneity is the argument.
Set Piece 07
Shrinking Present
D8 Rosa · S5
Split-screen time-lapse: a plan being written on one side, the world changing on the other. The plan takes a week to write; by the time it’s done, the world it describes has moved on.
Organizational Cluster
Set Piece 08
Strategic Plan vs. Reality
D9 Mintzberg · S5
Side by side: the beautiful formatted plan beside the messy, branching, improvisational path of what actually happened. Two paths diverging like a river delta.
Set Piece 09
Productivity System Time-Lapse
D9 Covey · S5
Friday evening: building the system. Color-coded categories, nested hierarchies. Monday morning: pristine. Monday 9:03 AM: checks email instead. Written in Phase VII to anchor this previously missing set piece.
Set Piece 10
Child vs. Adult
D9 March · S5
A child finger-painting, completely absorbed, no plan, pure action. Cut to: an adult paralyzed by goals and standards. March’s “technology of foolishness” made visible. Written in Phase VII.
The ten set pieces form a coherent visual architecture with the Garden of Forking Paths as the central node. The information-theoretic cluster visualizes the formal argument from three angles. The sociological cluster visualizes the cultural forces. The organizational cluster visualizes institutional dynamics. The neuroscience anchor provides the empirical foundation.
10 — A Note on Authorship

The Human in the Architecture

The question that hangs over any AI-assisted project: who wrote this?

The honest answer is that the question itself is malformed. The creative brief — the document that determines what the essay argues, how it argues it, what it refuses to argue, what it sounds like, and what it is not allowed to become — is entirely human. The bibliographic research, while compiled with AI assistance, was directed by human curiosity and constrained by human judgment about what matters. The editorial audit system, with its ten prompts and ten phases and severity ratings, is a human design for quality control.

The AI contributed what AI is good at: holding 132 sources in working memory simultaneously, maintaining tonal consistency across 38,000 words without fatigue, tracking three interwoven arguments across six sections without losing the thread, and producing prose that operates within the narrow register the creative brief demands — academic but humane, rigorous but compassionate, precise but not cold.

But perhaps the most telling artifact of human authorship is the Phase V discovery — the moment the audit system caught the essay’s own closing smuggling in a resolution the essay hadn’t earned. “The path is real / the garden is not” sounds like wisdom. It takes a human, reading with the full weight of 37,500 preceding words, to recognize it as betrayal. The AI could identify the structural violation. The decision that it was a violation — that the essay’s refusal to resolve is not a weakness but its most honest contribution — that was human.

The architecture is the authorship. The prompts are the creative decisions. The constraints are the taste. And the final judgment — this passes, this doesn’t, this needs surgery — remains, as it always does, human.