pieta.ip
System Brief · IP & Knowledge Development · 2026-09-01

From Atoms to
Attorney-Ready Patents

A self-improving engine that takes an idea, grounds it in 791 real patents and 29,175 verified atoms, generates hundreds of mechanism variants, compresses the best into novel hybrids, and exits with a complete attorney-ready patent package — and 31 commercial documents — before a human has had coffee. Then it turns itself inward and improves.

Substrate 791 EPO patents · 29,175 atoms
Patent packages 67+ attorney-ready (55 umbrella · 7 cooling · 5 metsigen)
Active IP domains metsigen · cooling · umbrella
All-time cost $173.88 · 25,680 API calls · 124M tokens
Pipeline outputs 19 autonomous · 31 docs/idea
Updated 2026-09-01
Built by David A.B. Van der Walt · Sole architect · 18 months · 25+ peer-reviewed papers · 2 patents filed · Accredited Financial Advisor · Patent pending PPN00002480
67+ attorney-ready packages 19 autonomous pipelines 31 documents per idea $173.88 total system cost
✓ We'll be in touch.

Who this is for

IP Firms & Counsel

Accelerate prior-art synthesis and draft generation. Attorney-ready packages go directly to prosecution — no reformatting required.

Industrial Partners

Turn mechanism concepts into commercial IP pathways and 90-day market entry blueprints across active domains.

Deep-Tech Investors

Evaluate a self-improving IP refinery, not a single patent. The moat is the substrate, the provenance, and the compounding loop.

Research Institutions

Convert frontier technical insights into protectable assets. The system generates, rates, and packages without human coordination.

Executive Summary

Pieta is a fully autonomous IP generation engine that turns a single anchor mechanism into attorney-ready patent packages — grounded in 791 real EPO patents and 29,175 verified mechanism fragments, with zero hallucination and full claim traceability.

Over 18 months, it evolved from a first documented run of 3,457 candidates into a 6-phase pipeline spanning Hunter-Killer ideation, E1.5 sectional trimming, SYNTH hybrid compression, and a 31-document commercial strategy layer — all without external headcount.

The system has delivered 67+ attorney-ready patent packages across three active IP domains — 55 from the umbrella IP Foundry proof (Tests 1 & 2), 7 from the cooling domain, 5 from metsigen — and then turned its own combinatorial engine inward: Pieta Mirror generated 7,490 self-analysis ideas and identified 15 buildable system improvements, with 7 independent derivations converging on the same structural fix.

Total all-time cost: $173.88. Equivalent manual IP foundry engagement: $300,000+. The engine that files is itself the IP: PPN00002480.

The system is live, production-grade, and self-improving. It is seeking the right institutional partnership for its next phase — whether that is IP filing and commercialisation, joint research, or strategic alignment. A 30-minute walk-through of any section of this brief is available on request.

01

The Problem

IP generation is broken — too slow, too expensive, and industrially blind. The countries that file fastest set the standards. The companies that file first own the markets.

Why Now

Global patent filing is accelerating. Volume alone no longer differentiates strong portfolios: the institutions that close the quality and speed gap — filing grounded, novel mechanisms faster than competitors can prior-art them — define the next decade of technical standards. Speed and precision are the only remaining leverage.

What Breaks

Noise — 3.2M utility models buried in prior art. Speed — provisional windows close while lawyers draft. Blind spots — no system sees structural isomorphisms across domains. Hallucination — LLMs generate claims with no grounding.

The Cost of Missing It

$23.7B+ in documented losses attributable to missed provisional windows, failed freedom-to-operate searches, and standard-essential patent traps. One missed filing can lock a company out of a market permanently.

Volume without precision is noise.
Pieta files with both.
The Economics Case

A manual IP foundry engagement — attorney team, technical consultancy, 18-month runway — costs $300,000+ for a comparable patent portfolio. Pieta delivered 67+ attorney-ready packages across three domains for $173.88 all-time. Zero external headcount. Under 30 days from anchor definition to first filing-grade output.

Phase 1 · The Foundation
02

The Refinery

Before a single patent idea could be generated, the engine needed something no LLM has: a grounded substrate. 791 real EPO patents across 32 domains, 7 meta-families — parsed, atom-extracted, and verified against a multi-model Reality Gate before a single claim was written.

The Engine — 5 Stages

Draw → Triangulate → Diverge → Ground → Audit. Five independent passes against the atom pool. Every output is traceable to its source atoms and the original patent text. No claim exists without provenance.

  • Draw: sample atoms from pool by semantic distance
  • Triangulate: find cross-domain structural isomorphisms
  • Diverge: expand the combination space
  • Ground: verify against substrate — kill ungrounded claims
  • Audit: Reality Gate — multi-model panel verdict

The Substrate

Three atom pools, built and verified over multiple runs. Legacy pool (first extraction pass), Universal Library corpus, and Synthetic verified pool — all passed the Reality Gate before entering production.

  • Legacy atoms: 3,003 (original EPO extraction)
  • Universal Library: 8,494 atoms
  • Synthetic verified (Gen 2): 17,678 atoms
  • Total: 29,175 verified atoms
  • 791 EPO patents · 32 domains · 7 meta-families

Anti-Collapse Proof

Gen 2 scaled run (2026-07-17): 142 synthetic atoms through the full Reality Gate under concurrent load. The engine held. No hallucinated atoms entered the pool.

  • Gen 1 baseline: 4,740 tested → 4,692 passed (99.0%)
  • Gen 2 scaled: 142 tested → 139 passed (97.9%)
  • 3 Reality Gate rejections — correctly caught and logged
  • 6 documented incidents — all resolved, all in the record
459
Outputs Shipped

334 chapters · 22 theses · 103 blueprints

$173.88
All-Time Cost

$57.16 last 30 days · 25,680 API calls · 124M tokens

97.9%
Survival Rate

Gen 2 scaled run — atoms that passed the Reality Gate

29,175
Verified Atoms

In the production pool — every atom earned its place

Phase 2 · The Hunt
03

Hunter-Killer. Sniper. Anchor.

The refinery proved the engine. The Hunt armed it. Instead of exploring the full idea space randomly, Pieta is given a specific mechanism target — the Anchor — and the grid systematically explores every way atoms from the substrate can combine with it to produce something new and fileable.

The Anchor

Each IP project starts with a single high-value mechanism target — a specific engineering challenge in a domain where IP whitespace exists. The anchor defines the exploration boundary: every idea the grid produces must touch this mechanism.

  • metsigen anchor: Pneumatic-Hydraulic Decoupler (PHD)
  • cooling anchor: Adaptive Nunome Cold Plate (AI accelerator, >10 kW/unit)
  • up to 11 sections per anchor (A–K)
  • each section scores independently — weak sections are stripped

Hunter-Killer Grid

The grid explores each anchor section's mechanism space systematically, producing forge ideas the operator wouldn't have considered independently. 50–200 forge ideas per run, each with a forge code, anchor section binding, and IPS pre-score on creation.

  • forge-* idea records with mechanism text
  • anchor section binding per idea (A–K)
  • IPS pre-score + genome DB registration
  • genome DB: 11,076 ideas across all projects

Sniper: The Rater

Every forge idea passes through a 4-model evaluation panel: three independent DeepSeek calls plus one GLM-4. Each model scores independently across IPS dimensions — novelty, non-obviousness, claim breadth, prior-art clearance, enablement. The panel reaches consensus. Diamond / Gold / Silver.

  • Diamond: IPS ≥ 75 — priority filing
  • Gold: IPS 70–74 — filing-grade
  • Silver: below 70 — recombination pool
  • Bronze: below threshold — archived
Genome DB · 2026-09-01

11,076 ideas registered across all projects and source tiers — Forge (HK grid), SYNTH (hybrids), T3 (gap critic pool), P1 (anchor combo pre-screening), EXT (external injections). Diamond 22 · Gold 64 · Silver 157 · Bronze 10,833. The Silver and Bronze pool is not waste — it is the recombination substrate for the next run.

Phase 3 · First Proof
04

Two Tests. A Rising Ceiling.

The first full end-to-end IP Foundry runs — grounded against 791 real EPO patents, scored under filing-grade weights. Test 1 established the pipeline works. Test 2 introduced cross-day fusion and delivered every filing-grade idea as an attorney-ready patent draft.

Test 1 — Baseline

Single-day fusion

2026-07-29 · first successful full run

Three generation tracks harvested from one day, fused directly, and scored against 791 EPO prior-art patents. Established that the foundry works end-to-end and that idea volume ≠ top quality.

3,457 ideas in88 super-patents27 filing-gradeIPS 79 top
Filing-grade (Diamond + Gold): 27 · IPS range 47–79
Test 2 — Cross-Day Fusion

Cross-day + fully productised

2026-07-29 → 30 · pipeline complete

4,596 candidates across two days distilled into a 377-idea cross-day pool. Fused under filing weights, auto-fault-checked, then turned into lineage-traced attorney-ready patent packages.

4,596 → 377 pool117 super-patents28 filing-gradeIPS 83 top
+32% more output · Filing-grade: 28 · 46% larger Silver pool
55
Total Filing-Grade

Attorney-ready patent drafts across both tests

83
Top IPS Score

Raised 79 → 83 by cross-day fusion in Test 2

+32%
More Output

Test 2 vs Test 1 — more super-patents, deeper Silver pool

791
Prior-Art Screen

Every idea grounded against real EPO patents at scoring time

The Pipeline Product — 7 deliverables per idea

Claims JSON · Claims MD · Technical SVG patent drawings · Commercial go-to-market kit · Prior art search with cited references · Full application draft (markdown) · Application draft (.docx, attorney handoff format). 0 manual steps between idea and completed package.

Phase 4 · IP at Scale
05

Three Domains. One Pipeline.

From the foundry proof, three focused IP projects were built and run — each with its own anchor mechanism, anchor sections, and full forge → E1.5 → SYNTH → Patent pipeline. The same autonomous stack, aimed at three different engineering problems.

metsigen

Pneumatic-Hydraulic Decoupling

PHD — the Pigtail Annular-Weir Cartridge. Separates pneumatic and hydraulic energy paths inside a single actuator body — eliminating the cross-coupling that limits precision in hybrid systems.

158 forge ideas generated
144 survived E1.5 section trim
3 SYNTH batches → 5 merge hybrids
5 attorney-ready patent packages
Stage: Forge → E1.5 → SYNTH → Patent
5
Patent Packages

cooling

AI Accelerator Cooling

Adaptive Nunome Cold Plate — liquid cooling for AI compute units exceeding 10 kW. Two 8-hour autonomous runs over 2 days. One DIAMOND-rated claim combining mechanisms the forge couldn't produce in a single idea.

72 forge ideas generated (11 sections A–K)
66 survived E1.5 trim
3 SYNTH batches → 52 hybrids
41 hybrids in survivor pool (≥7.0 score)
7 attorney-ready patent packages (+ P1 pending)
Stage: Forge → E1.5 → SYNTH → Patent
7+
Patent Packages

umbrella

Multi-Domain IP Foundry

The original IP Foundry runs — 8 physical domains, cross-day fusion across the full candidate pool. Tests 1 & 2 established the filing-grade threshold and delivered the first complete attorney-ready packages.

4,596 candidates harvested (2 days)
377 cross-day distilled pool
205 super-patents forged (Tests 1 + 2)
55 filing-grade packages (Diamond + Gold)
P1 Diamonds pending: combo-ac (IPS 82), 5-a-c (IPS 76)
Stage: Forge → Rater → Patent Branch
55
Patent Packages

The IP Pipeline: E1.5 Trim → SYNTH → Merge → Patent

Every forge idea enters a multi-stage compression that eliminates weak mechanism sections and combines the strongest surviving mechanisms into novel hybrids. The hybrids — not the forge ideas — are what gets filed.

  • E1.5 Trim: scores each anchor section independently — strips weak sections, kills only if all core sections fail
  • SYNTH: DeepSeek thinking model compresses batches into Top10 / Dark Horses / Tally / Synthesis — produces 5–10 hybrid concepts per batch
  • Merge: Unified Top 10 across all batches — cross-ranked by commercial viability
  • Survivor Pool: hybrids scoring ≥7.0 SYNTH score auto-enter the next run's idea pool — the system compounds
  • Patent Branch: every Diamond/Gold hybrid → 7-deliverable attorney-ready package
11,076
Genome DB

All ideas registered across all projects and tiers

22
Diamond Ideas

IPS ≥ 75 across all projects — priority filing candidates

64
Gold Ideas

IPS 70–74 — filing-grade, queued for patent branch

67+
Patent Packages

Attorney-ready drafts across all 3 active domains (55 umbrella + 7 cooling + 5 metsigen)

Want a 30-minute system walkthrough or the technical appendix?

The substrate, the Genome DB, and all three active IP domains are live. Leave your email and we'll respond directly — or arrange a walkthrough at a time that suits you.

✓ Noted. We'll be in touch.
Phase 5 · The Living System
06

19 Pipelines. 31 Documents. 0 Manual Steps.

The IP pipeline is one track of a larger system. Every idea that clears the patent gate also generates a full commercial strategy package — and a 12-stage industrial cascade that maps it from raw resource through to institutional power graphs and 90-day market entry blueprints.

Strategy Layer — 31 documents per qualifying idea

Unified Glossary
20 terms · 3 definitions each (scientific / engineering metric / customer benefit)
shared · project-level
Strategy Foundry
6 docs in parallel — blueprint · TAM/SAM/SOM · competitive matrix · buyer personas · feasibility · assumptions
6 docs / idea
Technical White Paper
7 sections in parallel · ~8,700 words · SAF KB citations · VP Engineering audience
1 doc / idea
Content Marketing Kit
One-pager · FAQ · press kit · 8-article blog series · podcast brief · full blog post #1 (SEO-ready)
6 docs / idea
Commercialization Mill
GTM playbook · sales battlecard · 12-slide pitch deck · 3-year financial model · PRD · data room index
6 docs / idea
Patent Package
Claims JSON/MD · SVG drawings · commercial kit · prior art search · full application draft (.md + .docx)
7 deliverables / idea

The Falls — 12-Stage Industrial Cascade

Every qualified idea is traced from raw resource streams through industries, processes, components, products, and markets — all the way to institutional power graphs, VCP+MCDA rankings, four strategic narrative perspectives, and an adversarially-critiqued 90-Day Blueprint. 17 node types, 18 edge types. Output feeds NEXUS episodic memory for cross-idea pattern matching.

  • S01 Resource · S02 Industry · S03 Process · S04 Product · S05 Market · S05b Dedup
  • S06 Ecosystem · S06b Institutional Power Map · S07 Network · S08 VCP+MCDA
  • S09 Four Strategic Narratives · S10 90-Day Blueprint (adversarial critic pass)
  • Outputs feed NEXUS episodic memory for cross-idea intelligence
19
Autonomous Pipelines

Idea to finished artifact — no human coordination required

31
Docs / Idea

Full strategy layer output per qualifying idea

12
Falls Stages

Resource → Institutional Power → 90-Day Blueprint

0
Manual Steps

Between idea input and finished deliverable package

Phase 6 · The Engine Improves Itself
07

Pieta Runs on Pieta

The same combinatorial topology engine that generates patentable inventions — turned inward. Instead of finding structural isomorphisms between patents, it finds structural isomorphisms between system components and their failure modes. The result: Pieta's own architecture becomes the next anchor.

What Pieta Mirror Is

Pieta Mirror is a git worktree on branch lab/mirror — an isolated copy of the live system where proposed improvements are tested before they touch production. The same engine that hunts patents hunts its own weaknesses.

  • 7,490 ideas generated — about Pieta's own architecture
  • 15 buildable system improvements identified
  • 8 convergent mechanisms — found from multiple independent angles
  • r = +0.017 — patentability and buildability are genuinely orthogonal

Why This Matters

Every AI system has a blind spot: the people who built it cannot see its structural flaws from inside. Pieta solved this by treating its own architecture as the domain and running the full HK grid against it. The improvements it found are the ones that couldn't be seen from inside.

  • improvements found by 7 independent derivations from different atoms
  • each run in Mirror — tested before production deployment
  • the system that filed for IP is now filing improvements against itself
  • compounding: each Mirror run makes the next patent run stronger

The Seven-Origin Finding — strongest convergence

When seven independent derivations from different starting atoms all identify the same structural weakness, that is not random — that is the engine repeatedly finding a real gap from different directions.

7 independent origins
7
Density-normalised thresholds. A single global similarity floor is wrong. Prior-art density varies by region. Replace with a local percentile — directly addresses 889 hard-blocked ideas.
Half-day fix · Highest priority
4 independent origins
4
Fusion falsifiability. Replace the score comparison at the heart of fusion with a real test — ablation, probe-before-fusing, closure surplus, incremental abort.
Replaces the engine's core rule · Half-day build
4 independent origins
4
Frozen reference frames. The pool mutates during a run — a score from spin 5 and spin 500 are measured against different baselines. Freeze the ruler.
Fixes moving-baseline bug · Quarter-day
3 independent origins
3
Shared read-surface. Cross-track exchange through a poll-only common surface — enables coordination without breaking track isolation.
Cross-track coordination without isolation loss
7,490
Self-Analysis Ideas

Generated by Pieta about its own architecture

15
Buildable Improvements

Identified and scoped — with time estimates

8
Convergent Mechanisms

Found from multiple independent angles

7
Strongest Convergence

Seven independent derivations to the same structural fix

A system that can improve itself is a system that compounds. The 15 Mirror improvements apply directly to the next production run — raising IPS ceilings, fixing prior-art density errors, and unlocking the 889 ideas currently hard-blocked by the seven-origin finding. That is what the commercial products below deliver on top of.

08

What It Becomes

Two products. One sells the engine's outputs — packaged intelligence for IP teams. The other runs the engine on your domain and gives you the IP.

Product 01 — Intelligence Platform

A VP IP or CTO subscribes to domain-specific patent intelligence: prior-art landscapes, whitespace maps, filing-grade idea feeds, and competitive freedom-to-operate assessments — all grounded in the atom substrate, not LLM guesswork.

  • $50,000 setup · $25,000/mo ongoing
  • domain-specific substrate built once, maintained continuously
  • weekly filing-grade idea feeds with IPS scores
  • competitive patent landscape updates

Product 02 — IP Foundry (Royalty)

Run the full pipeline on a client's anchor mechanism. Pieta generates the ideas, rates them, runs E1.5 + SYNTH + Patent Branch, and delivers a portfolio of attorney-ready packages. Client pays royalties on licensed IP. Pieta retains 100% of output IP generated from its own substrate.

  • royalty-based — no upfront for foundry runs
  • attorney-ready packages — goes directly to prosecution
  • 31 commercial documents per qualifying idea
  • 100% traceable provenance per claim
Capability Pieta PatSnap Palantir Google Patents AI Pure LLMs
Grounded substrate (real patents)
Autonomous idea generation
Attorney-ready patent drafts
Commercial strategy automation
Self-improving architecture
Commercial Proof

Manual IP Foundry engagement: $300,000 · 18 months for a comparable patent portfolio (law firm + consultancy). Pieta equivalent: $173.88 all-time · under 30 days from anchor definition to first attorney-ready packages. Scope delivered: 67+ packages, 31 commercial documents per qualifying idea.

09

Defensibility

The moat is not the technology — it is the substrate, the provenance, and the compounding. Every new atom run makes the next idea run better. Every new idea run adds to the substrate.

Verified Substrate

29,175 atoms — each traceable to its source patent and its Reality Gate verdict. Competitors start with text. Pieta starts with verified mechanism fragments.

End-to-End Provenance

Every claim in every patent package traces back to the atoms that generated it, and the patent text those atoms came from. Zero black boxes between substrate and output.

Compounding Survivor Pool

Every SYNTH run seeds the next. 41 of 52 cooling hybrids are in the survivor pool — the next run starts with proven mechanisms, not blank ideas.

Patent Protection

PPN00002480 — the substrate construction and the grounding methodology itself are IP. The engine that makes IP is itself IP.

Mirror Self-Improvement

The engine audits its own architecture using the same grounding methodology. Improvements are tested in the Mirror worktree before production — no other IP platform has this.

Genome DB & Track Record

11,076 ideas registered with scoring history. The provenance record is an asset — it proves the system's calibration history, not just its current output.

10

The Ask

The original pre-seed ask was to file 3–5 provisional mechanisms. We built a system that generates, evaluates, compresses, and attorneys-ready-packages at scale. Here is what we have and what we need next.

What We Built

Starting from: "file 3–5 provisional filings." Ending with: a fully autonomous IP generation pipeline, three active domains, 67+ attorney-ready packages, a self-improving mirror, and $173.88 all-time spend.

  • 3 active IP domains · 67+ patent packages
  • 11,076 ideas in the genome registry
  • 19 autonomous pipelines · 31 docs/idea
  • Mirror: 15 system improvements identified
  • $173.88 total cost · 0 external headcount

What's Next

Three near-term milestones that convert the built system into filed IP and first licensing conversations.

  • File P1 Diamonds — 8 high-IPS ideas awaiting patent branch (5 cooling, 2 umbrella, 1 metsigen)
  • First licensing conversation — cooling domain (AI accelerator market, >$12B TAM)
  • Physics validation layer — Q1 2027 — grounding claims against simulation data
  • Domain 4: expand to a 4th anchor mechanism

Why This Steward

I am the only person who has operated every pipeline stage end-to-end. I designed the safety architecture. I filed the patent. There are no co-founders, no equity splits, no team leaks. The IP chain is clean.

  • 25+ peer-reviewed papers · 2 patents filed
  • Constitutional governance layer already built
  • Accredited Financial Advisor — understands commercialisation
  • Choosing the right institutional home — not accepting the first offer
Roadmap — What We're Building Toward

Now: File remaining P1 Diamond patent branches. Run Mirror improvements (density-normalised thresholds — 889 ideas currently hard-blocked by this one fix). Land first licensing conversation in the cooling domain.

Q1 2027: Physics validation layer — atoms grounded against simulation data in addition to patent text. Raises the IPS ceiling and reduces prosecution risk on the strongest claims.

2027: 1,500+ patent packages across 6+ domains. Licensing revenue from cooling and metsigen domains. Substrate reaches full universal coverage across the 7 meta-families.

The ask was 3–5 filings.
We built the machine that files.
Strategic / Institutional Partnership

Request a 30-minute walkthrough — see the engine, the output structure, and the commercial logic behind Pieta. The substrate, the genome DB, and the pipeline are all live.

✓ Request received. We'll be in touch.
Follow the Build

If you want to follow Pieta as it evolves — new domains, Mirror improvements, licensing milestones — leave your email and we'll send major updates only. No noise.

✓ Added. Major updates only.
David A.B. Van der Walt
Founder · Sole Architect · Pieta IP Pipeline
dab.vdwalt@gmail.com