Sparse

The know-how your company runs on, captured before it walks out the door.

Sparse preserves the decisions only your best people know how to make.

Cited Governed In-boundary

Awaiting query

Type a customs question. Sparse drafts a cited answer for broker review.

Ask a follow-up, inspect a source, or request broker sign-off...

Human signs. AI drafts. Review before filing under licensed-broker supervision.

The risk

The risk isn't losing the documents.
It's losing the judgment that knew what to do with them.

When the one person who held a call in their head moves on, the knowledge leaves with them — but the obligation to act with reasonable care does not. 19 U.S.C. §1484 “reasonable care” outlives the expert who knew how to meet it.

Incoming materials

Email

Source

Critical decisions live across email, docs, and memory.

A thread holds the context, but not the reusable judgment.

Chat

Source

New hires keep asking the same judgment calls.

The answer repeats because the reasoning was never captured.

Ruling memo

Source

Only one person knows why we price this way.

Exceptions and rulings sit with a single license holder.

Spreadsheet

Source

The call that mattered is not one place you can audit.

Signals are visible; the deciding logic is scattered.

DocsChatsRulingsEmails
Sparse

Judgment brief

In-house

Preserve why the firm knew what to do with the documents.

Obligation

19 U.S.C. §1484

Reasonable care outlives the expert who knew how to meet it.

Supervision

19 U.S.C. §1641

Responsible control still needs a licensed human accountable for the call.

Boundary

19 CFR 111

Sparse keeps the judgment in-house instead of sending it to a public LLM.

Control point

Review

Human review remains the control point; Sparse captures the reasoning trail around it.

Shareable. Auditable. Actionable.

The reframe

Don't buy “AI agents.” Buy the judgment — before it leaves.

We capture how your best people decide, cite every answer to a source, gate the risky calls behind a human signature, and compound that knowledge inside your firm alone. The model is one component. The harness that makes it defensible is the product.

Generic chatbot
Public LLM agent
Enterprise search

One governed judgment layer

Cited to your private rulings, gated behind a human signature, compounding inside your boundary. Scoped to customs brokerage — not a generic assistant.

The proof point
single study · directional

Proven on public data — before we ask for a single record of yours.

ATLAS (arXiv 2509.18400) tests models on 10-digit HTS classification — the exact statutory work a senior broker does by judgment. A fine-tuned ~70B beats frontier reasoning, at ~1/5 the cost, self-hostable.

Fully-correct 10-digit HTS classification

ATLAS benchmark · score is percent correct (higher is better)

scale 0–50%
1

Sparse

LLaMA-3.3-70B · fine-tuned

40%
2

GPT-5-Thinking

frontier reasoning

25%
3

Gemini 2.5 Pro

Thinking

13.5%

Scores measure exact 10-digit classification on public benchmark data; results are directional and vary by use case.

Best result

Fully-correct HTS

40%

fine-tuned ~70B

Cost profile

Compared to frontier

~1/5

fraction of cost

Deployment

Control boundary

Self

hostable

Authority

19 CFR 111

Human

reviews + signs

Benchmarks include

10-digit HTSPublic dataFocused taskCost signalCited first draftBroker sign-off

What this proves — and what it doesn’t.

Proves (directionally)

A right-sized, fine-tuned model can beat frontier reasoning on a focused task at a fraction of cost — self-hostable, on public data, demo-able without a customer.

Doesn’t prove

Deployment-grade accuracy. 40% fully-correct = a reviewable, cited first draft on every case and a correct first draft on ~40%. It does not replace the licensed broker, who reviews and signs every entry (19 CFR 111). ATLAS is a single self-built study — cited as directional, not an industry standard.

Lower cost, self-hostable, on public data — single self-built study; directional, not industry-standard.

Where it fits

Search retrieves. A chatbot answers. Neither carries your liability.

A category view, not a brand fight. File search finds documents; a chatbot answers from public data. Only a governed brain cites your private rulings, gates the risky calls, and keeps an audit trail that belongs to your firm.

Where it fits

1. User question

A request comes in.

File search

Included

Covered in this step

Chatbot

Included

Covered in this step

Sparse

Included

Covered in this step

2. Retrieval

Find relevant information.

File search

Included

Covered in this step

Chatbot

Included

Covered in this step

Sparse

Included

Covered in this step

3. Answer generation

Create an answer from sources.

File search

Not included

Stops before this step

Chatbot

Included

Covered in this step

Sparse

Included

Covered in this step

4. Citations

Attach sources and explain the logic.

File search

Not included

Stops before this step

Chatbot

Not included

Stops before this step

Sparse

Included

Covered in this step

5. Policy gate

Check risk, privilege, and rules.

File search

Not included

Stops before this step

Chatbot

Not included

Stops before this step

Sparse

Conditional

Risk checked and gated

6. Human review

Broker reviews and approves.

File search

Not included

Stops before this step

Chatbot

Not included

Stops before this step

Sparse

Conditional

Reviewed and approved

7. Audit trail

Record, store, and replay the decision.

File search

Not included

Stops before this step

Chatbot

Not included

Stops before this step

Sparse

Included

Recorded with full audit trail

IncludedCovered in this stepConditionalRequires policy or human actionNot includedStops before this stepSparse · governed · cited · self-hostable · audit trail
Architecture

Four pillars — the exact requirements of the problem, not a feature list.

The knowledge was never written down because it’s competitive advantage. Governance isn’t overhead — it’s the regulatory requirement. Each pillar maps to a reason the incumbents fail.

System architecture · top to bottom

01

Data layer

Explicit docs + the judgment traces in email, chat, and your systems of record — synthesized into one entity-resolved brain.

02

Governance runtime

focal

Constraints, context management, permissions, approval gates, audit replay. Governance is the entry ticket, not overhead.

03

Provenance layer

Every answer cites which email, which case, which ruling — with an authority weight. An uncited answer is a liability, not a feature.

04

Vertical model

A fine-tuned ~70B beats frontier on focused task families at ~1/50 params, ~1/100 cost — self-hostable, no egress.

05

Human review

A licensed broker reviews and signs every entry before filing. The brain drafts; it does not replace the license (19 CFR 111).

06

Cited output

A cited first draft and a defensible audit record — the only thing that leaves the boundary. Reconstructable end-to-end.

See the thing

A governed, cited brain — made visible.

Real product surface, built on the spec — high-contrast, theme-aware, no images.

Dossier · 2026-06-24 · HTS Classification

Request

Classify: carbon-steel self-tapping screws, zinc-plated, 3.5 mm, boxed 1,000.

Proposed HTS

7318.15.8000
4 of 4 claims agree

Thread-forming (not bolts); zinc-plated finish routes under 7318.15 per NY ruling Nnnnnnn. No ADD/CVD flags on this lane. Boxed-quantity spot-check noted for Brownsville.

Evidence packet · 4 cited sources

“Screws of iron or steel, thread-forming, zinc-plated, not threaded over their full length, are classified under 7318.15…”

view provenance →

Confidence

0.87

Authority

0.91

Risk

Amber 3Low–Med

Senior broker must sign before filing

19 CFR 111.4 · reasonable care · licensed-broker supervision

Request sign-offReturn to drafter

Human signs. AI drafts. Every claim cited to a source you control.

How it works

Your customs records stay inside your boundary. Sparse brings the governed brain to them.

Sparse maps broker inboxes, SOPs, prior entries, and public authority into a permissioned knowledge layer, then returns cited draft work for licensed review.

  1. 1Before: scattered & risky
  2. 2Map, retrieve & verify
  3. 3After: cited & defensible

Before: scattered & risky

Inboxes, SOPs, entries, and rulings are useful — but disconnected, uncited, and off the audit record.

Client documents

invoices, BOMs

Broker SOPs

local playbooks

Team notes

edge-case calls

Broker inbox

classification Qs

CROSS rulings

public authority

+ authority, audit, and access records

After: cited & defensible

A permissioned knowledge layer links every draft to its source trail — inside your boundary, under review, on the audit record.

CROSS rulings

public authority

HTS notes

chapter logic

ABI exports

entry history

Broker SOPs

local playbooks

Graph connects sources
Cited draft+ broker

Proposed lane: 7318.15.8000 for zinc-plated self-tapping screws.

Evidence aligns across public authority, prior entries, and firm notes. Route to a senior broker before filing.

Sources (3)

CROSS rulingauthority
Entry #4471record
Broker emailpolicy

Human signs. AI drafts.

Boundary-first

Designed for read-only access and in-boundary deployment so regulated records stay controlled.

Permission-aware retrieval

Answers follow existing access rules, with source scope visible to reviewers.

Cited draft work

Every claim carries source trail, authority type, and review state for broker inspection.

Human sign-off

Sparse prepares the reasoning packet. Licensed staff review and sign before filing.

Security & continuity

Your data stays inside your boundary. We bring the brain to it.

Governance is the product, not an add-on. The same guarantees scale from a managed SME tier to your own VPC.

Your data stays in your environment

Single-tenant or customer-VPC. Isolation at the data layer, not just app code. Your private correspondence and the senior's inbox never leave your control — no egress to shared infrastructure.

Answers cite sources

Every quantitative or factual answer links back to its source document and passage. No unsourced superlatives. The reader can verify the chain before acting on it.

Permissions follow existing access

Default-deny, role-scoped. The brain can only surface what the requesting user could already see. A departed expert's captured judgment doesn't leak the files they once could open.

Human review remains visible

High-risk actions need a licensed human sign-off, recorded in the audit trail. The brain drafts; it doesn't replace the license (19 CFR 111). Approvals are reconstructable end-to-end.

Compliance posture

What's real, targeted, and by design.

EU AI Act

Governance-by-design positions us ahead of full applicability.

IN FORCE · AUG 2026

GDPR

Tenant isolation, no-egress, customer-held keys, open-format export.

BY DESIGN

SOC 2 Type II

Roadmap; not yet attained. We won't claim it until the report is issued.

TARGET

Sector attestations

Pursued per vertical (e.g. HIPAA for insurance). Never blanket-claimed.

ROADMAP

Data sovereignty

In-country inference option for restricted entries.

BY DESIGN

Status as of 2026-06-24. Target / Roadmap = commitments, not claims.

Methodology

How we avoid the overclaim that kills 95% of pilots.

Pre-revenue by choice.

No customer logos to hide behind. Every trust signal on this page is a benchmark, a statute, an architectural commitment, or a guarantee you can verify — not a borrowed name.

Capped-risk pilotExit rightsData escrowOpen-format exportWe-do-the-ingestion

Founders & team

To be completed with real credentials before this page ships externally. We won't invent it.

Economics

Priced on the outcome, not the headcount.

Value- and outcome-based — aligned to the liability we remove and the senior time we reclaim, not a per-seat search tax. The fine-tuned small model runs at ~1/100 the cost of a frontier call.

Design-partner pilot

~$25–90k/ firm / year

Directional SME pricing — value-anchored to liability avoided and senior-broker hours reclaimed, with a predictable, capped structure for SME budgets.

  • Governed, cited brain on one problem lane
  • We do the ingestion — read-only, inside your boundary
  • Back-test demo on public data, cited, first
  • Cited first draft on every case; senior reviews & signs
  • Outcome metric agreed up front (senior time reclaimed / error rate)
  • Per-firm brain that compounds on your own data
  • No per-seat tax · no 100-seat minimum · no cloud lock-in

Outcome-priced · the equation

Senior hours reclaimed
Review cycles reduced
Liability exposure avoided
Cited drafts produced+
= value to your firmcapped, predictable

The metric is agreed up front — senior time reclaimed / error rate — so price tracks the liability we remove, not seats we bill.

vs per-seat search

Glean ≈ $50–65

/ seat · ~100-seat min · retrieves docs, not a cited judgment.

vs frontier API

~1/100 cost

fine-tuned ~70B · runs where your data lives.

Objections, answered in-page

The questions a compliance reviewer asks first.

The buying signals we expect — answered directly, not buried in a footer.

Reviewer checklist · open any question
your boundary · brain stays in

See it before it leaves

See what your company already knows — before it walks out the door.

A private diagnostic on a read-only boundary: we map the one problem lane your firm can’t afford to lose, and show you the brain that’s currently walking off the floor.

No training on your dataCited outputsHuman-reviewed setupExit rights · open export