Skip to main content
Tandom
How it works
About
Discuss a sourcing project →
Resources/Guides/How to use Claude or ChatGPT for safer HTS code research

Guide

How to use Claude or ChatGPT for safer HTS code research

A prompt and verification workflow that uses current read-only HTS tools to produce a candidate brief—not a made-up final classification.

Updated August 28, 2026·9 min read·Skip to the prompt →
Share:X

On this page

TL;DRSet the boundaryWhat the tools doThe prompt templateReview the briefCommon pitfallsFAQ

TL;DR

  • Ask the model for a research brief and candidate list, not a final or "broker-grade" classification.
  • Connect an authenticated, read-only MCP catalog so the model can search current HTS rows, verify that proposed codes exist, and retrieve hierarchy and notes.
  • Make the model state missing product facts and unresolved conflicts. Never let it invent composition, use, origin, dimensions, or other facts needed to choose a heading.
  • Have a qualified reviewer apply the legal sequence and approve the code. Run duty and AD/CVD as separate consequence checks.

Set the boundary before you write the prompt

A polished answer can still be wrong. A model may invent a statistical suffix, skip an exclusion, treat a search result as a legal conclusion, or reason from product facts that were never supplied. Tool access reduces some of those failure modes, but it does not eliminate classification judgment.

Tandom's public MCP surface deliberately fails closed to a small read-only catalog. It includes HTS search, exact lookup, hierarchy, notes, duty, PGA, Chapter 99, AD/CVD, and regulatory-data status. It does not expose the private classifier, document extraction, broker overrides, or write actions.

The right deliverable is a traceable research brief: the supplied facts, plausible candidates, governing text retrieved, unresolved questions, and the next human review step.

Use each public tool for what it actually does

ToolUse it toDo not claim
search_hts_codesFind current rows by keywords or prefix.That the first result is the classification.
lookup_hts_codeConfirm a proposed code resolves and inspect its profile.That existence proves product fit.
tandom_hts_hierarchySee the parent and child context around a code.That hierarchy alone resolves exclusions.
tandom_hts_notesRetrieve applicable legal notes for review.That the model interpreted every note correctly.
tandom_duty_calculateModel duty and fee layers for supplied entry facts.That a duty result validates the code.
tandom_adcvd_checkScreen code, product, origin, and parties for exposure.That an HTS match determines legal scope.

Before relying on a time-sensitive result, the model can also call tandom_regulatory_status to report the freshness signals returned by the public data service.

Connect a compatible AI client to read-only trade data.

Tandom exposes an authenticated public MCP endpoint with a fail-closed catalog of read-only tools. Review the live catalog and client setup before use.

See AI and MCP setup →

Prompt the model to produce a reviewable brief

Use this with an MCP-compatible client that has access to Tandom's public tool catalog. Replace every bracketed field. If a fact is unknown, write "unknown" rather than guessing.

You are helping a US importer research possible HTS classifications.
You are not making the final classification.

PRODUCT FACTS
- Article: [plain-English name]
- Function and end use: [facts]
- Materials and composition: [facts or unknown]
- Form, dimensions, capacity, or power source: [facts]
- Imported as: [complete article / part / set / kit / unfinished]
- Country of origin: [ISO-2]
- Entry date: [YYYY-MM-DD]
- Other relevant evidence: [specification links or facts]

RESEARCH STEPS
1. List every missing fact that could change the heading. Do not infer it.
2. Use search_hts_codes to find plausible current rows. Search more than
   one factual phrase when necessary.
3. For each serious candidate, use lookup_hts_code and
   tandom_hts_hierarchy. A successful lookup proves existence only.
4. Use tandom_hts_notes for the relevant code or chapter. Identify the
   notes a human reviewer must interpret; do not claim they are resolved
   when the supplied facts are incomplete.
5. Do not invent CBP rulings, note text, legal citations, or 10-digit codes.
6. Do not label any candidate 'final,' 'approved,' or 'broker-grade.'

OUTPUT
- Supplied facts
- Missing facts
- Candidate codes with exact tool-returned descriptions
- Relevant hierarchy and notes
- Reasons each candidate may fit or fail
- Conflicts and questions for the reviewer
- Recommended next human review step

Only after a reviewer chooses a candidate, offer to run duty and AD/CVD
screening as separate analyses using the supplied origin and entry facts.

Review the brief before anyone relies on it

Confirm every cited code and text

Open the code in the Tandom catalog and the official USITC HTSUS. Confirm that quotations and descriptions came from tool output or the official source, not the model's memory.

Resolve missing facts with the supplier

If two candidates turn on composition, use, dimensions, or how the goods are imported, stop. Ask the supplier or engineering team for evidence. Do not ask the model to choose the "most likely" fact.

Search rulings outside the public Tandom catalog

The public MCP catalog does not include CBP CROSS search. A reviewer should search rulings.cbp.gov for materially similar products and check whether a ruling was modified or revoked.

Keep consequence analysis separate

Duty, PGA, Chapter 99, and AD/CVD results help the team understand exposure and information requirements. They should never be used as circular proof that the proposed code is correct.

Common pitfalls

  • Calling tool access a guarantee. Current data does not prevent the model from misreading the facts or legal sequence.
  • Treating search as classification. Search results are candidates, not decisions.
  • Inventing confidence scores. The public reference tools do not return classification confidence.
  • Assuming CROSS is built in. The public Tandom MCP catalog does not currently expose ruling search.
  • Pasting secrets into chat. Configure the API key in the client's secure connection settings, never in the prompt.
  • Sending confidential documents casually. Follow your organization's approved AI, privacy, and retention policies; redact unnecessary commercial details.

FAQ

Can Claude or ChatGPT give me a final HTS classification?+
A model can help organize facts and research plausible headings, but it should not be the final decision-maker. Even with current tools attached, it can misapply legal notes, misunderstand the product, or choose between plausible headings incorrectly. Have a qualified reviewer approve the code.
Does connecting Tandom MCP turn the model into an HTS classifier?+
No. The public MCP tools are read-only reference and calculation tools. They can search current HTS rows, look up a proposed code, retrieve hierarchy and notes, and check downstream duty and trade-risk signals. They do not expose Tandom's private description-to-code classifier.
What does lookup_hts_code prove?+
It proves that the proposed code resolves in Tandom's current HTS reference data and returns its tariff profile. It does not prove that the code is correct for the product. The product facts, legal notes, GRIs, and relevant rulings still need review.
What product facts should I include in the prompt?+
Include the article, function, end use, material composition, form, relevant dimensions or capacity, whether it is a part or complete article, how it is imported, country of origin, and entry date. Ask the model to identify missing facts rather than fill them in.
Can the prompt check AD/CVD exposure too?+
Yes, as a separate screening step after a candidate code and complete product description are available. The tandom_adcvd_check tool can surface potentially relevant orders, but HTS coverage is advisory and the result is not a legal scope determination.
Share:X

Keep reading

Related guides

How to find the right HTS code for your product

The classification workflow a qualified reviewer follows after the research brief identifies plausible headings and missing facts.

Read guide →

How to review broker HTS classifications

Use current public reference data to check filed codes and route exceptions to human review.

Read guide →

Use Tandom with your AI

Connect a compatible client to Tandom's authenticated, read-only public MCP catalog.

Read guide →

Tandom

Tandom helps US industrial buyers find, evaluate, and develop manufacturers across Asia and Latin America.

Discuss a sourcing project →

Proud to partner with

Microsoft for Startups

NVIDIA

Inception Program

Sourcing

  • How it works
  • What you receive
  • How engagements work
  • Discuss a sourcing project

Free tools

  • Tariff Calculator
  • AD/CVD Lookup
  • AD/CVD Catalog
  • HTS Catalog

Resources

  • Resource Center
  • Trade compliance guides
  • Roadmap

Company

  • About
  • Contact
  • Security
  • Accessibility
  • Public API status
  • Tandom Brasil ↗
For AI agentsllms.txtllms-full.txtConnect free import tools to your AIFree API overviewAPI reference

© 2026 Fintora Technologies Inc., d/b/a Tandom.ai. All rights reserved.

PrivacyTermsCookiesAcceptable Use

Made with ❤️ in São Paulo and San Francisco

Tandom

Tandom helps US industrial buyers find, evaluate, and develop manufacturers across Asia and Latin America.

Discuss a sourcing project →

Proud to partner with

Microsoft for Startups

NVIDIA

Inception Program

Sourcing

  • How it works
  • What you receive
  • How engagements work
  • Discuss a sourcing project

Free tools

  • Tariff Calculator
  • AD/CVD Lookup
  • AD/CVD Catalog
  • HTS Catalog

Resources

  • Resource Center
  • Trade compliance guides
  • Roadmap

Company

  • About
  • Contact
  • Security
  • Accessibility
  • Public API status
  • Tandom Brasil ↗
For AI agentsllms.txtllms-full.txtConnect free import tools to your AIFree API overviewAPI reference

© 2026 Fintora Technologies Inc., d/b/a Tandom.ai. All rights reserved.

PrivacyTermsCookiesAcceptable Use

Made with ❤️ in São Paulo and San Francisco