# EximAgent — full text

> EximAgent is an AI company organizing trade data and knowledge for AI agents. From one command line: find importers, classify HS codes, check tariffs, screen sanctions, enrich companies, and draft outreach — every result with a clear confidence label.

Last updated: 2026-08-13

## Operate EximAgent as an AI agent

EximAgent is a trade-intelligence CLI built for AI agents and the teams behind them — buyer and importer discovery, HS-code classification, tariff and sanctions lookups, company and contact enrichment, and staged outreach.

- Load the skill: `Read https://cli.eximagent.ai/skill and follow the instructions to use the eximagent CLI for international-trade intelligence.`
- Install (macOS / Linux): `curl -fsSL https://cli.eximagent.ai/install | sh`
- Install (Windows): `iwr https://cli.eximagent.ai/install -useb | iex`
- Authenticate: `eximagent login` (OAuth device flow) or `eximagent login --token <PAT>`; verify with `eximagent whoami`.
- Always-current command reference + usage doctrine: https://cli.eximagent.ai/skill
- CLI repository & issues: https://github.com/EximAgent/cli

Every command is `eximagent <category> [<subcategory>] <verb> [--flags ...]`. Args are camelCase (`hsCode`). Billable or irreversible steps preview first with `--dry-run`; lists of many entities use the `--inputs <file>` bulk shape instead of looping.

## What EximAgent does

- **Buyer & importer discovery** — `search run` (preview → confirm → stream), `search refine`, `collection ...`, `collection analyze`
- **HS codes & tariffs** — `hscode search`, `tariff`, `trade lookup`, `duty exposure`, `duty fta`, `landed cost`
- **Sanctions screening** — `sanctions check` (OFAC SDN — advisory; final clearance stays with you)
- **Customs shipment records** — `shipments search`, `company|product|route|price shipments`, `shipments market-signals|buyer-recurrence|price-trend|route-signals`, `evidence show`
- **Full-corpus analytics** — `analytics catalog|query|sql`, `market trend|momentum|growth|entrants|churned`, `companies profile|suppliers|customers|competitors`, `prospects find`
- **Company & contact enrichment** — `enrich company`, `enrich contacts`, `company verify|resolve|split`, `linkedin lookup`, `profile-match score|rank|lookalike`
- **Outreach** — `email draft --dry-run` → `email send --confirm`, `sequence ...`, `template ...`, `reply ...`, `suppression ...`
- **Saved state & automation** — `profile`, `corridor`, `collection`, `products`, `ideal-profile`, `kb`, `monitor`, `reminder`, `watch`

## Confidence model

Every company and contact field comes back as `{value, source, confidence}`:

- **verified** — provider-confirmed — treat as fact.
- **extracted** — pulled from a website crawl — candidate data, not a fact.
- **heuristic** — derived from secondary signals — a suggestion.
- **inferred** — a model's best guess from context — a hypothesis.

## Data sources & coverage

Importer/exporter discovery data, WTO and national tariff schedules, the OFAC SDN sanctions list, per-shipment customs and bill-of-lading records, live company-website crawls, and people-search + LinkedIn for contacts. Every row carries the source it came from, and shipment queries report a coverage envelope (complete / partial / unavailable) so a result is never overstated.

## How it works

EximAgent reads from established trade sources, combines them with live company crawls, and returns one structured row per result — each stamped with where it came from.

- **Read authoritative trade data** — Customs and bill-of-lading shipment records, tariff and trade-remedy databases, the HS taxonomy, and the OFAC SDN list.
- **Combine with live signals** — Website crawls, people-search contact verification, LinkedIn, and web search fill in companies, contacts, and current context.
- **Tag every row** — Each result carries its source and a confidence label, and shipment queries include a coverage note — so you can judge any number before acting.

### Where the data comes from

- **Customs & bill-of-lading records** — Per-shipment records of who shipped what, where, when, and at what value; every query reports its coverage.
- **Tariff, duty & HS databases** — Official duty rates, taxes, NTMs, trade remedies, FTA utilization, and the HS code taxonomy.
- **OFAC SDN list** — The published U.S. sanctions list, used to screen companies before you engage.
- **Company website crawls** — Public company sites read live to build profiles, find contacts, and enrich rows.
- **Contact verification & LinkedIn** — People-search email verification and LinkedIn company pages confirm and enrich decision-maker contacts.
- **Web search** — Resolves raw company names to their canonical website and domain.

## Known limits & staying current

Trade data is never perfectly complete or evergreen. Here is what to keep in mind, and how we keep results trustworthy.

### Shipment data comes with a coverage envelope

Every customs query reports whether the data is covered, partial, limited, or unavailable for that country and period. Read it before drawing conclusions — 'unavailable' means there is no usable data, not an absence of trade.

### Contact data is candidate until verified

Enrichment can return few or zero verified contacts even for real companies. Extracted, heuristic, and inferred fields are candidates to review, not guarantees — always respect the confidence tag.

### Outreach stays behind your confirmation

Drafts and sequences preview first and never send without explicit confirmation. Sanctions screening is an advisory first pass; final clearance stays with you and your legal team.

### Trade-domain by design

EximAgent is built for international-trade work — discovery, tariffs, sanctions, shipments, enrichment, and outreach. It isn't a general-purpose tool, and it grounds answers in sources rather than model guesses alone.

## Contact & support

- **Support & general** — Help with the CLI or web app, billing questions, partnership ideas, or anything else — email [support@eximagent.ai](mailto:support@eximagent.ai).
- **Data requests** — Represent a company in our index? Email us to have your business contact details reviewed, corrected, or removed. See our [Privacy Policy](https://eximagent.ai/policies/privacy) for how we treat business data.

## Frequently asked questions

### What is EximAgent?

EximAgent is a trade-intelligence CLI built for AI agents and the teams behind them. From a single command line it runs buyer and importer discovery, HS-code classification, tariff and NTM lookups, OFAC sanctions screening, company and contact enrichment, and staged outreach. Every row it returns carries a source and a confidence label, so an agent can act on verified data and flag anything that still needs a human eye. A sourcing team might use it to find importers for a product, confirm the right HS code and duty rate, and screen each company before reaching out. You can run it from the command line, drive the same capabilities from the web app, or hand it to an AI assistant as a skill so the assistant operates EximAgent on your behalf — the data and confidence labels read the same whichever way you reach them.

### How much faster and cheaper is this than researching leads manually?

In our internal benchmark, a trusted lead costs $1.45 and takes about 22 seconds with EximAgent, versus $5.50 and 70 seconds for the same AI agents working alone, and $5.12 against a modeled manual baseline (12 minutes). The quality gap is wider than the speed gap: 96% of EximAgent-assisted leads passed the trust check, versus 56% for independent agents. The setup was deliberately hard on us — 180 standard companies, three repeated runs, and the companies' websites hidden from the agents, so the numbers measure the indexed data layer rather than an agent's ability to browse. Behind those results sit 276 million-plus shipment records from official customs sources and 578,000-plus identified importers, with 82% of enriched companies yielding a verified contact. Corpus depth varies by trade lane, and every query reports its own coverage envelope.

### What does EximAgent cost?

Installing the CLI and creating an account are free, and the Free plan comes with 100 credits a month — enough to run a real week of prospecting before you commit to anything. Paid plans start at $50 a month; a higher plan raises your monthly credit allowance and unlocks the higher-yield skills, but the credit rate itself never changes between plans, so upgrading buys you more room rather than a better unit price. When a month runs hot, top-up packs add credits from about $0.12 each instead of forcing you onto a bigger plan. Sanctions screening, tariff lookups, and monitoring are free on every plan and are never metered, and read-only HS-code lookups on the hub need no install or account at all. Prices are quoted in USD, with VND billing available. As a reference point for scale, our published benchmark measured about $1.45 per trusted lead end to end.

### Which trade-data sources sit behind the CLI?

It draws on importer and exporter discovery data, WTO and national tariff schedules, the OFAC SDN sanctions list, and live crawls of company websites. Tariff and HS lookups come from official schedules, sanctions checks run against the published SDN data, and buyer discovery and enrichment combine trade records with what the CLI reads from a company's own site. It also reads per-shipment customs and bill-of-lading records, and resolves and verifies decision-maker contacts through people-search and LinkedIn, with web search mapping a raw company name to its canonical site. Every result includes the source it came from, and shipment queries report their own coverage — so your team can trace any row back to where the data originated, see where the data is complete, partial, or unavailable, and decide how far to trust it.

### How does EximAgent handle confidence on contact data?

Every contact field comes back as a value paired with its source and a confidence label. Data confirmed by a provider is marked verified; anything the CLI extracted from a website or inferred from other signals is returned as a candidate, not a fact. The labels form a single ladder — verified for provider-confirmed facts, extracted for fields pulled from a website crawl, heuristic for values derived from secondary signals, and inferred for a model's best guess from context — so the gap between a confirmed fact and a hypothesis is always explicit. That separation lets an agent use verified addresses straight away while holding candidates back for a quick human check, so outreach never goes out on a guess. The same value-source-confidence shape is used across enrichment, so confidence reads the same wherever data appears.

### Can I run it across hundreds of companies?

Yes. Bulk commands take a list of companies and process them in one run, streaming structured results back as each one resolves instead of forcing one tool call per company. An agent can hand over hundreds of rows, keep working, and read results as they arrive, with each row tagged by company so nothing gets mixed up. When a name is ambiguous, auto-pick resolves the best match, so large lists run without a human disambiguating every entry. Because results stream back tagged by company, you can pipe a bulk discovery straight into enrichment and then staged outreach without re-keying the list, and the run's collections and history stay saved to your account for later sessions. Billable steps still preview before they commit, so you can confirm the scope and cost of a few-hundred-row job before it runs.

### How does outreach stay safe to send?

Outreach always starts with a dry-run preview that shows exactly what would be sent and to whom. Nothing leaves until you explicitly confirm, and a countdown gives you a final window to cancel before the first message goes out. Once sending begins, replies are tracked per company and the outreach stage is recorded, so an agent can follow up based on where each conversation actually stands rather than re-sending blindly. Sanctions screening runs as an advisory first pass, so you can flag a counterparty before you ever draft a message, while final clearance stays with you and your legal team. Message templates, notes, and per-company stage are kept with each contact, so a sequence picks up exactly where the last touch left off. Opt-outs are honored automatically through a suppression list, so once someone unsubscribes they stay excluded from every later send without you tracking it by hand.

### Is the data private to my account?

Your collections, saved trade routes, message templates, notes, and per-company history are tied to your authenticated account, not written into your local project files. That keeps prospect lists and negotiation history out of your repo and available across your own sessions instead of leaking into version control. Sign-in is handled through the CLI's own login, so the data stays scoped to you and travels with your account rather than the machine you happen to be on. Because the workspace lives behind your login rather than in the working directory, you can move between machines or hand a task to an agent without copying state around, and nothing you save is shared into another user's account. Sign-in runs through an OAuth device flow rather than a stored password, and the access tokens it issues can be revoked at any time, so account access stays under your control.

### Why doesn't pasting the skill into claude.ai, Gemini, or ChatGPT work?

Because those are web chats, not agents with access to your machine. The skill file at cli.eximagent.ai/skill is a set of instructions that teaches an AI agent how to run eximagent commands — so the assistant reading it must be able to execute commands in a terminal on your computer. Coding agents like Claude Code, Cursor, Windsurf, and Codex CLI can do exactly that: paste the one-line prompt, and the agent reads the skill, installs the CLI if needed, and drives it for you. A chat website can at best read the file and summarize it — it has no terminal, so nothing runs. If you are in a web chat, the recommended path is the CLI: install it with the one-line command at the top of the page and type commands directly, or hand the skill to a coding agent. The web app at chat.eximagent.ai remains available if you prefer not to install anything.

## Product & ecosystem

- [EximAgent](https://eximagent.ai): what it does, capabilities, and setup.
- [About](https://eximagent.ai/about): how it works, data sources, confidence model, and known limits.
- [Methodology](https://eximagent.ai/methodology): how the benchmark was run — model-split results and downloadable data.
- [Pricing](https://eximagent.ai/pricing): plans, included credits, add-ons, and top-up rates.
- [Contact](https://eximagent.ai/contact): support, data requests, and booking a call.
- [Documentation](https://eximagent.ai/docs): install, authenticate, and operate the CLI — guides, command reference, and the MCP integration (index at https://eximagent.ai/docs/llms.txt, full text at https://eximagent.ai/docs/llms-full.txt).
- [Open Web App](https://chat.eximagent.ai): the same capabilities in a web UI — requires a free account sign-in.
- [EximAgent Blog](https://eximagent.ai/blog): trade insights, guides, and HS-code explainers (index at https://eximagent.ai/blog/llms.txt, full text at https://eximagent.ai/blog/llms-full.txt).
- [HS Codes reference](https://eximagent.ai/hscode): HS-code lookups, tariffs, and trade docs (index at https://eximagent.ai/hscode/llms.txt, full text at https://eximagent.ai/hscode/llms-full.txt).
- [Company directory](https://eximagent.ai/companies): importer profiles from customs records — shipment activity, top HS codes, and trade partners (index at https://eximagent.ai/companies/llms.txt).

## Languages

This site is also available in Vietnamese (Tiếng Việt):

- [Trang chủ](https://eximagent.ai/vi)
- [Giới thiệu](https://eximagent.ai/vi/about)
- [Phương pháp đo](https://eximagent.ai/vi/methodology)
- [Bảng giá](https://eximagent.ai/vi/pricing)
- [Liên hệ](https://eximagent.ai/vi/contact)

## Legal

- [Privacy Policy](https://eximagent.ai/policies/privacy)
- [Terms of Service](https://eximagent.ai/policies/terms)