Pre-submission document verification.
Your bid package is checked against everything the notice actually requires — mandatory documents, names, prices and each stated requirement — with every finding grounded in the source text. How it verifies, how accurate it is, and what it costs: all on this page.
First verification free · 1 credit ₩290,000 = up to 3 runs of one notice until it closes · Buy credits →
Requirement extraction
Requirements are pulled from the tender package — tables included — into a structured, reviewable checklist.
Compliance check
Your bid is matched against each requirement. Gaps and deviations surface before submission — not after a rejection.
Mandatory-document check
The required-documents list is extracted from the notice and checked against your package — a missing form surfaces before it disqualifies you.
Cross-document consistency
Company name, representative, and dates are compared across every document in the package — a stale year or a mismatched name gets flagged.
Price consistency
Line items are summed against totals and checked against the stated budget — arithmetic slips and budget overruns are caught before submission.
Grounded, machine-certain findings
Each finding is backed by quotes from the source text. Only high-certainty results are marked certain; the uncertain are set aside for a person to review.
The LLM proposes. A deterministic layer decides.
Miriboa never lets a language model have the last word. Extraction and judgment are proposed by AI, then confirmed by a deterministic layer that scores certainty and grounds every finding in the source.
- 01
Parse
HWP/HWPX, PDF, DOCX and XLSX packages are parsed and normalized — tables preserved, not dropped, including the requirements most parsers lose inside HWP tables.
- 02
Extract requirements
The AI proposes the requirement set; a critic pass filters it into a structured golden checklist.
- 03
Judge compliance
Each requirement is checked against the bid and graded — machine-certain, or needs-review.
- 04
Report
A pre-submission report lists met, missing, and deviating requirements, each grounded in the source.
Measured in July 2026 on an internal golden set of 173 requirement items. The tender notices are real and published; the bid packages are synthetic, written for the benchmark. These figures describe benchmark performance and are not a guarantee of results on your own documents.
- 92.5%
- requirement-extraction recall — how completely requirements are found (full golden set, 173 items)
- 96.5%
- machine-certain precision — how often findings marked "certain" were right
- 18 / 19
- defects caught in the adversarial judgment benchmark
Miriboa is a vendor-operated verification service — send the notice number and your bid package, and the report comes back. Nothing to install, nothing to integrate. Request verification →
Reading a notice is not the same as proving your package meets it — the paid verification cross-checks every document, price and name, reviewed by a person on your deadline, to produce that proof.The reading half, before that, is free — our Claude connector reads notice documents with tables intact →
Miriboa checks documents against a notice’s stated requirements. It is not legal advice, not a legal determination of eligibility, and not a guarantee of winning or passing evaluation — final responsibility for your submission is yours.
How is this different from other bid-support services?
Alert feeds, award histories and bid-price analytics help you choose tenders and set a price. Miriboa covers the one step after those — checking, before submission, that your finished package meets the notice’s requirements. It works alongside those tools, not instead of them.
How is this different from pasting the notice into a chat AI?
Chat is useful for a draft-level look. But a chat answers differently every run, easily misses requirements inside HWP tables, and can assert things without evidence. Miriboa returns the same verdict for the same documents, quotes the source for every finding, and never asserts what it cannot confirm.
What files do I send?
Your bid package as HWP/HWPX, PDF, DOCX or XLSX — tables are preserved, including inside HWP. For the notice, the 나라장터 notice number is enough; we fetch the package ourselves.
How long does a verification take?
Each run is returned within one business day of receiving the package. If we miss that, the credit is restored.
How is my bid package protected?
An NDA takes effect the moment you submit a request — documents are used only to perform the verification, access is limited to the person performing it, and files are purged within 15 days (immediately on request). See Security & Confidentiality in the footer for the full policy.
What does it catch — and what does it not do?
It checks required-document completeness, name/date consistency across files, price arithmetic against the budget, and each requirement in the notice, all with verbatim evidence. It is not legal advice, not an eligibility ruling, and not a guarantee of winning.
How do credits work?
Your first verification is free (sign-up credit). One credit (₩290,000, VAT incl.) covers one notice with up to three runs until its deadline — fix, re-verify, submit verified.
Why three runs per notice?
Because the point is the fix cycle: first run finds the gaps, you patch the package, the re-run confirms it — so the version you actually submit is the verified one.
Check your federal proposal against the solicitation — before you submit.
Miriboa reads the full solicitation package (attachments included), extracts every requirement, and checks your draft proposal against each one. Deviations, omissions, and weak commitments come back as findings — each with verbatim quotes from both documents.
Regarding solicitation:
The LLM proposes. A deterministic layer decides.
Verbatim evidence, never paraphrase
Every finding cites exact quotes from the solicitation and from your proposal, and each quote is mechanically re-checked against the source text. A finding that cannot be matched to the source is never asserted — it goes to a person for review instead.
Same input, same verdict
Each judgment is run several times and has to agree with itself, then passes through fixed rules — so the same documents produce the same findings on every run, unlike a conversation with a language model.
Catches what generative reviewers miss
The rule-based layer catches the mistakes LLM reviewers miss most often: numbers that do not match, missing required documents, and contradictions between documents inside the solicitation package itself.
The measurement method, failure cases and limits are published — figures are from the Korean golden set; a formal English golden set is in preparation. See the benchmark →
The steps before verification support SAM.gov too.
- SAM.gov notice search — find current solicitations by keyword (Korean or English). Search notices →
- Free weekly alerts — matching new notices every Monday. Fill in your company profile (entity type) and each notice gets a free eligibility verdict. Start alerts →
Sample report — a real SAM.gov solicitation
A real, publicly posted federal solicitation, verified against a synthetic proposal with planted defects: a period-of-performance deviation, spec deviations, and a missing required document. Every one is caught and quoted.
Concierge verification — available now
Send the solicitation number (or SAM.gov link) together with your draft proposal package, and you get the full findings report back — typically within one business day. Your documents are handled confidentially and purged after delivery.
Regarding solicitation:
Talk to the conciergeSelf-serve wizard (Korean, first run free)or write to hello@sizlon.io
Self-serve submission is live via the wizard (Korean interface, KRW billing) — first verification free with a sign-up credit; after that one credit is ₩290,000 and covers up to 3 runs of the same solicitation until it closes (VAT included). API access is in preparation.
Miriboa is a pre-submission self-check aid. It is not legal advice and does not guarantee evaluation outcomes.