Skip to content
DealLens

How it works

Six passes over one deal, in a fixed order, with a hard separation between the parts a computer should do and the parts a model should do. That separation is the whole design.

01

You give it what you have

A listing URL from any marketplace or broker site — or just the listing text if the page blocks scrapers. Then whatever documents exist: P&Ls, tax returns, the lease, a CIM, payroll registers, bank statements, equipment lists, utility or fuel reports, seller disclosures. More documents means a more confident report, but a listing alone still produces a useful one.

02

Every document is read and traced

PDFs, spreadsheets, Word files, CSVs and photographs of statements are all parsed, with page and sheet boundaries preserved. That traceability matters: a figure that cannot be pointed back to a page is marked unsupported, and unsupported figures do not count toward earnings.

03

The arithmetic runs in code, not in a model

Revenue, gross profit, EBITDA, SDE, normalized SDE, add-backs, margins, debt-service coverage, break-even, margin of safety, working capital, every multiple and five valuation methods are computed in a deterministic engine. A language model is never asked to add, divide or amortize — it is given the results and asked what they mean.

04

The listing’s own history is recovered

Archived versions of the same advertisement are pulled from the Internet Archive and parsed with the same extractor as the live page, then diffed field by field. Price cuts, restated cash flow, a rewritten reason for selling and a moved founding year all surface automatically — with the dates.

05

The outside world is investigated

Competitors within 1, 3, 5 and 10 miles with ratings, review counts and hours. Census demographics for the trade area against national benchmarks. Traffic counts and planned development. Corporate registrations, licences, inspections, liens, litigation and property records. Each research brief is independent, so a blocked source degrades one section rather than the report.

06

A model does the judgement — and only the judgement

With the numbers fixed and the research in hand, the model identifies risks, quantifies each in dollars, writes the narrative, and drafts the offer strategy and the questions for the broker. On the Deep tier a second pass audits the finished report against the computed facts for contradictions and unsupported claims.

You choose the model

The default is OpenAI’s flagship at high reasoning effort, which is the most reliable at catching arithmetic that does not reconcile. You can switch to any of the others on any analysis — and because the financial engine is deterministic, the numbers do not change when you do. Only the interpretation does.

ModelProviderContextBest at
OpenAI GPT-5.4 · High reasoningDefaultOpenAI400KDefault. Deepest financial reasoning and the most reliable at catching arithmetic that does not reconcile.
OpenAI GPT-5.2 ProOpenAI400KSlowest and most expensive, and the best at the hardest reconciliation problems.
Claude Opus 5Anthropic200KExcellent at long-document synthesis and writing the narrative sections in a defensible, hedged voice.
Claude Sonnet 5Anthropic200KFast, capable balance for Deal Scan and mid-tier reports.
Gemini Pro · Google Search groundingGoogle1,000KBest outside-research engine — native Google Search grounding returns real, citable sources for entity, licence and lawsuit checks.
Gemini FlashGoogle1,000KHigh-volume grounded search at low cost. Used for the research fan-out.
Kimi K3Moonshot AI256KVery strong long-context reasoning at a fraction of flagship pricing. Good second opinion on the financial reconciliation.
GLM-5Zhipu AI200KZhipu flagship. Competitive structured-extraction quality, very low cost.
Why offer a choice at all?
Different models fail differently. Running the same deal through two of them and comparing the red-flag registers is a genuinely useful second opinion — and it costs one extra credit rather than a second $15,000 engagement. Research uses Gemini with Google Search grounding regardless of your choice, because grounded search returns citable sources rather than plausible-sounding ones.

What the report will never do

  • Invent a record, a case number, a filing ID, a date or a URL. If a search returns nothing, the report says so — an empty result is an honest finding.
  • Let a seller claim drift into being described as a fact. Every assertion is tagged documented, seller claim, or hypothesis.
  • Speculate about a named individual’s motives or integrity. It describes records, not people.
  • Manufacture red flags to look thorough. When something checks out, it says so plainly.
  • Give you legal, tax, accounting or environmental advice. It tells you precisely what to take to the professional who can.

Common questions

How long does an analysis take?

A Deal Scan takes about three to five minutes. A Full Deal Report takes eight to fifteen. Deep Due Diligence takes fifteen to twenty-five, because it runs the public-record and environmental research and then audits its own output.

What if the marketplace blocks the scraper?

Several marketplaces block datacenter traffic. When that happens the report falls back to archived versions of the listing and to text you paste in directly, and it tells you plainly in the limitations section that the live page could not be read.

What file types can I upload?

PDF, Excel, Word, CSV, plain text and images. Scanned documents are read with vision OCR, though a native export is always more reliable.

How It Works · DealLens