How Resubly Reads a Contract with AI

The Short Version

You drop a contract PDF into Resubly. An AI model reads it and pulls out the fields that matter for a renewal: the vendor, the total cost, the start date, the renewal date, the notice period, and the payment terms. Every field it returns carries a confidence score. Nothing enters your live renewal list until you look at what it found and confirm it. That review step is not optional and it is not a nag. It is the design.

This post is the honest walkthrough of how that works, including where it is strong, where it is weak, and what happens when it gets something wrong. If you handle contracts for a finance or ops team, you should know exactly what a tool does with them before you upload the first one.

Step One: You Upload, We Extract

When a PDF lands in the drop zone, Resubly sends the document to a large language model (currently Google Gemini) with a strict instruction: return only the renewal-relevant fields, as structured data, and say how confident you are about each one. The model does not get to freewheel. It fills a fixed shape or it fails, and a failed structured response falls back to a plain pattern-matching pass rather than guessing.

The fields it targets are the ones a renewal decision actually turns on: vendor name, total contract value, currency, start date, renewal date, notice-period days, and the vendor domain. Not the whole contract. Resubly is not trying to be a legal review tool. It is trying to answer one question: when does this renew, and by when do you have to act.

Step Two: Every Field Gets a Confidence Score

This is the part most extraction tools hide. Resubly attaches a per-field confidence score to each value the model returns. A renewal date lifted verbatim from a clearly labelled clause scores high. A total cost inferred from a table with merged cells and three currency symbols scores low, and it is meant to.

Those scores are not decoration. They drive what happens next. High-confidence fields are pre-filled and ready to accept. Low-confidence fields are flagged so your eye goes straight to the values most likely to be wrong, instead of you re-reading the entire contract to check work you did not do.

Step Three: Nothing Is Trusted Until You Confirm

An extracted contract does not appear in your renewal list. It appears in a review state. You see the document alongside the fields the AI pulled, with the low-confidence ones marked. You correct anything wrong, fill anything missing, and confirm. Only then does it become a tracked subscription with a real renewal date and a real notice deadline.

This matters because the cost of a silent extraction error in this domain is not a typo. It is a renewal date that is thirty days off, which means a notice window that closes before you knew it opened. A tool that auto-imports contracts and trusts its own output is optimising for a demo, not for the one job that has to be right. Resubly would rather cost you two minutes of review than let a wrong date sit unexamined until the invoice arrives.

What It Is Good At, and What It Is Not

AI extraction is genuinely strong on clean, text-based contracts with labelled terms. It reads a renewal clause faster and more consistently than a human skimming at the end of the day. It does not get bored on the fortieth contract.

It is weaker on scanned documents, unusual layouts, contracts where the renewal terms live in an addendum, and anything where the commercial reality contradicts the plain text. That is precisely why the confidence score and the human confirmation exist. The model is a fast first pass, not a final authority. You are the final authority, and the tool is built to keep it that way.

What Happens to Your Document

The document is sent to the AI model for extraction and the field values come back. Your contract content is not used to train any AI model. The uploaded file is stored against your organisation and the subscription it belongs to, and it is deleted when you delete the contract or close your account. The security page lists every provider that touches your data and the full retention and deletion lifecycle.

Why We Built It This Way

The whole point of Resubly is to turn renewals from surprises into decisions. An extraction pipeline that quietly guesses would reintroduce exactly the surprise we are trying to remove. So the design rule is simple: the AI does the reading, the score tells you where to look, and a person signs off before a date can ever trigger an alert. Fast where it can be, careful where it must be.

If you want to see the wider system the extraction feeds into, read Inside the Renewal Machine, or start dropping in your own contracts and watch the review step do its job.

Sources: Resubly product architecture (contract ingestion pipeline, per-field confidence scoring, and review-before-commit flow), 2026.