> ## Documentation Index
> Fetch the complete documentation index at: https://docs.libratech.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Review basics
> Check a contract against your firm's Playbook — its standard positions and rules — and get a structured, citation-backed answer.
**Review** is the depth tool. Where Discovery pulls the same handful of values out of many documents at once, Review goes deep on the contract in front of you — typically a draft you've received from the counterparty, when you want to know whether it actually fits your standards.
The check runs against a **Playbook**: your firm's framework for a particular contract type, like an employment contract, an NDA, or a service agreement. Libra reads the contract, evaluates it against every Rule in the Playbook, gives each Topic a risk level, and cites the passage it based that on.
## What's in a Playbook
A Playbook is built in three nested layers — Topics at the top, Positions inside each Topic, Rules inside each Position.
| Layer | What it is |
| ------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Topic** | A subject of negotiation. *Working hours*, *Place of work*, *Termination*. A Playbook usually has a handful, one for each clause you actually negotiate. |
| **Position** | Inside a Topic, a Position is a wording you would sign for it. Every Topic starts with a **Starting position** — *"a position you would accept for this clause"* — and a **Not acceptable position**, your red line. Between them you can add as many **Fallback positions** as you need: *"a compromise you would accept if the Starting position was not met."* |
| **Rule** | Inside a Position, a Rule is a specific, testable condition. Every Position needs at least one; together, its Rules define what the Position means. |
A quick example. For the Topic *Working hours* in an employment contract, your Starting position might consist of two Rules:
* *Weekly working time does not exceed 40 hours.*
* *The agreed gross monthly salary compensates for no more than 10 overtime hours per month.*
Together, those two Rules describe what an acceptable working-hours clause looks like for you. Libra checks the contract against the whole framework and tells you, Topic by Topic, where it holds up and where it falls short.
You'll learn how to build one in [Create a Playbook](/en/features/review/templates). Once a Playbook exists, you can run it against any contract of that type, as often as you like.
## Where a Review starts
There are two paths, and they end in the same result.
**From the Review page.** Open **Review** in your project. Your Playbooks sit across the top under three tabs — **My Playbooks**, **Shared** and **Libra** — for the ones you built, the ones your team shared with you, and the ones Libra ships. **New Playbook** starts an empty one and **Browse templates** opens the full library. Pick a Playbook and choose **Run**; the **Select Documents to review** dialog opens, and once you've picked the files, **Start Review** kicks it off. You can select more than one file — the Review returns a single set of Topic verdicts across everything you attached.
**From Chat.** Drop the contract into a chat and ask Libra to *"review this against our standard NDA terms"*, or pick **Tools → Create new → Review** explicitly. Libra offers you the matching Playbooks to choose from, runs the Review, and shows the result inline. See [Reviews from chat](/en/features/review/from-chat).
Either way the finished Review is saved into the project's **Reviews** folder in **Project files**, and the run joins the list below the Playbooks on the Review page with its status, document count and Topic count.
## What you get back
A Review result is structured, not narrative. Topics are numbered `01`, `02`, `03` and laid out one after another, each with a risk badge and a **Reasoning** paragraph. The Positions underneath start collapsed; open one to see its Rules.
| Element | What it tells you |
| -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Topic risk badge** | **No risk**, **Medium risk** or **High risk** for the Topic as a whole — plus **Not found** when the documents contain nothing judgeable on it. |
| **Reasoning** | A short paragraph, on the Topic and again on each Rule, explaining the verdict in Libra's own words. |
| **Position match** | For each Position, how its rules came out: a **Met** count over the rules Libra could judge, and a separate **Not applicable** tally — *"2/3 Met · 1 Not applicable"*. The count is literal and never flips by position type: on a **Not acceptable position**, *"2/2 Met"* means both forbidden clauses were found in the contract, and a clean contract reads *"0/2 Met"*. |
| **Rule outcome** | On a **Starting position** or **Fallback position**, **Met** or **Not met**. On a **Not acceptable position** the same judgement reads **Detected** or **Not detected** — the wording you forbade is either in the contract or it isn't. **Not applicable** and **Pending** can appear on any position type. |
| **Citations** | Small pills inline in the reasoning, labelled with their source. Hover one to see the cited passage, then **View in document**; click it to open the document viewer at that page with the passage highlighted. |
Once the Review has finished, **Export** in the result header writes the whole thing out as a Word document.
See [Understanding Review results](/en/features/review/results) for how to interpret each part.
## When to use Review
The fastest way to spot where a redline has drifted from your standard positions.
Run a Review to see at a glance which Topics need a redline, and where the deviations actually sit.
Every contract is measured against the same Topics and Rules, so you can triage a stack the same way and see which ones need a partner's attention.
**Auto mode** swaps a Topic's rules for a question — *"is this clause enforceable under prevailing case law?"* — and answers it from your research sources.
## Review vs. Discovery
Both extract structured information from documents, but they answer different questions.
| | Review | Discovery |
| ------------- | ------------------------------------------------------------------------- | ------------------------------------------------ |
| **Focus** | Does this contract meet our standards? | What are the values across many contracts? |
| **Documents** | One contract — several files if you attach them — judged as a single set. | Many documents, each judged on its own. |
| **Output** | Per-Topic risk, rule-level reasoning, citations. | A table, one row per document. |
| **Best for** | Negotiation, redlining, compliance checks. | Comparison, data extraction, portfolio analysis. |
When in doubt: if the question is *"is this one contract OK?"*, run a Review. If the question is *"how do these many contracts compare?"*, run a Discovery.
## Tips for getting good Reviews
A Playbook with a couple of well-defined Topics gives you cleaner output than a sprawling one that tries to cover everything. Add Topics once you trust the basics.
*"Weekly working time does not exceed 40 hours"* is a rule. *"Working time should be reasonable"* is not. Specific, testable, unambiguous.
On a Starting or Fallback position, **Add ideal language** attaches the wording you would actually accept, and the Word add-in uses it when it redrafts a flagged clause. Not acceptable positions don't take one — there is no ideal version of a clause you never want to see.
Red is the signal, whatever word it carries: **Not met** on a Starting or Fallback position, **Detected** on a Not acceptable one. Click through to the cited passage and confirm Libra read the contract the way you would before you act on it.
## Next steps
Topics → Positions → Rules → ideal language.
Skip the rule-building and ask a research-backed question instead.
What the risk badges, Met counts, and citations actually mean.
Run one without leaving the conversation, and keep the result as context.