Skip to main content
For AI agents: a documentation index is available at https://docs.coverbase.com/llms.txt. This page is also available in markdown by appending .md to the URL.
This guide is part of the User Guides collection. It pairs with the Contract Guardian guide, which covers clause sets and clause reviews. Insights are the field-level half of contract intelligence; clause review is the language-level half. The types an insight can apply to are set on Document types.
A document insight is a field you want pulled out of every document of a given type. You define it once (a name, a description, a type, and a mode), and from then on Coverbase populates it automatically whenever a matching document is processed, with a page citation and a verbatim source quote attached to the value. Insights are not limited to contracts. Any document type can carry them: an insurance certificate’s coverage limit, a SOC 2’s audit period, a DPA’s subprocessor notification window. Contracts are where most teams start, because the same fifteen questions get asked of every agreement.
The most common setup mistake is writing insights as if the AI can see your intent. It cannot. It sees the insight name, your description, the type, and the mode. Everything in this guide comes back to making those four things carry the meaning.

What you get for each insight

Every extracted value arrives with:

The value

Stored in its declared type: text, a parsed number, an ISO date, or a boolean. Dates normalize to YYYY-MM-DD; numbers strip currency symbols and separators.

A verbatim source quote

The exact span from the document that supports the value. Coverbase checks that the quote appears in the document. An answer whose quote cannot be located is kept, marked Supporting evidence not verified at low confidence, and waits for a reviewer to Accept answer.

A page citation

The 1-indexed page where the quote lives. If the model cites the printed page label instead of the physical page, Coverbase corrects it to the page the quote was found on.

A confidence and a rationale

High when the document states it explicitly, medium when it had to be inferred, low when the model was unsure. Plus short notes on any ambiguity or assumption.
When a document does not contain the answer, the insight comes back empty rather than guessed. An empty insight is a finding rather than a failure, and it usually means the clause is missing from the vendor’s paper.

Where insights show up

On the document itself

Open any document and switch to the Insights tab. This is the full view: every insight configured for that document type, with values, confidence, source quotes, and page links. From here you can accept an unverified answer, re-extract, export the whole set to CSV, or Add insight: define one, preview what it extracts from this document, and save it for every document of this type.
The Extracted insights card on a contract’s Documents tab rolls up insights across every linked document, grouped by field. Insights with no extracted value are hidden here to cut noise. Open the individual document to see the blanks.
Extracted insights are fed to the model that writes the contract summary and populates the contract risk profile. Better insights produce a better summary, so the two improve together.
Export CSV on the document Insights tab produces one row per insight with the value, all four typed columns, confidence, source quote, page number, reasoning, and whether the value was AI-extracted or entered manually.

When extraction runs

  1. Automatically, on upload. When a new document finishes processing, Coverbase extracts every enabled insight whose document types match that document.
  2. On demand, per document. Open a document’s Insights tab and choose Refresh all. Use this after you add or reword an insight, since existing documents were processed against the old definition.
  3. On demand, per insight. Re-extract a single insight from the row’s actions after you tighten its description.
  4. In bulk, across history. A new insight starts empty on every document you already hold. Configuration → Document Insights → Document types shows exactly how many, and a backfill re-extracts them. See Backfilling history.
Adding a new insight does not fill your existing documents on its own. Until you run a backfill, the field only populates on documents processed after the change. When you edit an existing insight, you choose which documents to re-run as you save: see Applying a change.

Creating an insight

Go to Configuration → Document Insights. You need the org-settings update permission to reach this page.
1

Create a group first (optional but recommended)

A group is a folder that shares document-type scope with everything inside it. Set Data protection to apply to DPAs and MSAs once, and every insight you drag into it inherits that scope. Without groups you set document types on every insight by hand and they drift apart.
2

Add the insight and name it for a human

Name is what reviewers see in the UI and in exports. Use the term your team uses: Liability cap, Governing law, Termination notice period. The name is also the first thing the AI reads, so a vague name costs you accuracy.
3

Write the description

This is the instruction. See Writing descriptions that work below. It matters more than every other setting.
4

Pick the type

Text, Number, Date, or Yes/No. The type controls how the value is stored, validated, sorted, and displayed. Choosing Number for a monetary field also offers the Currency (USD) display format.
5

Pick the mode

Extract or Synthesize. Synthesize is only available for a Text insight; choosing any other type switches the mode back to Extract. The next section covers this choice.
6

Scope it to document types

Choose the document types this insight applies to, or inherit them from the group. Leaving the list empty applies the insight to every document type, which is rarely what you want: it means Coverbase will hunt for a liability cap inside a SOC 2 report.
7

Try it on a real document before you roll it out

Open a representative document, go to its Insights tab and choose Add insight. Define the insight there and run the preview: it extracts from that one document and shows the value, the quote, the page and the confidence before anything is saved. Iterate on the description until it holds up, then save it, which scopes it to that document’s type.That is cheaper than discovering an ambiguous description after backfilling three thousand documents.

Extract vs Synthesize

This is the setting people get wrong most often.

Extract: a single, typed answer

The model returns one concise answer in the insight’s type: a name, a date, a number, or Yes/No. It prefers the document’s own wording, and interprets or normalizes only as far as the type needs, so a Yes/No insight reads the clause and answers Yes or No. It must cite a verbatim quote from the document, and Coverbase checks that quote. If the document does not answer, the insight comes back empty.

Synthesize: a written summary

The model writes a short answer in its own words that combines or explains what the document says: rolling up several clauses, or turning legalese into a plain verdict. It still has to cite a verbatim quote from the document. Because the answer is prose, Synthesize is only available for Text insights. If the document cannot answer, the value comes back empty.
Both modes are grounded. What changes between them is the shape of the answer: a single value you can sort and filter on, or a sentence a reviewer reads.

The decision table

Yes/No insights

A Yes/No insight is always Extract, because Synthesize only takes Text. That works: Extract answers Yes or No even though neither word appears in the contract, and quotes the clause it relied on. Insights created earlier as Yes/No with Synthesize now run as Extract, so they need no change.
Write a Yes/No description as the question, and say what counts as Yes. “Do we have audit rights?” reads Section 8.3, answers Yes, and cites the clause. Where the answer turns on nuance (notice periods, conditions), the quote carries the nuance and the value stays filterable.

The same question, both ways

Take one requirement (do we have the right to run a penetration test?) and see how the mode changes what you get.
Name: Pen test rights granted Type: Yes/No · Mode: ExtractDescription: Does the customer have a contractual right to perform penetration testing or security testing against the vendor’s production environment? Answer Yes only if testing is affirmatively permitted, including where it requires notice or scheduling. Answer No if testing is prohibited, or if the contract only offers third-party test summaries in place of customer testing.Result: Yes, quoting “Customer may, no more than once per twelve (12) month period and upon thirty (30) days’ prior written notice, conduct penetration testing of the Services.” on page 14, confidence high.Good when you want to sort your portfolio by which vendors you can test. The nuance about notice periods lives in the quote; the filterable answer lives in the value.
Many teams run both: a Yes/No Extract field for the dashboard and a companion Synthesize field summarizing the terms. They cost one extra pass each and answer two different jobs.

Quick rules

  • If you want one value you could sort or filter on (a date, a number, a name, Yes or No), use Extract.
  • If you would have to read a paragraph and then say a sentence back, use Synthesize on a Text insight.
  • Every Yes/No, Number and Date insight is Extract. Synthesize takes Text only.
  • A Number or Date you would have to work out is still Extract; put the working in the description.
  • When you cannot decide on a Text insight, start with Synthesize. You get an answer with a quote attached, and you can tighten to Extract later once you have seen how the language reads.
Mixing modes across your insight set is normal and costs nothing. Coverbase groups insights by mode and runs each group as its own pass over the document.

Concise and Detailed answers

Every insight also has an Answer format, set on its Definition tab. It decides how long the stored value is. New insights start as Concise, because a short value is easier to sort, filter, compare across vendors, and copy into a field. Insights that existed before answer formats were introduced stay Detailed, so their values read the same as they always have. Switch one to Concise only after you have tried it on the Test tab.
The format changes the length of the answer, not what counts as the answer. Both formats follow the same rules: a later amendment or override controls over the original clause, a section marked superseded or void is ignored, a unit heading such as “in thousands” applies to the figures beneath it, and a Yes/No answer is No only when the document says so. If the document is silent, the value stays empty.

Writing descriptions that work

The description is the prompt. Treat it like an instruction to a sharp new analyst who has never seen your contracts and will not ask follow-up questions. A description that performs well usually has four parts:
1

Define the thing precisely

“The maximum aggregate liability cap that applies to the vendor” beats “liability”.
2

Name the aliases

List the headings the clause hides under: Limitation of Liability, Liability Cap, Maximum Liability, Limitations on Liability.
3

Say what to do about edge cases

“If the cap is expressed as a multiple of fees, return the multiple and the lookback period. If liability is uncapped, return ‘Uncapped’.”
4

Say what not to return

“Do not return the indemnification carve-out amounts. Do not return the customer-side cap.” Exclusions prevent the most common wrong answers.
Name: Liability Description: (empty) Type: Text · Mode: ExtractReturns something from the liability section, but which sentence varies by document. On a contract with asymmetric caps you cannot tell whose cap you got.
When an insight misfires, read the reasoning on the extracted value before you change anything else. It usually says which sentence the model picked, and the fix is one exclusion sentence in the description.

A starter library

There is no packaged template for insights the way there is for clause sets. Insight definitions are yours to write, because they encode what your program tracks. Use this as the copy-and-adapt starting point. Group them, scope them to your contract document types, and delete anything you will not use.

Group: Contract basics

Scope to MSA, order form, SOW, terms of service, software license agreement.

Group: Renewal and exit

Scope to MSA, order form, terms of service.

Group: Risk and liability

Scope to MSA, DPA, security addendum.

Group: Data protection and security

Scope to DPA, MSA, security addendum, SCC.

Group: Service levels and AI

Scope to SLA, MSA, AI addendum.
In this library, Extract appears wherever the answer is a single value (dates, jurisdictions, figures, named frameworks, Yes/No), and Synthesize where the answer is a written judgment. Every Synthesize row is a Text insight, because that is the only type Synthesize takes.

Auditing coverage

Writing an insight is the easy half. Knowing whether it worked across your whole corpus decides whether anyone trusts the field. Configuration → Document Insights answers that. Three tabs over the same data:

Insights: is each definition healthy?

Your library, with coverage on every row: how many eligible documents carry a value, how many of those had verified evidence, and how many are waiting for a human to accept an unverified answer. Select several rows to enable, disable, rescope, regroup, archive, or backfill them in one action.
A matrix: document types down the side, insights across the top, a fill rate in every cell. This view answers “what do we extract from an MSA, and how well?”An em-dash means the insight is not scoped to that document type. A percentage means it is.
Every extraction in the org, filterable by insight, confidence, whether the quote was grounded, review state, and whether the value came from AI or was set manually.Filter to Needs review, or to low confidence and Not grounded, and you have a review queue. Click any row to open that document with the Insights tab already scrolled to the value in question, so you never leave the list to check a value.

Two kinds of blank

A missing value means one of two opposite things:
A brand-new insight shows 100% stale and 0% filled. That means the definition has not run yet. Backfill first, then judge the fill rate.

Backfilling history

A backfill re-extracts documents you already hold, so a new or reworded insight applies to your whole corpus instead of only to what arrives next.
1

Scope it

Pick the insights, and optionally narrow by document type or vendor. Starting from a stale badge in the coverage matrix pre-fills the scope for you.
2

Choose what to re-run

Only never attempted (the default) only touches documents the insight has never run against. Missing values also re-runs documents that were attempted and came back empty; use this after rewording a description. Every eligible document re-runs everything, replacing existing AI values.
3

Read the estimate

Before you confirm, Coverbase tells you how many documents it will process and roughly how many model calls that costs. Extraction batches every matching insight into one pass per document, so adding insights to a backfill is close to free. Adding documents is what costs.
4

Watch it run

A progress bar tracks dispatch. Large backfills run for a while; you can leave the page, and you can cancel, which stops further documents being queued.
A backfill never overwrites a value someone set by hand, in any mode. A value someone cleared by hand is left alone too, unless you tick Re-extract these too, replacing what was cleared when the dialog offers it.
Backfills are capped per run and per day. If a scope is too large, narrow it by document type or vendor and run it in batches. The cap exists so a single click cannot spend an unbounded amount on model calls.

The insight workbench

Click an insight on Configuration → Document Insights to open its workbench. Everything about one insight lives here: what it extracted, how to test a change, its definition, the fields it fills, its history, and the changes waiting for a reviewer. The header shows the insight’s name, whether it is on, its current version (Version 3, for example), and whether it fills fields automatically or asks a reviewer first. Test, Re-run and Export start from here. On Values, filter by revision, verdict, confidence, or whether the quote was found in the document. Click a row to open the value’s detail: the value, the quote and page, the reasoning, the verdict, and a timeline of everything that happened to it.

Teaching an insight with examples

A description tells Coverbase what to look for. An example shows it. Add examples on the Definition tab when the description is right but the answers keep coming back in the wrong shape, or when one kind of wording keeps tripping it up. Each example has three parts:
  • Document Excerpt. The passage the answer comes from, pasted from a real document (up to 4,000 characters).
  • Expected Answer. What the insight should return for that passage. Leave it empty when the passage does not answer the question, which is how you teach an insight not to guess.
  • Why This Is the Answer (optional). One sentence on why that is the answer, such as “The amendment in Exhibit C replaces the Net 30 term.”
Coverbase uses up to three of an insight’s examples each time it runs. Turn an example off to stop using it without deleting it. Adding, editing, or removing an example changes the definition, so it creates a new revision.
The fastest way to build examples is from your own corrections. When you correct a value on the Values tab, choose Save as example and Coverbase saves the document’s passage with your corrected answer.

Testing a change before you save

The Test tab runs your edited definition, including unsaved changes and examples, against documents you choose. Nothing is saved and no field is filled.
1

Pick documents

Choose a handful that cover the cases you care about: a clean one, one with an amendment, one you know came back wrong.
2

Run the test

Coverbase extracts each document the same way it does in production.
3

Compare

Each row shows the stored value next to the new one, with the new quote and page. Rows where the answer changed are marked, so you can see whether the edit fixed the problem without breaking a document that was already right.

Applying a change

When you save an edit that affects extraction (the description, type, mode, answer format, display format, document types, or examples), the insight moves to a new revision and Coverbase asks which documents should use it. Renaming an insight, turning it on or off, reordering it, or moving it to another group does not create a revision. Before you confirm, Coverbase shows how many documents it will re-run. Values set or corrected by hand are never overwritten by a re-run. Every value records the revision that produced it. Values extracted before revisions existed show Before versioning, so you can always tell which definition an answer came from.

Marking values correct or incorrect

A verdict records that a person checked a value against the document. On the Values tab, mark a value Correct or Incorrect, one at a time or by selecting several rows. You can clear a verdict if you change your mind. When you mark a value Incorrect, you can enter the right answer. The corrected value replaces the extracted one, is treated as set by hand, and is never overwritten by a later re-run. It also flows to any field the insight fills, following that field’s rules. Verdicts do three things for you:
  • They tell you which insights to fix. Filter to Incorrect to see where a definition goes wrong, then fix it and re-run those documents with Selected documents.
  • They become examples. Choose Save as example on a correction.
  • They build the dataset for your decision model.

Seeing one document type at a time

The Document types tab on Configuration → Document Insights shows coverage for each type. Click a type to open a grid of every document of that type down the side and every insight that applies to it across the top. Use it to read an MSA’s insights side by side across vendors, or to spot the one document where a value is missing. On Configuration → Document types, each type shows how many insights apply to it and links to those insights.

Retiring an insight

Three actions, easy to confuse:
Delete is not the safe default. It is only available on an already-archived insight, it tells you exactly how many extracted values it will destroy, and it makes you type the insight’s name to confirm. Archive is almost always what you want.

Promoting an insight to a custom field

An insight lives on a document. Your team works from vendor, contract, and assessment records. Promotion carries the value across.
1

Open the insight's Fields tab and choose Promote to custom field

Link an existing field of a compatible type, or Create a new field from the insight’s name and type.Text fills Text, Number fills Number, Date fills Date, Yes/No fills True/False. Select and multi-select are not supported.
2

Set the gates

Require a grounded quote (on by default) skips answers whose quote could not be located in the source. Minimum confidence skips anything below the bar. Together these decide how conservative the promotion is.
3

Choose what happens when the field already has a value

Never overwrite only ever fills an empty field. Fill if empty also refreshes a value this same insight wrote before. Latest document wins additionally replaces values written from older documents, which is the right choice for a vendor-level field fed by many documents.
4

Backfill the field

Leave Backfill existing values checked and Coverbase populates the field across every document you already hold.
A promoted value keeps a link to the document, page, and verbatim quote it came from, so a field on a contract record can show a reviewer why it holds that value.
Promotion never overwrites a value a person typed: not on backfill, not on a later upload, not under any conflict policy.

Filling built-in contract and document fields

Besides custom fields, an insight can fill fields Coverbase already has on contracts and documents. Choose them on the insight’s Fields tab. A contract field is filled on the contracts linked to the document. The insight’s type has to match the field: a Date insight fills a date field, a Number insight fills a number field, and a Text insight fills a text field. Each built-in field uses the same gates and conflict choices as a custom field: Require a grounded quote, Minimum confidence, and Never overwrite, Fill if empty, or Latest document wins. Latest document wins compares the dates of the documents, so an older document processed later does not replace a newer one’s value.
A value a person typed into a field is never overwritten by an insight, whichever conflict choice you pick.

Fill automatically or ask a reviewer

The Fields tab also sets what happens when the insight finds a value for a field. With Ask a reviewer, pick a reviewer on the Fields tab. If you leave it empty, the request goes to the owner of the document’s vendor. If neither is set, the change still waits on the Review tab, but no one is notified. The reviewer sees the field, its current value, and the proposed value with its quote. Approve writes the value. Reject leaves the field as it is. If a newer document proposes another value before anyone acts, the older proposal is marked as replaced. Review pending changes for one insight on its Review tab, or for every insight on the Review tab of Configuration → Document Insights, where you can approve or reject several at once.
Use Ask a reviewer for fields that drive reminders or reports, such as a contract’s renewal date, and Fill automatically for fields people only read.

The audit trail

Every insight keeps a full record on its History tab. Definition Changes. Each version of the definition is listed with what changed, who changed it, and when. Open one to see the definition and examples exactly as they were. Value Changes. Every change to a value is recorded and never edited afterwards:
  • Extracted, or extracted again by a re-run, with the revision that produced it
  • Set or cleared by hand
  • An unverified answer accepted
  • Marked correct or incorrect, a verdict cleared, or a value corrected
  • Written to a field
  • A review requested, approved, or rejected
Each entry shows who or what made the change (an upload, a re-run, a backfill, or a person) and the value before and after. The same timeline appears in a value’s detail on the Values tab. Values that existed before the history was introduced start with one entry recording the value as it stood then.

The decision model

The Model tab on Configuration → Document Insights lets you build a model tuned to your organization’s documents from the answers your team has checked. You never need one: insights work without it.
1

Build the dataset

Coverbase gathers every value marked Correct and every correction. The tab shows how many examples that gives you and how they spread across insights. More verdicts make a better dataset, so mark values as you review them.
2

Evaluate

Runs your verified values as a test and reports how often the standard model and your candidate model agree with your team’s answers.
3

Train

Training needs Coverbase to enable it for your organization. Until then, Start training is unavailable; contact your Coverbase team to turn it on.
4

Activate

Once a trained model is ready and its evaluation looks right, Activate it. From then on, every insight in your organization extracts with it. Only one model is active at a time. Retire it to go back to the standard model.

Sharing a library between orgs

Insight definitions can be exported as a JSON file (names, descriptions, types, modes, and document-type scope, with no values and no ids) and imported into another org. This runs through the Coverbase API rather than a button in the dashboard. An import matches on the insight’s stable key. Existing definitions are skipped unless the import explicitly opts into overwriting them, so reimporting a shared library never silently reverts local prompt tuning. The Export on a single insight’s page is different: it downloads that insight’s extractions as a workbook (document, vendor, value, confidence, grounding, page and quote).

Reviewing and correcting values

The AI drafts; a reviewer checks the evidence before anyone relies on it.

Check the quote before you trust the value

Expand any insight on the document’s Insights tab to see the source quote, page number, confidence, and the model’s reasoning. Scan low-confidence values first; they are flagged because the model was not sure.
When the quote could not be located in the document, the insight reads Supporting evidence not verified. Check the answer against the document, then choose Accept answer to record that a reviewer accepted it; the evidence stays marked as unverified. To fix a wrong value, mark it Incorrect on the insight’s Values tab and enter the right answer (see Marking values correct or incorrect). A value set through the API is recorded as manual, is never overwritten by re-extraction or a backfill, and shows as manual in the CSV export.
Saving a change on the insight’s Definition tab asks which documents to re-run: only new documents, selected documents, or all past documents. See Applying a change. On a single document, Refresh all re-runs every insight, and a row’s actions re-run one.
Export CSV gives you every insight for the document with all metadata: the display value, each typed column, confidence, source quote, page number, reasoning, and whether it was AI-extracted or manual. Useful for spot-auditing a batch of contracts, or for handing a legal reviewer a worksheet.

Manage insights from MCP or the API

You can define, test, backfill and review insights from an MCP client or with an API key, as well as in the dashboard. An MCP client reads with query_platform(kind=...) (document_insight_configs, document_insight_config_detail, document_insights, document_insight_pending_changes, document_insight_stats, document_insight_backfills). It writes with mutate(entity="document_insight_config", action=...), mutate(entity="document_insight_value", action=...), mutate(entity="document_insight_example", action=...), mutate(entity="document_insight_backfill", action=...) and mutate(entity="document_insight_pending_change", action=...). The API routes sit under /v1/document-insights, /v1/document-insight-values and /v1/document-insight-backfills. See Create and manage document insights. You can also read coverage, value history, the inbox and accuracy checks, compare and export values, open evidence images, run an insight on one document, and delete an archived insight. An MCP client reads these with query_platform(kind=...) (document_insight_coverage, document_insight_value_query, document_insight_pivot, document_insight_config_events, document_insight_value_events, document_insight_snippets, document_insight_inbox, document_insight_model_scorecard, document_insight_preview) and writes with mutate(entity="document_insight_config", action=...) (test, export, delete), mutate(entity="document_insight_extraction", action=...) (run, start_preview) and mutate(entity="document_insight_pending_change", action="bulk_resolve"). Bulk approval and rejection of pending changes is in MCP only. See Delete a document insight and the sections after it. Before an MCP client sends a write, it shows you the change and waits for you to confirm it. The MCP tool reference lists every field. Creating or changing an insight, its examples, targets, groups or backfills needs org_settings:update:org. API keys do not hold it, so use a key created by a person whose role holds it. Reviewing values needs only vendor:update:org. Even with the right key, archiving or restoring an insight, unlinking a custom field, retiring a decision model and deleting an example, group, target or value stay with a signed-in user.

Troubleshooting

The insight comes back empty on documents that clearly contain the answer

Almost always one of four things:
  1. It never ran on that document. If the insight was created after the document was processed, it has never been attempted there. Check the coverage matrix: a stale badge means backfill, not a broken definition.
  2. A type that does not fit the question. A Number or Date insight only stores a value that parses as one, and a Yes/No needs a question with a yes-or-no answer. Match the type to the question, or use a Text insight.
  3. Wrong document-type scope. If the insight is not scoped to the type that document was classified as, it never ran. Check the document’s type on its detail panel, and check the insight’s document types (or its group’s).
  4. The description names the wrong thing. The model looked for what you described and did not find it. Add the aliases the clause hides under.
Yes/No insights always run as Extract, which reads the clause and answers Yes or No. Write the description as the question and say what counts as Yes. If it still comes back empty, the clause is usually missing from the document or the insight is not scoped to that document type.
Coverbase cites the physical page of the PDF, which often differs from the printed page label on long agreements with front matter or per-exhibit numbering. If the quote is correct, the citation is pointing at the right place.
A Number insight only stores a numeric value when the extracted text parses as one. Currency symbols and thousands separators are stripped automatically; ranges, footnotes, and unit suffixes are not. Tighten the description to ask for the figure alone.
Extraction is grounded against the document’s text layer. When a file’s pages are images, the document’s Insights tab says This file has no text to read; choose Run again and the re-run reads the pages with character recognition. If that still finds nothing, re-upload a text-based version of the document.
Scope it. An insight with an empty document-type list runs against every document in your library, including SOC 2s and policies. Put it in a group with the correct scope and enable inheritance.
You saved with Only new documents, so documents processed earlier keep the value from their revision. Filter the Values tab by an older revision, select those documents, and re-run them, or save again with All past documents. Values set or corrected by hand are never re-run.
The insight is set to Ask a reviewer with no reviewer chosen, and the document’s vendor has no owner. Pick a reviewer on the insight’s Fields tab, then approve the waiting change on the Review tab.
Training needs Coverbase to enable it for your organization. You can still build the dataset and run an evaluation. Contact your Coverbase team to turn training on.
The page requires the org-settings update permission. Ask an admin in your organization to grant it, or to make the change for you.

What’s next

Document types

The types an insight applies to, including your own custom types.

Contract Guardian guide

Insights tell you what a contract says. Clause reviews tell you how far it sits from what you would accept. Set up your clause sets next.

Analyst and reviewer guide

Where insights and clause reviews land in the day-to-day assessment workflow.