Skip to main content
GET
Get a contract review

Authorizations

Authorization
string
header
required

Workspace credential issued from the automation console at /automation. Send it as Authorization: Bearer vq_ws_.... This is NOT a Data API key: a vq_key_ credential is refused here and names the other product in the error.

Path Parameters

matterId
string
required

mat_ identifier of the matter to work inside. Everything in this API hangs off a matter, and the matter in the path is what the authorization boundary is checked against. Take it from GET /v1/matters.

reviewId
string
required

rev_ identifier of the contract review. Returned on the operation that launched it, at either depth.

Response

Successful Response

One contract review: its findings, or its progress toward them.

id
string
required

Public identifier, rev_ followed by 32 hex characters.

Example:

"rev_9f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6"

matterId
string
required

mat_ identifier of the matter this review belongs to.

Example:

"mat_9f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6"

status
enum<string>
required

Review status, using the same five public values as an operation. While queued or running, every findings list is empty and the scalar fields are absent. That is the truthful shape of a review that has not happened yet, not an error.

Available options:
queued,
running,
succeeded,
failed,
cancelled
Example:

"succeeded"

createdAt
string<date-time>
required

When the review was created (RFC 3339).

Example:

"2026-08-19T14:32:10Z"

contractType
string | null

Contract type the review ran as, echoed from the request.

Example:

"msa"

userSide
string | null

Which side the review argued for, echoed from the request.

Example:

"buyer"

playbookId
string | null

The playbook the review actually ran against. Absent when it ran against the built-in defaults, so the two cases can be told apart after the fact.

Example:

"pbk_9f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6"

jurisdiction
string | null

Jurisdiction the review ran under.

Example:

"US"

round
integer
default:1

Negotiation round this review was run for.

Example:

1

summary
string
default:""

Prose summary of the review's conclusions.

Example:

"Twelve substantive changes, seven of them in the liability and indemnity sections."

overallRisk
string | null

Overall risk rating for the contract: green, yellow or red.

Example:

"yellow"

businessImpactSummary
string | null

What the findings mean commercially, in plain language.

Example:

"Two changes shift risk toward us; the rest are housekeeping."

approvalGate
ReviewApprovalGate · object | null

Whether a human should sign this off before it goes out. Reported, never enforced.

liabilityExposure
ReviewLiabilityExposure · object | null

How much you are on the hook for: caps, carve-outs, indemnities and insurance.

counterpartyMatch
ReviewCounterpartyMatch · object | null

Set when a known counterparty paper was recognized, which means the findings include counterparty-specific redlines layered on the general analysis.

clauses
ReviewClause · object[]

Every clause analyzed, with its severity against the playbook position.

redlines
ReviewRedline · object[]

Proposed edits, ready to send to counterparty counsel. Check each one's grounding before applying it automatically.

negotiationPriorities
ReviewNegotiationPriority · object[]

What to raise first and what to trade, in tiers.

missingClauses
string[]

Standard clauses ABSENT from the contract. The one finding that cannot be expressed as a clause analysis, because there is no clause to analyze.

Example:
flags
ReviewFlag · object[]

Things the reviewer noticed and deliberately did not redline: a wrong entity name, an odd schedule entry, a real ambiguity. Confirm these with a human before signing.

parseWarning
string | null

Set when the model's output only partly parsed, which means the findings may be incomplete. Present is the difference between acting on the findings and asking a human first.

Example:

"Two clauses could not be parsed and are omitted from the findings."

deep
ReviewDeepMeta · object | null

What the deep verification pass did. Absent on a standard review, which is the signal that no verification ran rather than that it found nothing.

completedAt
string<date-time> | null

When the review reached a terminal status (RFC 3339).

Example:

"2026-08-19T14:32:10Z"

Last modified on August 23, 2026