Skip to main content

AI configuration

What this page is — the tab that sets AI behaviour for every document of a type: the drafting assistant, which analyses run automatically at submit, each counterparty round and finalize, and two advanced JSON settings.

What it is for — so the right analysis is waiting on a document when someone opens it, without anyone remembering to run it.

The problem it solves — useful analyses only happen when someone remembers to run them, which is usually after the document has gone out.

Route: /org/papers/designer/<type> → AI Config · Permission: Create/edit/retire project types and template versions..

Figure 1 — Configured once on the type, applied to every document made from it.

1. What it is​

Four settings, and they are not equally real:

SettingDoesActually used by
Drafting utilityThe generator offered while authoringThe Drafting AI drawer
Auto-run analysisCapabilities that run on submit, round and finalizeThe lifecycle engine
Redline playbook (JSON)Fallback positions and preferred languageOnly the Compromise drafter
Extraction schema (JSON)Intended to shape term extractionNothing at present — it is saved but not used. Use smart fields to shape extraction
Redline grade does not use this tab's playbook

Redline grade grades against each clause's fallback positions in the Clause library. The playbook JSON here only seeds the Compromise drafter. If redline grading looks generic, add fallbacks to the clauses — not JSON to this tab.

AI configuration is saved on the type, with its own Save AI config button — the header's Save draft does not save it, and it does not need publishing.


2. Why you would use it​

  • Reviewers start from analysis, not a blank document. Risk analysis and missing clauses run on submit, so the approver opens a document with both already waiting.
  • Every counterparty round is checked the same way. Version diff and shadow redline on each round catch the four-word indemnity change nobody reads for.
  • Finished documents carry their own summary. Summarize and Extract key terms on finalize put a summary and seeded obligations on every executed agreement.
  • Spend is predictable. Each event's selection is a known number of runs at a known cost per document.

3. How it spreads​

EventFires whenResults land in
On submitA document is submittedThe document's AI Assistant, as cached results
On counterparty roundEach counterparty round is recordedSame
On finalizeA document is finalizedSame — and Extract key terms seeds the obligation register

Runs are best-effort: a failed capability is logged and never blocks the transition or the other capabilities.


4. Step by step​

  1. Pick a Drafting utility, or leave No drafting assistant.
  2. In each event, pick the analyses to run.
  3. Leave the JSON boxes empty unless you use the Compromise drafter.
  4. Save AI config. Invalid JSON blocks the save with a message.

5. Field reference​

Drafting utility​

Draft Generator · Clause Suggester · Tone Rewrite · Translator · Annexure Generator — or none. The ? beside the picker opens the selected utility's guide.

Auto-run analysis​

Nineteen capabilities can be selected on any event. Four cannot: Compromise draft, Fairness / balance, Compliance & policy check and Cross-document consistency.

GroupSelectableSensible event
Analysis on any eventSummarize, Risk analysis, Extract key terms, Missing clauses, Blind spots, Entity & concept graph, Classify, Redaction suggestions, Retention advice, Approval routing, Cross-validate, Regulatory drift, Smart fields, Regional annexuresSubmit or finalize
Needs a round or trailVersion diff, Redline grade, Shadow redline, Negotiation summary, Negotiation analyticsOn counterparty round — they produce nothing useful on a first submit

On a round event, Redline grade is fed the newest open counterparty redline automatically.

Rules that apply to every automatic run​

RuleEffect
CreditsEach run costs the capability's normal credits — usually 450
Monthly cappapers.ai_monthly_credit_cap stops automatic and manual runs alike
Confidential documentsAutomatic runs are blocked unless System Config papers.ai_confidential_cloud is allow. Silent — only the server log says so
Manual runsAlways available, whatever this tab says

Read-only​

Without Create/edit/retire project types and template versions. the tab says it is view-only and names the permission.


6. Worked example​

A legal operations lead configures a Master Services Agreement type.

EventSelectedCredits
On submitRisk analysis, Missing clauses900
On counterparty roundVersion diff, Shadow redline, Redline grade1,350 per round
On finalizeSummarize, Extract key terms, Entity & concept graph1,350

A typical MSA here goes through three counterparty rounds, so each agreement costs about 900 + 3 × 1,350 + 1,350 = 6,300 credits automatically — worth knowing before 200 of them a year run against the monthly cap.

They leave the Extraction schema empty: it would do nothing. They paste their liability and payment fallbacks into the Redline playbook, knowing it will only seed the Compromise drafter, and add the same fallbacks to the clauses in the library so Redline grade uses them.

One document is marked confidential. On submit, no analysis appears — the cloud AI gate blocked it, and the reviewer runs Risk analysis by hand, which is allowed.


7. The admin contract​

Must be trueWhereWhat breaks without it
The selected utilities are active and enabledOrbit AI Flow, /org/ai-utilitiesThose runs fail, silently
papers.ai_monthly_credit_cap has roomSystem ConfigAutomatic runs stop mid-month
papers.ai_confidential_cloud = allow, if confidential documents should auto-runSystem ConfigNothing runs on them
The type's lifecycle records counterparty roundsLifecycleRound events never fire
Save AI config was pressedThis tabNothing is saved — Save draft does not cover this tab

8. Downstream​

When you…Then
Save a new selectionIt applies from the next event on every document of the type — no publish
Select Extract key terms on finalizeObligations are written to the register on every finalize
Select Entity & concept graphThe knowledge graph's AI edges for each document are replaced on each run

9. Don't confuse this with…​

How to run an AI actionManual runs, always available
Orbit AI FlowWhere utilities and models are administered
Clause libraryWhere Redline grade's fallbacks actually live
Smart fieldsThe real way to define what gets extracted

10. Troubleshooting​

SymptomCause
An expected analysis never appearsThe utility is disabled, the cap is reached, or the document is confidential
My extraction schema changed nothingThe schema is not currently used — define smart fields instead
Redline grading ignores my playbookIt uses clause-library fallbacks, not this JSON
Changes did not saveSave AI config is separate from Save draft
Round analyses never runThe lifecycle does not record counterparty rounds
A capability is missing from the pickerIt is one of the four that cannot auto-run