Skip to main content

How to run an AI action

What this page is — the two places Orbit Papers offers AI on a document, what running one actually does, and what it costs.

What it is for — so the 23 capabilities are something you reach for deliberately, on the document in front of you, rather than a menu nobody opens.

The problem it solves — unclear costs and prerequisites mean people either never try the AI or spend credits on runs that return nothing useful.

Route: /org/papers/documents/<document>/ai, or AI Assistant on the document · Permission: Use AI drafting/extraction/Q&A for documents.

Figure 1 — All 23 capabilities, grouped, beside the document they run against.

1. Two surfaces, the same capabilities​

SurfaceWhereUse when
AI Assistant drawerOn the document, beside the fieldsYou are working on the document and want an answer without leaving it
AI workspaceThe document's own AI pageYou are reviewing rather than editing, and want room to read results

The capabilities, the results and the cache are shared between them — a result generated in the drawer is the same result the workspace shows. They differ only in how much room you get to read it.

The four groups​

GroupAnswersCapabilities
UnderstandWhat does this document say?7
NegotiateHow good a deal is it, and what is still open?8
ComplyDoes it meet our rules and the law?7
TransformTurn its content into structured values1

The full list, with cost, inputs and what each writes, is in the AI capabilities reference.


2. Why you would use them​

The economics of contract review are unforgiving: the cost of reading is paid every time, by whoever happens to be holding the document, and the value of having read it decays.

  • They answer against the document in front of you. Reading a fifty-page agreement to answer one question is how review becomes a bottleneck. These answer the question directly, with the clause cited so you can check.
  • A result is generated once and read many times. Because results are saved to the document (§5), the cost is paid once and the answer is available to everyone thereafter. That is where the saving actually comes from — not from any single run being fast.
  • They make expertise available to whoever has the document. A reviewer who has never seen a lease gets the lease checklist, the retention statute and the fairness calibration applied to their first one.
  • The ones that write turn analysis into tracked work. Extraction seeds the obligation register; the graph builds the knowledge graph. Those two convert reading into something the organisation can act on later (§6).
  • They are cheap relative to what they catch. 450 credits against an uncapped indemnity, a double-applied tax, or a notice period shortened inside a reformat.

3. What you provide​

Most capabilities are a single press. Four need something first, and the interface asks rather than offering a button that could only fail:

CapabilityNeedsRequired?
Compromise draftBoth positions, typed inYes — it refuses without them
Redline gradeThe specific counterparty redline to gradeYes — suggestion_id or suggestion_text
Regional annexuresJurisdictionsOnly if the document names none itself
Smart fieldsDefinitions configured in Papers settingsNothing at run time, but nothing runs without them

Several more take an optional input that materially changes the answer — the perspective on Risk analysis, the audience on Redaction suggestions, the policy on Compliance & policy check. Leaving those blank gives you a usable default, not the best answer available.

Three are perspective-aware​

Risk analysis, Shadow redline and Fairness / balance are cached per perspective — our side, the counterparty, or neutral.

Run the important ones from the other side too

The most useful thing risk analysis can tell you is often what the counterparty will object to. Because results are cached per perspective, both answers are kept — and switching perspective is a separate run at a separate charge, not a refresh of the same one.


4. Worked example — one document, four capabilities​

A supplier's master services agreement arrives. Here is what a full first pass costs and returns.

StepCapabilityInputWhat it gave back
1Fairness / balanceour side34 — heavily one-sided. This is the triage decision: worth a full review
2Missing clauses—No limitation of liability, importance: high
3Risk analysisour sideUncapped liability at clause 11, with the redline to ask for
4Risk analysiscounterpartyTheir objection list — the IP assignment at clause 14

Total: 1,800 credits, four runs, about six minutes.

What the reviewer walks away with. Not four reports — one negotiating position. Fairness said the document is worth arguing about; missing clauses and risk analysis agreed on what (the uncapped liability) and supplied the specific ask (mutual cap at 12 months' fees, carve-outs for confidentiality and IP); and the counterparty-perspective run named the trade — concede narrowing on clause 14 to win the cap on clause 11.

All four results are now saved on the document. The colleague who picks this up next week pays nothing to see them.


5. Results are kept with the document​

Figure 2 — A result opens in its own tab, marked as saved, with Re-run beside it.

A result belongs to the document, not to your session. Somebody opening the document tomorrow sees what was already run. That is deliberate: it makes the analysis part of the document's history, and it stops the same question being paid for repeatedly.

Reading a cached result is free. Only a re-run is charged.

A cached result does not know the world changed

The cache is keyed on this document's content, which is right for most capabilities and misleading for two:

  • Cross-document consistency compares against related documents. If one of those changed, this document did not — so nothing invalidates the cache.
  • Regulatory drift is a snapshot of the law on the day it ran, and the law moves without touching your document at all.

For those two, re-run on a schedule rather than trusting age.


6. What is applied, and what is not​

The general rule is that nothing is applied to a document automatically. Not a clause, not a redline, not a translation, not a retention date. A legal artifact only changes when a person changes it — every AI result is a proposal you read first.

Two capabilities are exceptions, and they do not touch the document body either:

CapabilityWritesBehaviour on re-run
Extract key termsThe obligation register — obligations tagged source: ai_extractedAdds only what is new; deduped by description. Extracted obligations can be cancelled but never deleted
Entity & concept graphThe knowledge graph — this document's edgesReplaces this document's AI-derived edges rather than merging

Neither alters a word of the document. But both change data the organisation then works from, so both are decisions rather than free actions.


7. The admin contract​

Five things must be true before a capability appears, and all but the first fail silently.

Must be trueWhereWhat happens if it is not
Your role holds Use AI drafting/extraction/Q&A for documents.Role editorNo AI Assistant button at all
The utility's global is_active switch is onOrbit AI Flow → utilities"This utility is currently disabled"
The utility is enabled for your organisation/org/ai-utilitiesThe capability is absent from its group, with no error anywhere
papers.ai_monthly_credit_cap is not reachedSystem Config"monthly AI credit cap reached: n of n credits used this month". 0 means uncapped
The document has extractable textThe documentA scanned PDF analyses to nothing. Run OCR first
The document type does NOT decide which capabilities are offered

This is the most common misconception about Papers AI, and it sends people to the wrong screen.

The type's AI Config tab governs auto-run only — which capabilities fire on submit, round or finalize. Manual runs are always available regardless of what the type configures. A capability missing from a group is a permission or a utility-enablement problem, never a type problem.

Confidential documents: automatic runs are blocked, manual runs are not

For a document whose confidentiality is confidential:

  • Automatic runs are blocked entirely — default deny. A platform administrator must set the System Config key papers.ai_confidential_cloud to the literal value allow. The block is silent to the user and appears only in the server log.
  • Manual runs are not blocked. Where a local model key is configured, the run is forced onto the on-prem model and audited on the document timeline as ai_local_routed; content never reaches a cloud API.

So a confidential document can return a result you pressed for, while its type's auto-run policy quietly does nothing.


8. Drafting AI is a different thing​

The Drafting AI drawer on the authoring page writes: it drafts a body, suggests clauses, rewrites tone, translates, turns a transcript into a document, and proposes counter-proposals. It also carries a Human writing depth control.

The capabilities on this page analyse. The distinction matters because drafting output is meant to be edited and applied, while analysis is meant to be read.

Compromise draft sits on the drafting side despite appearing in the Negotiate group — it produces wording to paste, and it is reached from the Drafting AI drawer.


9. Don't confuse this with…​

Orbit AI FlowWhere utilities, prompts and models are administered. This is where they are used
Ask the repositoryAnswers across the whole corpus. These run against one document
AI configurationWhere auto-run is set per type. It never controls what is offered manually
Zonal extractionReads fixed positions on a scanned page. These read meaning

10. Troubleshooting​

SymptomCause
No AI Assistant buttonYour role lacks Use AI drafting/extraction/Q&A for documents.
A capability is missing from a groupThe utility is off for your organisation (§7). Not a document-type setting
A whole group is missingEvery capability in it is disabled. Transform has one member, so it vanishes entirely
A result looks staleIt is cached with the document. Re-run — and see the two special cases in §5
A capability will not run on a pressIt is one of the four that need an input first (§3)
Nothing ran on submit or finalizeNothing is configured on the type, or the document is confidential and cloud AI is default-denied (§7)
Obligations appeared that nobody createdExtract key terms was run — it writes to the register (§6)
Graph edges disappeared after a re-runEntity & concept graph replaces rather than merges (§6)
"Adapt to jurisdiction" cannot be foundIt is not offered — see the reference
"monthly AI credit cap reached"The organisation's monthly Papers AI spend cap is exhausted. It resets next month