Extract the clauses that matter from a negotiated agreement, compare each against your playbook and its fallbacks, and register the obligations — with the position, and any deviation, left to a named lawyer.
Take the agreement as it stands — the executed document, its amendments, side letters and any restatement.
02
Read the bank's playbook: the preferred position, the named fallbacks, and where a term has to go to counsel.
Reason
03
Extract the clauses in scope and quote the text, with the definitions that give each term its meaning.
04
Compare each clause against the playbook position and the fallbacks the bank's lawyers have already approved.
05
Assemble the obligations, conditions and dates into a register, each one tied to the clause it came from.
Decide
06
Mark what is missing, non-standard or open to two readings, and keep that apart from what it could not find.
07
Route the term to the lawyer who owns it, with the clause, the playbook rule and the distance between them.
Out
08
Hand counsel a worked file — the clauses, the quoted text, the marked deviations and the register behind them.
09
Retain the version compared, the playbook rule applied, the lawyer's position and the reasons they gave.
→Product statement
The agent extracts, compares and records. Nothing it produces is a legal conclusion or legal advice; accepting a deviation, answering the counterparty, negotiating, executing and judging enforceability stay with a named lawyer.
Example workflow
One agreement, end to end
AgentHuman
1Agreement receivedThe document as executed or as drafted, with its amendments, side letters and any restatement
2Set and version resolvedWhich document governs today, and which defined terms carry across the rest of the set
3Clauses extractedThe clauses in scope, quoted to the clause number, read with the definitions that bind them
4Playbook comparedEach clause against the preferred position and the named fallbacks, with the gaps marked
No human action required
Stages 1 to 4 run before a lawyer opens the file — the set, the clauses and the playbook are compared first. Nothing in that stretch advises, accepts a deviation, answers the counterparty or signs anything.
5DecisionSplits on how far each reading is evidenced and how far the term sits from the playbook
Clauses quoted, deviations inside a named fallback
Reaches counsel as a worked file.
A term open two ways, or a clause it could not evidence
Reaches counsel marked unresolved, not as a deviation.
Legal counsel on the matter
Reads the worked file, takes the position on each deviation, and owns the advice, the mark-up and the signature.
Adopt · Overrule · Escalate
Positions taken — handed back▼
6Counsel decides, agent recordsOnly the position a named lawyer took, with the reasons given, written where access and policy allow
7Outcome evaluatedReadings counsel overruled, clauses counsel added, register dates corrected and business outcome
Overruled readings
A reading counsel overruled is counted as a failure.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Any legal conclusion or advice on the agreement.
Accepting a deviation from the playbook.
Accepting a counterparty's drafting or position.
Negotiating, or sending a mark-up or a reply.
Automation boundaryAgent acts unaided
✓Extract the clauses in scope and quote the text they come from.
✓Compare each against the bank's playbook and fallbacks.
✓Mark what is missing, non-standard or open to two readings, and mark what it cannot evidence.
✓Register the obligations, conditions and dates.
Write actions run only inside the approval boundaries agreed during implementation. A counterparty mark-up is not one.
Signing, executing or releasing any document.
Deciding whether a term is enforceable.
Waiving or varying an approved fallback position.
Changing the playbook, templates or access rules.
Example output
One agreement, annotated
Everything the agent marks is attached to the clause and the version it was read from.
Review output · single agreementIllustrative example
Agreement
Set
Playbook
Deviations marked
Confidence
Position
Vendor outsourcing agreement
Two amendments, one side letter
Vendor, v4
Four, quoted to clause
84%
None taken by the agent
As receivedThe documents as executed and the playbook as approved — the agent neither drafts them nor re-versions them.
Evidence usedLiability cap under fallbackNo step-in right locatedSide letter redefines a term
Why four, not sixTwo more were dropped — a playbook preference is not a legal requirement.
ActionAdoptOverruleEscalate
What the score decidesWhere the file sits in counsel's queue — not whether a deviation is acceptable.
Value
Where AI adds value
The same four claims, placed at the point in the workflow where each one applies.
Where the value landsValue 01 – 04
Every agreement in scopeAs executed and amended
03Playbook
Compare to your own playbook
Read each clause against the preferred position and the fallbacks your lawyers have already approved, not against a general market standard.
01Approved path
Reach counsel with the file worked
Pulling clauses out of a set and quoting them is slow and mechanical, so the quotes, the marked deviations and the register arrive with the agreement rather than after it.
02Human review
Separate a deviation from a preference
A term the playbook takes no position on, a clause open two ways, a definition that changes across the set — written down as unresolved instead of raised as a deviation.
04Build an evidence trail
Retain the version compared, the clauses quoted, the playbook rule applied, the lawyer's position and the reasons given — on both paths.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
Integration availability depends on the client's existing systems and API access.
Agent controls
Six layers between a clause and a position
Each control wraps the one inside it. The agent takes no legal position — it works the file a lawyer will take one on — and no reading leaves these layers as advice.
L6 · Outermost — last line of defenceInward → L1 · closest to the model
L6Rollback / safe modeReturn agreements to unaided review if evaluations or production signals degrade.Roll back
L5TraceabilityRecord the version compared, the clauses quoted, the playbook rule and the lawyer's position.Record
L4Privilege and accessRestrict who may open a matter file and what may be written into it.Restrict
L3Counsel gateNo deviation is accepted, waived or answered without a named lawyer.Gate
L2Version and set scopeThe set is resolved to the document in force before extraction, and a version the agent cannot resolve holds the file.Scope
L1Quotation testA reading is held back unless the clause, its text and its location are named.Cite
Model coreClauses marked — the text quoted, the playbook rule compared and what is unevidenced
L1 – L2Decide whether a reading may stand
L3Decides who may accept a deviation
L4 – L5Hold the file's limits, keep the record
L6Pulls automation back when signals degrade
How Nestack evaluates it
Evaluate the clause it did not find — not only the ones it did.
Coverage runs the whole depth of the workflow, and every layer is cut by slice.
Surface — the marked file counsel opens
Depth of coverage ▼
E1Clause-extraction evaluationWas the clause found, and is the quoted text the text in the document?
E2Set and version evaluationDid it read the document in force, with its side letters?
E3Playbook comparison evaluationWas the clause matched to the right rule and the right fallback?
E4Absence calibrationWhen it reported nothing, was there nothing there to find?
E5Slice evaluationHow does performance change across specific agreement cohorts?
Floor — the non-standard term that reached a lawyer
Failure modes
Where each failure originates in the agent
Seven failure modes plotted against the five stages of the agent lifecycle. None of them is a wrong legal answer, because the agent gives none — they are wrong readings of documents, reaching a lawyer as though they were right.
Agent lifecycleDirection of processing →
01 · Assembly2 modes
LW-01
Superseded version read as current
The original is quoted after an amendment or restatement moved the term.
LW-02
Document never in the set
A side letter nobody filed varies terms the agent reads as settled.
Stage gathersThe agreement, its amendments and side letters
02 · Extraction2 modes
LW-03
Clause read outside its definitions
A term defined elsewhere in the set is read at its ordinary meaning instead.
LW-04
Not found reported as not there
A clause it missed and a clause the agreement never had come back the same way.
Stage extractsClauses, the text quoted and the terms defined
03 · Comparison1 mode
LW-05
Playbook position stated as law
A preferred position is written up as though a rule required it.
Stage comparesEach clause against the playbook and fallbacks
04 · Handover1 mode
LW-06
Obligation dated from the wrong trigger
A notice period is registered from execution, not the event that starts it.
An NDA cut from the bank's own template has one version and a playbook written for it. Failures gather where the drafting came from the other side and a defined term travels across a set. Nestack reports by slice, not only in total.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Counterparty-paper agreements
5.1%
3.5×
Review
ISDA and CSA schedules
3.9%
2.7×
Review
Scanned and side-lettered files
2.8%
1.9×
Watch
Bank-template NDAs
1.2%
0.8×
Normal
Bar: mis-marked-clause lift vs. bank-template NDA baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
The signed version tells you what was missed
A deviation the agent never marked surfaces in the executed document — the term counsel negotiated is not the one it read. That comparison feeds the loop.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Overruled readings rise in one agreement cohort, or a clause counsel added was never on the list.
02Diagnose
Traced back through the set — which version was read, which definition applied, which playbook rule was matched.
03Improve
The extraction pattern or the playbook mapping is re-approved by the general counsel's office and version-linked.
04Verify
Re-run over agreements already executed, including the ones counsel overruled a reading on.
05Learn
The wording that carried two readings is written into the playbook, beside the fallback it sat against.
Learn → DetectThe return edge. A playbook is revised while agreements are still in negotiation, so each cycle re-compares files the last one had already handed to counsel.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, the document set and the playbook, extraction and comparison, evaluation, counsel handover, then validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Agreement scoping and legal-boundary definition.
02Document-store and CLM assessment.
03Playbook, fallback and escalation mapping.
04Version, amendment and side-letter resolution.
05Clause extraction and quotation standard.
06Defined-term resolution across the set.
07Playbook comparison and deviation marking.
08Obligation, condition and date register.
09Privilege, access and confidentiality controls.
10Absence-calibration and slice evaluation suite.
11Counsel handover and document-system integration.
12Observability, deployment and Agent Care handover.
12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallelFinal scope and sequence confirmed in discovery
Engagement tiers
What each tier includes
Rows are the capabilities named in each tier's scope. Higher tiers include everything below them. No tier moves the legal position off a named lawyer.
Capability✓ in scope · — not at this tierPilotOne agreement type, one playbookProductionProduction workflow integrationAdvancedMulti-entity / multi-jurisdiction
Introduced at Pilot
Clause extraction quoted to the document✓✓✓
Playbook comparison with deviations and gaps marked✓✓✓
Obligation, condition and date register✓✓✓
Named-counsel gate on deviations✓✓✓
Privilege and access controls on the file✓✓✓
Audit trail and baseline evaluation✓✓✓
Introduced at Production
Additional agreement types and playbooks—✓✓
CLM, document-store and workflow integration—✓✓
Observability and evaluation—✓✓
Introduced at Advanced
Multi-entity and multi-jurisdiction playbooks——✓
High volume and portfolio re-papering——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on the agreement types and playbooks in scope, document-store and CLM integrations, document volume, access controls and deployment requirements.
Separate from buildBuild pricing is separate from recurring Agent Care, which covers managed monitoring, evaluations, incidents and verified improvements after launch.
What we need from you
What you bring, and what we build with it
Each input maps to a piece of build scope and a week in the delivery timeline.
You bringWe build with it
01A set of agreements and the mark-ups your lawyers returned→Agreement scoping and legal-boundary definitionWeek 1
02Your playbook — preferred position, fallbacks and who owns each→Playbook, fallback and escalation mappingWeek 1
03Access to the document store, the CLM and the signed archive→Document-store and CLM assessment, then integrationWeek 2
04The amendments, side letters and restatements behind each file→Version, amendment and side-letter resolutionWeek 2
05The clauses you actually care about, and how you quote them→Clause extraction, quotation standard and defined-term resolutionWeek 3
06Your rules on privilege, access and what a matter file may hold→Privilege, access and confidentiality controlsWeek 4
07Named lawyers, and who may accept a deviation→Counsel handover and review workflow, then supervised queuesWeeks 5–6
Nothing else is requiredDeployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
Phases are drawn over the weeks they actually occupy. Week 5 replays agreements your lawyers have already marked up, so nothing live waits.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1The agreements in scope, the playbook and who owns eachW2Document-store and CLM access, then version resolutionW3Clause extraction, defined terms and playbook comparisonW4Obligations register, privilege controls and evaluationW5Agreements replayed against mark-ups you already returnedW6Lawyers work the live queue under review, then handover
Reading the bandVersion and side-letter resolution lands before extraction starts, because a clause quoted from a superseded document invalidates every comparison behind it. The bars show that order, not a smooth ramp.
At the end of W6Lawyers have worked live agreements from the agent's file, the readings counsel overruled have been counted, and Agent Care takes over monitoring.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Banking AI agent
Build a review agent around the playbook your lawyers already apply.
Show us a set of agreements, the playbook you compare them to and the mark-ups your lawyers returned. We'll re-read that set against your own positions and mark two things on each file — the clauses counsel added that the agent had not marked, and the readings a lawyer overruled.
