Skip to content
D
EU AI Act: Not High Risk Q2

Contract & Offer Generation Agent

From offer decision to signed contract - with the right clauses for every jurisdiction.

Generates employment contracts from standardised templates with correct parameters and routes them through the approval process.

Analyse your process
Airbus Volkswagen Shell Renault Evonik Vattenfall Philips KPMG

Select template via rules, validate mandatory clauses, recommend optional clauses via AI

The agent selects contract template and fills parameters deterministically by contract type and jurisdiction, validates 15 mandatory clauses under transparency and fixed-term employment directives rule-based and recommends additional clauses via AI extraction - HR approval remains as Human-in-the-Loop step.

Outcome: Instead of 3 weeks waiting time per candidate and since August 2022 sanctioned mandatory information (EU Directive 2019/1152), a complete contract in hours, with automatic check against compensation bands and legal routing for special clauses.

67% Rules Engine
22% AI Agent
11% Human

The logic behind this decomposes an employment contract into the eight decision steps that truly make up its creation:

Eight decisions, three weeks waiting for the contract

An employment contract is not a document. It is a chain of eight decisions - contract type, template, parameters, mandatory clauses, compensation band, optional clauses, legal review, HR approval. Most organisations still treat it like a Word file: open template, fill in fields, save as PDF, email to candidate. And then wonder why candidates wait three weeks for their contract - and why mandatory disclosures are missing that have carried penalties since the 2022 EU Transparent and Predictable Working Conditions Directive transposition deadlines.

Fifteen Mandatory Disclosures and a Template from 2019

This agent follows the Decision Layer principle: each decision is either rule-based, AI-assisted, or explicitly assigned to a human.

Under the EU Directive on Transparent and Predictable Working Conditions (2019/1152), transposed into national law across all member states, every employment contract must contain a defined minimum set of disclosures: composition and amount of remuneration including overtime pay, allowances, and payment dates. Working time arrangements including rest breaks and shift systems. Notice periods. Reference to applicable collective agreements. Occupational pension arrangements. Training entitlements. End date for fixed-term contracts. Name and address of the contracting parties. And more. (US: requirements vary by state, but California, New York, and several others mandate specific written disclosures at hire.)

Missing a mandatory disclosure is not a theoretical risk. Labour courts across Europe have awarded damages when employers failed to notify employees of important contractual terms - such as exclusion periods in collective agreements that the employee missed because they were never informed.

In practice, template management breaks down as follows: templates were created in 2019, before the directive transposition. Someone wrote a checklist in 2022. Some offices use the updated version, others use the old one from the shared drive. Fixed-term contracts lack the objective reason. Part-time contracts omit overtime compensation terms. Collectively agreed contracts miss the reference to the applicable agreement. Nobody notices - until someone litigates.

Where Exactly the Process Breaks

The errors are not random. They occur at four predictable points.

Template sprawl. A company with three locations, collective and non-collective contracts, fixed-term and permanent variants needs at least twelve templates. In practice, thirty exist - because each office has made local adjustments, because the old version was never deleted, because someone created a copy for a special case last year. Which template is current is anyone’s guess.

Manual parameter transfer. Compensation, working hours, location, benefits, start date - everything is transcribed manually from the offer letter into the contract. A transposed digit in the salary. A wrong start date. The probation period says six months when three was agreed in the offer. These errors surface at best when the candidate reads the contract. Sometimes they never surface at all.

Missing mandatory clauses. Not every clause belongs in every contract. Non-compete agreements only for certain positions, relocation support only for site changes, company car provisions only above a certain grade. Which optional clauses apply to which case exists in no template - it lives in the experience of the person drafting the contract. When that person is ill, on holiday, or has left the company, the clauses are missing.

No compensation validation. The offer says EUR 85,000 (USD 93,000). The compensation band for the position caps at EUR 82,000. Nobody checks systematically. The contract goes out, the hiring manager has made a promise that breaks the pay structure. The Comp&Ben team discovers it months later when payroll data flags the anomaly - and can no longer correct it.

Nine Steps, Three Decision Principles

Contract type       Template          Parameters          Mandatory clauses
determine      -->  select       -->  populate       -->  validate
(R: Rules)          (R: Rules)        (R: Data             (R: Checklist per
                                       transfer)            jurisdiction)

Compensation band   Optional clauses  Legal review        HR approval
validate       -->  recommend    -->  route          -->  grant
(R: Band check)     (A: Context AI)   (R: Escalation      (H: Human)
                                       rules)

Contract
issue
(R: Automated
 after approval)

Of nine decision steps, seven are rule-based. The rules are unambiguous: contract type follows from position, term, and collective agreement status. The template follows from contract type and jurisdiction. Parameters come from the approved offer. Mandatory clause validation checks against a jurisdiction-specific list. Band validation compares the agreed compensation against the stored band. Issuance is automated after approval through the defined channel.

Only one step uses AI: recommending optional clauses. A non-compete for a sales director with key account relationships. Relocation support for a site change over 100 kilometres. A signing bonus for a position that has been vacant for four months. That is context-based interpretation - no rule engine can model every constellation. But the AI recommends only. Whether the clause is included is decided by legal or HR.

And exactly one step stays with a human: the final approval. HR reviews the completed contract before it reaches the candidate. Not because the system is unreliable, but because accountability for a contractual offer cannot be delegated.

Contracts reach candidates in three hours instead of three weeks, cutting offer dropout

Most discussions about contract generation end at the PDF. But the critical moment comes after: the time between verbal acceptance and signed contract determines whether the candidate starts or walks away.

Juro, a contract management software provider, reports a reduction in time-to-hire of up to 75 percent through automated contract generation. The figure is high, but the direction is correct: when a contract reaches the candidate in three hours instead of three weeks, the dropout rate in the offer process drops significantly. In a labour market where strong candidates have three offers on the table simultaneously, the speed of contract delivery is not an administrative detail. It is a competitive factor.

Infrastructure That Reaches Beyond the Individual Contract

The template engine that determines contract types and populates parameters here is not a one-off solution. The same logic is reused by the HR Document Management Agent for references, certificates, and amendments. The clause library that manages mandatory and optional clauses here forms the foundation for the Legal Contract Review Agent. The band validation uses the same engine as the Merit Cycle Governance Agent.

The less obvious infrastructure: every generated contract produces a complete decision log. Which template was selected and why. Which parameters were taken from which source. Which mandatory clauses were validated. Whether the compensation falls within the band. Whether and why legal was involved. Over hundreds of contracts, these logs reveal where the process systematically stalls - and where the templates themselves need updating.

For organisations that hire regularly, this is not an efficiency project. It is the foundation for ensuring every contract is legally sound, compensation-compliant, and fully traceable - without anyone having to manually review every line.

Micro-Decision Table

Who decides in this agent?

9 decision steps, split by decider

67%(6/9)
Rules Engine
deterministic
22%(2/9)
AI Agent
model-based with confidence
11%(1/9)
Human
explicitly assigned
Human
Rules Engine
AI Agent
Each row is a decision. Expand to see the decision record and whether it can be challenged.
Receive contract generation request Intake approved offer data and position details Rules Engine

Structured intake from recruiting system or approval workflow

Decision Record

Rule ID and version number
Input data that triggered the rule
Calculation result and applied formula

Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.

Select contract template Choose correct template for position type, jurisdiction, and category Rules Engine

Template selection rules per position attributes and jurisdiction

Decision Record

Rule ID and version number
Input data that triggered the rule
Calculation result and applied formula

Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.

Populate standard fields Fill template with candidate, position, and compensation data AI Agent

Automated data merge from offer approval and master data

Decision Record

Model version and confidence score
Input data and classification result
Decision rationale (explainability)
Audit trail with full traceability

Challengeable: Yes - fully documented, reviewable by humans, objection via formal process.

Apply jurisdiction-specific clauses Include mandatory clauses for the applicable employment law Rules Engine

Clause selection rules per jurisdiction and contract type

Decision Record

Rule ID and version number
Input data that triggered the rule
Calculation result and applied formula

Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.

Add collective agreement references Include applicable collective agreement terms and references Rules Engine

Agreement mapping per employee group and location

Decision Record

Rule ID and version number
Input data that triggered the rule
Calculation result and applied formula

Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.

Validate internal consistency Check that all contract elements are consistent with each other Rules Engine

Cross-field validation rules (probation period matches jurisdiction, etc.)

Decision Record

Rule ID and version number
Input data that triggered the rule
Calculation result and applied formula

Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.

Route for legal review Send completed draft to legal for compliance review Rules Engine

Routing rules based on contract type and non-standard elements

Decision Record

Rule ID and version number
Input data that triggered the rule
Calculation result and applied formula

Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.

Legal review and approval Confirm legal compliance and approve for issuance Human

Human legal review for contract accuracy and compliance

Decision Record

Decider ID and role
Decision rationale
Timestamp and context

Challengeable: Yes - via manager, works council, or formal objection process.

Issue contract Send contract to candidate for signature AI Agent

Automated issuance through document signing platform

Decision Record

Model version and confidence score
Input data and classification result
Decision rationale (explainability)
Audit trail with full traceability

Challengeable: Yes - fully documented, reviewable by humans, objection via formal process.

Decision Record and Right to Challenge

Every decision this agent makes or prepares is documented in a complete decision record. Affected employees can review, understand, and challenge every individual decision.

Which rule in which version was applied?
What data was the decision based on?
Who (human, rules engine, or AI) decided - and why?
How can the affected person file an objection?
How the Decision Layer enforces this architecturally →

Does this agent fit your process?

We analyse your specific HR process and show how this agent fits into your system landscape. 30 minutes, no preparation needed.

Analyse your process

Governance Notes

EU AI Act: Not High Risk
Not classified as high-risk under the EU AI Act - the agent generates documents without making employment decisions. However, the legal accuracy of generated contracts is critical: incorrect clauses, missing statutory requirements, or inconsistent terms can create legal liability. Legal review before issuance is mandatory. GDPR applies to candidate personal data used in contract generation. Works council information rights may apply to standardised employment contract templates.

Assessment

Agent Readiness 78-85%
Governance Complexity 31-38%
Economic Impact 61-68%
Lighthouse Effect 36-43%
Implementation Complexity 28-35%
Transaction Volume Weekly

Prerequisites

  • Contract templates per position type, jurisdiction, and employee category
  • Clause library with jurisdiction-specific legal requirements
  • Collective agreement reference database
  • Offer approval data from recruiting or compensation process
  • Legal review workflow
  • Document signing platform for contract execution
  • Template version management and change control

Infrastructure Contribution

The Contract & Offer Generation Agent builds the template management and conditional clause assembly infrastructure that the HR Document Management Agent and Policy Document Agent leverage. The pattern of jurisdiction-specific content selection from a parameterised clause library is reusable across all legally sensitive document generation. Builds Decision Logging and Audit Trail used by the Decision Layer for traceability and challengeability of every decision.

What this assessment contains: 9 slides for your leadership team

Personalised with your numbers. Generated in 2 minutes directly in your browser. No upload, no login.

  1. 1

    Title slide - Process name, decision points, automation potential

  2. 2

    Executive summary - FTE freed, cost per transaction before/after, break-even date, cost of waiting

  3. 3

    Current state - Transaction volume, error costs, growth scenario with FTE comparison

  4. 4

    Solution architecture - Human - rules engine - AI agent with specific decision points

  5. 5

    Governance - EU AI Act, works council, audit trail - with traffic light status

  6. 6

    Risk analysis - 5 risks with likelihood, impact and mitigation

  7. 7

    Roadmap - 3-phase plan with concrete calendar dates and Go/No-Go

  8. 8

    Business case - 3-scenario comparison (do nothing/hire/automate) plus 3×3 sensitivity matrix

  9. 9

    Discussion proposal - Concrete next steps with timeline and responsibilities

Includes: 3-scenario comparison

Do nothing vs. new hire vs. automation - with your salary level, your error rate and your growth plan. The one slide your CFO wants to see first.

Show calculation methodology

Hourly rate: Annual salary (your input) × 1.3 employer burden ÷ 1,720 annual work hours

Savings: Transactions × 12 × automation rate × minutes/transaction × hourly rate × economic factor

Quality ROI: Error reduction × transactions × 12 × EUR 260/error (APQC Open Standards Benchmarking)

FTE: Saved hours ÷ 1,720 annual work hours

Break-Even: Benchmark investment ÷ monthly combined savings (efficiency + quality)

New hire: Annual salary × 1.3 + EUR 12,000 recruiting per FTE

All data stays in your browser. Nothing is transmitted to any server.

Contract & Offer Generation Agent

Initial assessment for your leadership team

A thorough initial assessment in 2 minutes - with your numbers, your risk profile and industry benchmarks. No vendor logo, no sales pitch.

30K120K
1%15%

All data stays in your browser. Nothing is transmitted.

Frequently Asked Questions

Does the agent replace legal review of contracts?

No. The agent generates a complete draft from approved templates and verified data, but legal review before issuance is always a human step. The agent reduces the legal reviewer's workload by producing consistently structured, pre-validated drafts.

How does the agent handle non-standard contract terms?

Non-standard terms (special clauses, individual negotiations, executive arrangements) are flagged during generation and require additional legal review. The agent populates the standard elements and marks sections requiring manual attention.

What Happens Next?

1

30 minutes

Initial call

We analyse your process and identify the optimal starting point.

2

1 week

Discover

Mapping your decision logic. Rule sets documented, Decision Layer designed.

3

3-4 weeks

Build

Production agent in your infrastructure. Governance, audit trail, cert-ready from day 1.

4

12-18 months

Self-sufficient

Full access to source code, prompts and rule versions. No vendor lock-in.

Implement This Agent?

We assess your process landscape and show how this agent fits into your infrastructure.