Job Posting Agent
Publish compliant, consistent job postings - across every channel, every language.
Creates compliant job postings from requirement profiles and coordinates multi-channel publication. EU AI Act high-risk classification applies.
Analyse your process
Extract job profile via AI, anti-discrimination check via rules, channel routing
The agent generates job adverts via AI from the job profile, checks wording deterministically for anti-discrimination-compliant language against a prohibited-terms list and routes publication rule-based to the most effective channels per target group - approval remains with HR.
Outcome: With 30 percent of applicants experiencing discriminatory wording as exclusion and typical anti-discrimination claim risks of 3 monthly salaries, the lever lies in consistent language assessment before publication.
The architecture addresses the conflict between reach pressure and legal precision:
Three recruiters, three wordings, three discrimination risks
Three recruiters, three phrasings, three risk levels. That is the reality of job postings when twenty positions need to be filled simultaneously. One posting speaks of a “young, dynamic team” - an anti-discrimination violation that can cost up to three months’ gross salary in compensation before a labour tribunal. The next omits the salary range that becomes mandatory under the EU Pay Transparency Directive by June 2026. The third is technically correct but so generic it disappears among thousands of listings. And all three were manually posted on three different channels because nobody knows which channel delivers the best return for which position.
This is not a quality problem of individual recruiters. It is a system problem.
The Triple Risk of Every Single Posting
Job postings are the most vulnerable artefact in the entire recruiting process. They are simultaneously a legal document, a budget item, and a calling card - and in most organisations, none of these three is systematically managed.
Legal risk: anti-discrimination law today, pay transparency tomorrow. Every discriminatory phrase opens a liability case. “Native-level German” instead of “excellent command of German” - the difference is an anti-discrimination claim. With fifty open positions per year and an average of twenty applications per position, a single systematic phrasing error can trigger five-figure damages. From June 2026, the EU Pay Transparency Directive tightens requirements further: every job posting must include a concrete salary range. Omitting this information or handling it inconsistently risks sanctions and erodes candidate trust before the first conversation takes place. (US: state-level pay transparency laws in Colorado, New York, California, and Washington already mandate salary ranges in postings.)
Cost problem: scatter without control. The average cost per hire across Europe ranges from EUR 4,700 to EUR 5,500 (USD 5,200-6,000) - depending on source and industry. A significant portion flows into job postings running on the wrong channels. Single listings on job boards cost EUR 1,000 to EUR 1,300 per posting. Anyone running five channels simultaneously easily spends over EUR 5,000 per position on publishing alone - without knowing which channel delivers qualified applications and which only generates clicks.
Quality problem: inconsistency as an employer brand killer. When the same position appears on the market in three variants - once with bullet points, once as flowing text, once with outdated benefits - it signals organisational randomness. With an average vacancy duration of 164 days for specialist positions in parts of Europe, every day counts when a poorly worded posting attracts the wrong candidates or repels the right ones.
Where Manual Processes Fail
The typical process chain for a job posting looks like this:
Hiring department Recruiting Approval
----------------- ---------- --------
Requirement ──> Write text ──> Review
(often informal) (varies by (usually content
recruiter) only, not legal)
|
v
Manual posting
(3-5 portals,
copy & paste)
Every arrow in this diagram is an error source. The requirement arrives as an unstructured email. The text is written under time pressure without consulting the employer brand guidelines. The review covers content but not legal compliance. The posting is published manually - and performance is never systematically evaluated.
Three validation layers gate every posting before a recruiter sees it
A Job Posting Agent does not replace the recruiter. It replaces the randomness. From a structured requirement profile, a posting draft is generated that passes through three validation layers before a human sees it:
First layer: anti-discrimination compliance. Every formulation is checked against a compliance catalogue - gender-neutral language, no age discrimination, no indirect discrimination through language requirements. This is not a stylistic suggestion but a hard rule. What does not pass does not proceed.
Second layer: pay transparency. Salary ranges are drawn from the stored compensation bands and formatted to the prescribed standard. Consistent across all postings, all channels, all languages. No deviation, no omission.
Third layer: channel optimisation. Which portals deliver the best conversion rates for which position, region, and seniority level is decided by rules - not by gut feeling. Performance data flows back and improves channel selection for the next posting.
Only then does the recruiter see the draft. And reviews what only a human can review: does the tone fit? Does the description match the actual team culture? Are there technical nuances that only someone who has spoken with the hiring department knows?
What This Means for Recruiting Leadership
The question is not whether job postings will be automated. The question is whether they will be treated as infrastructure - with governance, version control, and an Audit Trail - or whether they remain random products that become a liability at the next anti-discrimination claim or the first pay transparency audit.
The difference between an organisation that has solved this and one that has not shows itself not in the individual posting text. It shows itself in the ability to answer the question “How do you ensure all your job postings comply with the Pay Transparency Directive?” with a systemic response rather than “Each recruiter checks for themselves.”
A Decision Layer makes every step traceable: which rules were applied, which checks passed or failed, who approved. Not as retrospective documentation, but as an integral part of the process. For a high-risk system under the EU AI Act - and that is precisely what an agent is that influences who sees job postings - this traceability is not optional. It is mandatory.
Micro-Decision Table
Who decides in this agent?
8 decision steps, split by decider
Receive requirement profile Parse job requirements and posting parameters Rules Engine
Structured intake from job profile system
Decision Record
Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.
Generate posting content Create job posting text from requirement profile and templates AI Agent
AI-generated content following brand and format guidelines
Decision Record
Challengeable: Yes - fully documented, reviewable by humans, objection via formal process.
Check anti-discrimination compliance Scan posting for potentially discriminatory language AI Agent
Language analysis against anti-discrimination compliance rules
Decision Record
Challengeable: Yes - fully documented, reviewable by humans, objection via formal process.
Verify pay transparency requirements Ensure salary range is included per applicable directive Rules Engine
Rule-based check against Pay Transparency Directive requirements
Decision Record
Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.
Review and approve posting Human review of generated content before publication Human
Recruiter or hiring manager confirms content accuracy and tone
Decision Record
Challengeable: Yes - via manager, works council, or formal objection process.
Select distribution channels Determine which job boards and platforms to publish on Rules Engine
Channel selection rules per role type, location, and budget
Decision Record
Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.
Format per channel requirements Adapt posting to each channel's format and field requirements AI Agent
Automated formatting per channel specification
Decision Record
Challengeable: Yes - fully documented, reviewable by humans, objection via formal process.
Publish and track Distribute posting and monitor channel performance AI Agent
Automated publishing with response tracking per channel
Decision Record
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.
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 processGovernance Notes
Assessment
Prerequisites
- Structured job requirement profiles
- Brand and tone guidelines for job postings
- Anti-discrimination language guidelines per jurisdiction
- Pay transparency rules per applicable directive
- Job board integrations and API access
- EU AI Act conformity assessment for high-risk classification
- Posting approval workflow
Infrastructure Contribution
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
Title slide - Process name, decision points, automation potential
- 2
Executive summary - FTE freed, cost per transaction before/after, break-even date, cost of waiting
- 3
Current state - Transaction volume, error costs, growth scenario with FTE comparison
- 4
Solution architecture - Human - rules engine - AI agent with specific decision points
- 5
Governance - EU AI Act, works council, audit trail - with traffic light status
- 6
Risk analysis - 5 risks with likelihood, impact and mitigation
- 7
Roadmap - 3-phase plan with concrete calendar dates and Go/No-Go
- 8
Business case - 3-scenario comparison (do nothing/hire/automate) plus 3×3 sensitivity matrix
- 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.
Job Posting 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.
All data stays in your browser. Nothing is transmitted.
Related Pages
Related Agents
Candidate Screening Agent
Structure the screening process - with full EU AI Act compliance built in.
Executive Recruiting Agent
Board-level searches with full confidentiality and governance tracking.
Interview Scheduling Agent
Find the slot, book the room, send the invite - without the email ping-pong.
Frequently Asked Questions
Does the agent write job postings from scratch?
The agent generates posting content from structured requirement profiles using templates and guidelines. A human always reviews and approves the content before publication.
How does the agent handle salary ranges for pay transparency?
The agent checks whether the applicable jurisdiction requires salary range disclosure and validates that the posting includes the required information. It does not determine salary ranges - those come from the compensation structure.
What Happens Next?
30 minutes
Initial call
We analyse your process and identify the optimal starting point.
1 week
Discover
Mapping your decision logic. Rule sets documented, Decision Layer designed.
3-4 weeks
Build
Production agent in your infrastructure. Governance, audit trail, cert-ready from day 1.
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.