Playbooks·HR / People·HR01
Job Description Builder
Turn hiring manager inputs into a role brief, approved job description, and must-have criteria pack
GenAI impact
What this playbook delivers
Projected against the same workflow run manually, end to end
- 47%
- Faster than the manual baseline
- ~2.1hrs
- Saved per cycle
- 3
- Source-of-truth artifacts
Estimated impact based on 1 open role with 4 input documents · Real savings vary with team volume and current process maturity
The challenge
Why the workflow breaks
Three patterns show up across teams using GenAI without a shared workflow
Inflated requirements
Postings ask for years of experience, tools, or degrees that aren't truly necessary — narrowing the candidate pool and creating misleading screening standards.
Criteria confusion
When must-haves and nice-to-haves are mixed, reviewers evaluate candidates inconsistently, and that inconsistency travels into shortlisting, interviews, and offers.
Unsupported language
GenAI can produce confident phrasing about benefits, growth paths, or culture that the organization can't actually support once the candidate is in the door.
Where GenAI helps
From confused intake to source-of-truth artifacts
Here’s what changes when the team uses this playbook
From
To
Hiring managers describe the role in shorthand
Role Requirements Brief becomes the source of truth
Must-haves and nice-to-haves get mixed in the posting
Must-Have Criteria separates non-negotiables before drafting
JDs claim benefits and culture nobody approved
Approved Job Description uses only reviewed claims
Each recruiter writes JDs their own way
Same workflow, same checks, same artifacts
How the playbook works
3 phases, one source of truth
Each phase produces an artifact the next phase builds on
Extract & separate
AI pulls verifiable must-haves from the intake notes and explicitly excludes nice-to-have preferences before any drafting begins.
Build brief
Approved criteria become a structured Role Requirements Brief — responsibilities, capabilities, and evaluation criteria that recruiters and hiring managers can both rely on.
Draft & approve
The brief drives the Approved Job Description — candidate-facing copy tied directly to source-of-truth requirements with explicit verification gates before posting.
What you’ll produce
Sample artifacts from the workflow
Interim and final deliverables you can review and download
Must-Have Criteria
Evidence-backed list of non-negotiable role criteria, separating must-haves from preferences and linking each requirement to business context.
Role Requirements Brief
Structured role brief translating workforce context, benchmarks, and legacy language into clear responsibilities, capabilities, and evaluation criteria.
Approved Job Description
Final job description with aligned responsibilities, requirements, success profile, and hiring-ready language for review and posting.
Built into the workflow
Quality and risk checks at every step
Verification, data handling, and definition-of-done rules are part of the playbook — not afterthoughts
Quality
The dedicated extraction-then-verification sequence enforces strict must-have/nice-to-have separation, producing job descriptions grounded in objectively measurable criteria rather than inflated requirement wish lists.
Risk handling
Governed data-handling rules prevent raw compensation benchmarks from being pasted into GenAI prompts, while mandatory criteria verification blocks hallucinated or unverified requirements from reaching external job postings.
LIVE ONLINE LABS
Join a live Lab for this workflow
An AGASI expert runs your team through the Job Description Builder workflow on your own real work — so you leave with the method, not a recording.
Built around this exact playbook
You internalise the method, not a recording.
Facilitated by an AGASI expert
Live online coaching on prompts, verification, and where the workflow tends to break.
Public or private formats
Join an open public Lab, or bring it in-house for your team.
Get started
Run the Job Description Builder playbook
Step-by-step prompts, role guidance, data-handling notes, and definition-of-done checks for every step of the workflow