How to Build Job Posts and JDs With an Agent
A practical guide to drafting role-specific job descriptions and public job posts with market research and approval.
Founder, Task Machine
Building a job post and job description means turning a role brief into two connected artifacts: an internal description that defines the work and a public post that helps the right candidates self-select. The best version is specific about outcomes, honest about constraints, and careful about language that filters people out for the wrong reasons.
This work matters because the post sets the top of the hiring funnel. A vague role attracts volume. A specific role attracts better matches, gives screeners a clearer bar, and reduces disagreement later in the process.
Why job posts quietly underperform
Most weak posts fail before anyone applies. They describe a fantasy role, stack too many must-haves, hide compensation even when it should be stated, or use coded language that makes qualified candidates opt out.
The bundle's method starts with the role, not the copy. It confirms responsibilities, must-haves, location, compensation notes, and team context, then researches comparable live postings so the draft is market-aware. The agent self-critiques before approval, with a bias-language check and a cap on true requirements.
What the manual process looks like
Done by hand, a careful job-post build has six steps:
- Gather the role title, team, reporting line, employment type, location policy, and compensation notes.
- Define 3 to 5 owned responsibilities and the outcomes expected in the first 6 to 12 months.
- Separate genuine must-haves from nice-to-haves, keeping must-haves tight.
- Research 3 to 5 comparable live postings and compare scope, qualifications, and framing.
- Draft the structured job description and the public post in employer-brand voice.
- Check the draft for inclusive language, inflated requirements, vague responsibilities, and compensation review needs.
The skipped step is usually research or self-critique. That is how a post ends up looking like every other post while still carrying accidental bias.
What an agent can automate
An agent can assemble the hiring packet while leaving the final hiring and publishing decisions with people:
- Extract the role brief. The agent turns a messy brief into title, team context, responsibilities, must-haves, nice-to-haves, location, and compensation notes.
- Research comparable roles. It reads 3 to 5 live postings where web search is available and notes common responsibilities, qualifications, and framing.
- Structure the JD. It builds mission, responsibilities, must-haves, nice-to-haves, and what success looks like over the first 6 to 12 months.
- Write the public post. It leads with mission and impact, uses "you", and mirrors the employer-brand voice document.
- Self-critique for bias and clarity. It replaces coded language, trims excessive requirements, turns vague chores into owned outcomes, and flags compensation for HR review.
The agent does not screen applicants, rank people, invent compensation, or publish the post.
The guardrails that make it safe
Hiring content affects who applies, so the guardrails focus on scope, language, and approval. The agent must omit compensation if it was not provided, flag that compensation needs HR sign-off, and note that salary ranges may be legally required in some jurisdictions.
The workflow also forces a self-critique before approval. That critique catches coded language, inflated must-haves, unclear responsibilities, and weak openings. The final packet waits for human approval before any post is published or sent to a job board.
Set it up in Task Machine
The Job post & JD builder playbook installs the People Agent, the Research, structure, write, self-critique, approve workflow, the employer-brand voice document, and three hiring skills. Setup takes a few minutes. You need a Task Machine workspace and permission to install playbooks (workspace owners have it). Web search improves comparable-posting research, but the workflow can draft from the role brief and employer-brand voice document when research tools are unavailable.
1. Find the playbook
Open Playbooks in your workspace and search for "job post", or browse the People category. The card shows the People Agent, workflow, employer-brand document, and hiring skills it creates.

2. Preview what it installs
Preview & install opens the install preview before anything is created. Review the People Agent, the Research, structure, write, self-critique, approve workflow, the employer-brand voice document, and the job-post, job-description, and recruiting-pipeline skills.

3. Define the role brief
Start setup asks for the role title, team and role context, must-have skills, and compensation or location notes. Strong answers name the team, reporting line, core outcomes, real constraints, and whether compensation needs HR review before publication.

4. Generate and review
Generate customized playbook applies your role brief to the agent, workflow, document, and skills. In the review step, check that the workflow researches comparable postings, structures the JD, writes the post, self-critiques for bias, and waits for approval.

5. Install
Install customized playbook creates the hiring packet workflow in your workspace. Two follow-ups arrive in your inbox: set employer-brand voice and start Research, structure, write, self-critique, approve. The first run researches comparable postings where available, drafts the JD and public post, critiques them, and waits for approval before publishing.

What good looks like
A strong hiring packet gives candidates and reviewers the same picture:
- Responsibilities are outcomes. The post describes owned work, not a grab bag of tasks.
- Must-haves are limited. Requirements are real filters, not every skill someone might use.
- The post is market-aware. Comparable postings inform scope and language without being copied.
- Approval catches risk. Compensation, inclusive language, and external publishing all get human review.
Common questions
Can the agent publish the role to a job board? No. It prepares the JD and public post and waits for approval. Publishing stays with the hiring owner.
What if compensation is not known yet? The agent should omit the range rather than invent one and flag that compensation needs HR sign-off before publication.
Does this replace recruiting judgment? No. It prepares a better packet. Hiring criteria, candidate evaluation, and final approval stay with people.
Can it use an existing company JD template? Yes. If a prior JD or template is available, the agent uses it as the structural baseline and surfaces gaps before adding new sections.