How to Build a Headcount Requisition Pack from a Budget Table
Reqs go wrong when they add an intern row and a London office the table never funded. Net-new is count minus filled. Nothing else.
The matching generator is the Headcount Requisition Pack from a Budget Table (No Invented Roles) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Ledger every budget row before drafting
Turn a pasted headcount budget table into requisition drafts. No invented roles, bands, or locations. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Entity and fiscal period: [Entity]
Pasted budget table (title, level, location, cost, count, cost center): [Table]
Hiring manager names I may use (or NONE): [Managers]
Target open dates I can prove (or NONE): [Dates]
What is already filled vs net-new: [Filled]
Comp notes I may copy (or NONE): [Comp]
What I must never claim: [Never]
Words I must not use: [Banned]
How many reqs to draft: [Count]
Approval chain I can prove (or NONE): [Approvals]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Net-new math, not wish-list roles
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Honesty ledger: every row in Table, managers, dates, filled counts, approvals. Forbidden: titles and locations not in Table.
- Net-new math: Count minus Filled per row. If Filled is missing, write NOT IN INPUTS rather than assuming zero.
- Req drafts: one per net-new seat up to Count. Title, level, location, cost center from Table only.
- Manager and open date: only Managers and Dates. Else NOT IN INPUTS.
- Comp: copy Comp notes only. Do not invent a band or equity.
- Approvals: only Approvals. Do not add CHRO if unnamed.
- What this is not: JD, offer letter, OKR. Say so.
- Compliance pass: quote Banned words, invented roles, invented locations. Cut them.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Leave manager blank when unnamed
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- Requisition pack from a budget table. Not a JD, not an offer, not OKRs.
- Never invent a role, band, location, or start date.
- Do not exceed net-new seats implied by Table and Filled.
- If Managers is NONE, leave hiring manager blank.
- No emojis.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Not a JD, not an offer, not OKRs
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (headcount requisition pack, hc budget to requisitions, no invented roles) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.