CV bullet points from your responsibilities
Achievement-shaped bullets built only from things you actually did. Written for ChatGPT, free to copy, with every placeholder explained below.
The prompt
## Role
You write CV bullets that state outcomes, using only facts the candidate supplied.
## Context
Role: {{job_title}} at {{company_type}}
What I did day to day: {{responsibilities}}
Things that changed because of me: {{outcomes}}
Numbers I actually know: {{metrics}}
Job I am applying for: {{target_role}}
## Task
Write CV bullet points for this role.
## Constraints
- Use only the facts above. Invent no metrics, no percentages, no team sizes.
- Where I gave no number, write the bullet without one rather than estimating.
- Structure: what I did, how, and what changed as a result.
- Lead with the outcome, not the task, wherever an outcome exists.
- Weight toward what matters for the target role.
- No "responsible for", no "helped with", no "utilised".
- 4–6 bullets, each one line.
## Output format
The bullets, then a list of any missing numbers worth finding before applying.
Now write the bullets.Open this in the prompt builder to adapt it, score it, and re-render it for a different model.
What to replace
| Placeholder | What to put there |
|---|---|
| {{job_title}} | Your title. |
| {{company_type}} | Size and sector for context. |
| {{responsibilities}} | What you actually did. |
| {{outcomes}} | What changed because of you. |
| {{metrics}} | Only numbers you genuinely know. |
| {{target_role}} | The job you are applying for. |
Why this prompt works
- No invented metrics
- A CV with a fabricated percentage is a liability in an interview. The prompt has to forbid it explicitly, because achievement-shaped bullets invite invented numbers.
- Missing numbers listed
- Turns "I do not have data" into a short research task before you apply.
- Banned filler verbs
- "Responsible for" describes a job description, not an achievement, and is the default phrasing a model reaches for.
More prompts
- Interview answers from your real experience — STAR answers built from what you actually did, with the follow-ups you will be asked.
- Blog post from an outline — Turn a rough outline into a full draft that keeps your structure and does not pad.
- Rewrite for clarity without changing meaning — Tighten prose while keeping the author's voice and every factual claim intact.
- Summarise a document without distorting it — A summary that separates what the source says from what it implies.
- Code review for correctness only — Findings with a triggering input, ranked by severity — and permission to find nothing.
- Debug from an error and stack trace — Ranked hypotheses with a test for each, instead of one confident guess.
Browse the full prompt library, all career & job search prompts, or read the guides.