Fictional data. The score assesses the CV against the selected level.
Back to homepageSample CV report
Fictional example · AI / LLM Engineer
The project, personal contribution and checks support a first-job application.
Based on the CV's content and structure. This is not an assessment of the person.
The score describes CV quality against the application target. First job in tech.
How the CV shows preparation for a first role
The project, personal contribution and checks support a first-job application.
What supports this impression
What creates doubt
What they may ask
Why this question?
Clarifying the documented check.
FIRST 20 SECONDS
After 5 seconds
AI / LLM Engineer
After 10 seconds
The project, personal contribution and checks support a first-job application.
After 20 seconds
The description identifies 20 test questions and retrieval improvements after incorrect answers. API integration does not mean model training.
This is a simulation of the first impression created by the document, not a real hiring decision or a prediction for a specific application.
Evidence of preparation for the role
The assistant cites sources and refuses answers when no source is available.
74/100The CV separates personal work from course instructions or help from others.
74/100The description identifies 20 test questions and retrieval improvements after incorrect answers. API integration does not mean model training.
74/100Citations, refusal and document isolation show decisions at project scale.
74/100Discussing errors with a mentor led to correcting the user filter.
74/100The summary does not highlight the concrete project
70/100What weakens the document — evidence before opinion
The summary does not highlight the concrete project
The summary does not highlight the concrete project
A concrete project makes the profile easier to recognise.
Move the project and personal contribution above the course or tool list, preserving its educational or personal context.
Goal: first job as an AI / LLM Engineer. Course project: a documentation assistant in Python. Following course instructions, connected a pretrained model API to retrieval from a vector database. Independently added source citations, refusal when no source is available and user document isolation. Prepared 20 test questions, including questions unanswered by the documentation; checked citations and improved retrieval after incorrect answers. Discussed incorrect answers with my mentor and corrected the user filter. Local project, no commercial experience. Did not train or fine-tune the model. Summary: interested in AI technologies. Courses: Python and LLMs.
Strong signals
The description identifies 20 test questions and retrieval improvements after incorrect answers. API integration does not mean model training.
Action plan
How to revise your CV
The report identifies what to clarify and improve. You choose the wording and are responsible for its accuracy.
- Establish the facts
Review the cited CV passages and specific advice. Identify your own work, the support you received and what you can confirm. Check anything you cannot remember.
- Revise in your own words
Clarify the description yourself using the recommendations. Include only true information. If the advice concerns something you have not done, do it before adding it to your CV.
- Recheck the new version
Read the whole CV, save the revised PDF or DOCX and upload it for another analysis. Compare findings and evidence as well as the score.
A clearer description does not guarantee a higher score. The score depends on the information shown in the new document.
What does your CV communicate?
See your free result and most important evidence.