As of 13 August 2026, AI can choose which projects to include in your freelance portfolio.

What to actually do

1. Use a tool built for this

   The route this page recommends

2. Do it yourself

   Second choice

   A chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.

   How to actually do it

   1. Open a blank document and write the freelance service, target clients and type of work you want to win.
   2. Gather one factual entry for every possible project, including the problem, your role, work completed, outcome, evidence you can show and any confidentiality limits.
   3. Remove or anonymise client names, personal data and commercially confidential details before pasting the entries into a chatbot.
   4. Paste the prompt and supply the service, positioning, portfolio limit and project entries in the marked sections.
   5. Compare the proposed rankings and reasons against your original project records, correcting any invented or overstated claim.
   6. Choose the final projects and order, then rewrite each project description so it accurately shows your contribution and uses only evidence you can publish.

   Prompt

   Help me choose which projects to include in my freelance portfolio. Use only the information I provide and do not invent clients, results, responsibilities, tools, dates or figures.
   
   My intended freelance service and target clients:
   [DESCRIBE THE SERVICE AND CLIENTS]
   
   The impression I want the portfolio to create:
   [DESCRIBE THE POSITIONING]
   
   Portfolio limits:
   [NUMBER OF PROJECTS, PAGE OR WEBSITE LIMITS, AND ANY CONFIDENTIALITY RULES]
   
   Projects:
   [FOR EACH PROJECT, INCLUDE THE PROJECT NAME, CLIENT TYPE OR ANONYMOUS LABEL, PROBLEM, MY ROLE, WORK COMPLETED, TOOLS OR METHODS, OUTCOME, EVIDENCE I CAN SHOW, AND ANY CONFIDENTIALITY LIMITS]
   
   For each project, score its fit with my target clients, strength of evidence, clarity of my contribution, distinctiveness and risk of confusing the offer. Use low, medium or high rather than inventing numerical scores. Separate facts from inferences and flag missing information.
   
   Then provide:
   1. A ranked shortlist that fits the portfolio limits.
   2. A short reason for including or excluding every project.
   3. The strongest order for the selected projects.
   4. Any project that needs a better description, proof or anonymisation before publication.
   5. Three specific questions I should answer before making the final choice.
   Do not make the final decision for me. End with a concise recommendation stating what the evidence supports and what remains a matter of personal judgement.

   Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.

3. Hand it to a person

   The distant third

   A person who owns the outcome does this end to end, worth it when the failure is dear.