# AI use cases for Dossier (AienTech/dossier) Repo: [AienTech/dossier](https://github.com/AienTech/dossier) | Use cases: 4 | Page: https://dedupedai.com/use-cases/aientech-dossier/ Dossier is a self-hosted job search app that keeps one career profile and drafts a tailored resume and cover letter for each job, then tracks each application. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Draft a tailored resume and cover letter for one posting: https://dedupedai.com/use-cases/aientech-dossier/tailor-resume-for-one-job-posting/ - Get a daily shortlist of scored job postings: https://dedupedai.com/use-cases/aientech-dossier/run-daily-job-search-with-agent/ - Track every application and interview in one place: https://dedupedai.com/use-cases/aientech-dossier/track-applications-from-draft-to-offer/ - Send applications from Gmail and draft replies to employers: https://dedupedai.com/use-cases/aientech-dossier/send-applications-and-answer-replies-via-gmail/ ## How to draft a tailored resume and cover letter for one posting with Dossier Repo: [AienTech/dossier](https://github.com/AienTech/dossier) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Paste a job posting and get a resume and cover letter built only from your profile facts. **Who it is for:** A job seeker who has a specific posting open and needs a resume and cover letter that match it, without inventing experience. **The problem:** Rewriting the same resume for every posting takes hours, and generic drafts miss what the employer asks for. **The outcome:** A tailored resume and cover letter as PDFs, a match view showing which requirements your profile covers, and a list of gaps the posting asks for that your profile does not have. ### Steps 1. Fetch the Compose file: `curl -fsSL -o compose.yml https://raw.githubusercontent.com/AienTech/dossier/main/compose.production.yml` 2. Create the secrets in `.env` with `echo "POSTGRES_PASSWORD=$(openssl rand -hex 24)" > .env` and `echo "DOSSIER_SECRET=$(openssl rand -base64 32)" >> .env` 3. Create your password hash with `docker run --rm -it --platform linux/amd64 ghcr.io/aientech/dossier hash-password`, then add the printed line to `.env` as `DOSSIER_PASSWORD=argon2id:…` 4. Start Dossier with `docker compose up -d`, open http://localhost:3000, sign in, and choose a model in Settings → AI provider 5. Fill in your profile, then paste a posting under New application and review the drafts and the gaps before you download the PDFs ### Prompt to paste into your agent ```text Using the AienTech/dossier repo, follow its README to start the app with Docker Compose on this machine and open http://localhost:3000. Paste the posting text from into New application and report the match summary and the list of gaps. Verify that every resume line traces to a fact in the profile before reporting success. ``` ### Caveat The first start downloads an image of about 1.7 GB, and drafts take a few seconds to a few minutes depending on the AI model you choose. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/aientech-dossier/tailor-resume-for-one-job-posting/ ## How to get a daily shortlist of scored job postings with Dossier Repo: [AienTech/dossier](https://github.com/AienTech/dossier) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Let the optional job agent search once a day and keep the best matches for your review. **Who it is for:** A job seeker who wants new relevant postings checked against their profile without searching every day by hand. **The problem:** Checking several job boards every day is slow, and most postings are not a good fit. **The outcome:** A daily shortlist on the Agent screen, with each new posting scored against your profile and the reasons given. Optional tailored drafts wait for your review. ### Steps 1. Start Dossier as described in its README with `docker compose up -d`, then sign in at http://localhost:3000 2. Choose a job source in Settings, using JSearch, Adzuna or the Bundesagentur für Arbeit, as described in the wiki page Choosing a job source 3. Enable the job agent and set the search you want it to run once a day 4. Open the Agent screen each day, read the scores and reasons, and save or dismiss each posting 5. Open Find jobs to score any posting by hand against your profile (inferred, check the README) ### Prompt to paste into your agent ```text Using the AienTech/dossier repo, set up its job agent with the job source and the search . Return the top postings from the Agent screen with their scores and reasons. Verify that the agent has not sent or applied to anything, since the README says it never does. ``` ### Caveat The job agent only runs the search you set and keeps results for your review, so you still apply yourself and the README does not describe how to create the job source accounts. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/aientech-dossier/run-daily-job-search-with-agent/ ## How to track every application and interview in one place with Dossier Repo: [AienTech/dossier](https://github.com/AienTech/dossier) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README See each application on a board or table and a dashboard with your funnel and upcoming interviews. **Who it is for:** A job seeker running many applications at once who loses track of status, deadlines and interviews. **The problem:** Applications spread across email, spreadsheets and job boards make it hard to see what needs follow-up. **The outcome:** A board and table of every application from draft to offer, and a dashboard showing your funnel for the last 30 days, 90 days or all time, with a week-by-week chart and upcoming interviews. ### Steps 1. Start Dossier with `docker compose up -d` and sign in at http://localhost:3000 2. Create an application for each job from New application, or from a posting you saved in Find jobs 3. Move each application across the board as its status changes, or edit it in the table 4. Open the dashboard and pick the funnel range you want: last 30 days, 90 days or all time 5. Export your data as one file from the app regularly, using its export feature ### Prompt to paste into your agent ```text Using the AienTech/dossier repo, after it is running at http://localhost:3000, read the applications on the board and the dashboard funnel for the last 30 days. Return a short list of applications with a status and the next interview date. Verify the counts match the number of applications shown on the table view. ``` ### Caveat Dossier is desktop only and single user, so it works best in a laptop or desktop browser with one password and one profile. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/aientech-dossier/track-applications-from-draft-to-offer/ ## How to send applications from Gmail and draft replies to employers with Dossier Repo: [AienTech/dossier](https://github.com/AienTech/dossier) | Difficulty: Advanced | Time: 90 minutes | Basis: From the README Send each application from your own address with its PDFs, then draft answers to employer replies. **Who it is for:** A job seeker who wants applications sent from their own Gmail address and replies handled in the same app. **The problem:** Switching between the job search tool and Gmail to send PDFs and answer employers slows down every application. **The outcome:** An application email from your own address with the resume and cover letter PDFs attached, replies shown next to each application, and drafted answers you confirm before anything is sent. ### Steps 1. Create your own Google OAuth client and follow the wiki page Connecting Gmail and Calendar, then enter it in Settings → Google, or set DOSSIER_GOOGLE_CLIENT_ID and DOSSIER_GOOGLE_CLIENT_SECRET 2. Start Dossier with `docker compose up -d` and sign in at http://localhost:3000 3. Open an application and review the email Dossier prepared for the address the posting names 4. Confirm the email to send it with the PDFs attached from your own Gmail address 5. When an employer replies, let the AI read it and review the drafted answer, offering interview times you are free ### Prompt to paste into your agent ```text Using the AienTech/dossier repo, connect Gmail with the Google OAuth client and open the application for . Return the prepared email and any employer reply with the drafted answer. Verify that nothing is sent until you confirm it, as the README states. ``` ### Caveat Gmail and Calendar are optional and need your own Google OAuth client, so the README does not claim a simple one-click connection. Risk, credentials: The Google OAuth client ID and secret let Dossier send email from your Gmail address, so store them only in your own Dossier settings or .env file and never share them. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/aientech-dossier/send-applications-and-answer-replies-via-gmail/