# AI use cases for Franco (GortexAI/franco) Repo: [GortexAI/franco](https://github.com/GortexAI/franco) | Use cases: 3 | Page: https://dedupedai.com/use-cases/gortexai-franco/ Franco is an outbound sales agent that runs on your own machine and uses the Claude Code or Codex subscription you already pay for. It works through a list of accounts, sends short email sequences from your own mailbox, reads replies and handles them. It has three modes: generated outreach, approved copy sent word for word, and Raad funnels. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Send approved email sequences to a list of researched accounts: https://dedupedai.com/use-cases/gortexai-franco/send-approved-email-sequences-to-researched-accounts/ - Import your contact and do-not-contact lists from CSV: https://dedupedai.com/use-cases/gortexai-franco/import-a-contact-list-and-suppressions-from-csv/ - Run Franco from the published container image: https://dedupedai.com/use-cases/gortexai-franco/run-franco-on-a-chatgpt-plan-in-docker/ ## How to send approved email sequences to a list of researched accounts with Franco Repo: [GortexAI/franco](https://github.com/GortexAI/franco) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Import a CSV of accounts with one sourced observation each and let Franco send your signed-off sequence word for word. **Who it is for:** A founder whose outbound copy has been approved and must go out exactly as written. **The problem:** Sending a multi-step sequence by hand, on business days, with replies and opt-outs tracked, eats hours each week. **The outcome:** A running sequence per account from your own mailbox, with no model writing the emails. ### Steps 1. Install with `pipx install franco`, then run `franco init ~/franco && cd ~/franco` 2. Set outreach mode to templates in Franco.local.yaml and define your campaign steps with the merge fields 3. Run `franco import --template --kind accounts > accounts.csv` and fill in one row per account 4. Check the file with `franco import accounts.csv --dry-run`, then import it 5. Start the loop with `franco run`; new campaigns start in preview ### Prompt to paste into your agent ```text Set up GortexAI/franco in approved copy mode: create the home folder, add my campaign to franco.local.yaml, validate with a dry run and stop before anything is sent so I can review the preview. ``` ### Caveat This card is written from the GortexAI/franco README, not from a test run by Deduped. Before you start, make sure you have Python 3.11 or newer. Check the repo for newer instructions before you rely on these steps. Risk, outbound-email: Franco sends real email from your mailbox; follow the compliance settings (footer, postal address, opt-outs) and local anti-spam law. 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/gortexai-franco/send-approved-email-sequences-to-researched-accounts/ ## How to import your contact and do-not-contact lists from CSV with Franco Repo: [GortexAI/franco](https://github.com/GortexAI/franco) | Difficulty: Beginner | Time: 20 minutes | Basis: From the README Bring existing spreadsheets into Franco and make sure suppressed addresses and domains are never emailed. **Who it is for:** A sales lead moving an existing prospect spreadsheet and do-not-contact list into an automated tool. **The problem:** Typing contacts in one by one is slow, and a missed opt-out list can send mail to people who asked not to hear from you. **The outcome:** Contacts imported and checked row by row, with suppressions loaded before any campaign runs. ### Steps 1. Get a template with `franco import --template --kind contacts > contacts.csv` 2. Validate with `franco import contacts.csv --kind contacts --dry-run`; nothing is written 3. Import and verify emails with `franco import contacts.csv --kind contacts --verify` 4. Load your do-not-contact list with `franco suppress import do_not_contact.csv` 5. Or use the Import CSV panel on the dashboard's Contacts tab ### Prompt to paste into your agent ```text Import into GortexAI/franco as contacts with a dry run first, report every rejected row and its reason, then load as suppressions before importing for real. ``` ### Caveat --verify spends one verification credit per address that is not already marked verified. 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/gortexai-franco/import-a-contact-list-and-suppressions-from-csv/ ## How to run Franco from the published container image with Franco Repo: [GortexAI/franco](https://github.com/GortexAI/franco) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Use the prebuilt image that already includes Chromium and the Claude CLI instead of a local Python install. **Who it is for:** An operator who wants Franco on a Linux server, isolated from their laptop. **The problem:** Installing Python, Chromium and the agent CLI by hand on a server is fiddly and easy to get wrong. **The outcome:** Franco running in Docker with your data folder, .env and config mounted, and its dashboard reachable. ### Steps 1. Run `docker pull ghcr.io/gortexai/franco:latest` 2. Put your settings in Franco.local.yaml and your keys in .env 3. Start it with `docker compose up -d` 4. Optionally verify the image with `gh attestation verify oci://ghcr.io/gortexai/franco:latest --owner GortexAI` 5. Open the dashboard and keep new campaigns in preview until you have read the first emails ### Prompt to paste into your agent ```text Deploy GortexAI/franco with the published ghcr.io image and docker compose on , mount ./data, .env and my config, verify the image attestation, and confirm the dashboard loads. ``` ### Caveat This card is written from the GortexAI/franco README, not from a test run by Deduped. Before you start, make sure you have Python 3.11 or newer. Check the repo for newer instructions before you rely on these steps. 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/gortexai-franco/run-franco-on-a-chatgpt-plan-in-docker/