# AI use cases for Jev Social (socai-io/jev-social) Repo: [socai-io/jev-social](https://github.com/socai-io/jev-social) | Use cases: 4 | Page: https://dedupedai.com/use-cases/socai-io-jev-social/ Jev Social is an open-source, local-first research agent that runs read-only browser steps in your signed-in Chrome to produce source-cited reports from Instagram, TikTok, and LinkedIn. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Build a source-cited social research report: https://dedupedai.com/use-cases/socai-io-jev-social/cited-social-research-report/ - Let Codex run browser-grounded social research: https://dedupedai.com/use-cases/socai-io-jev-social/codex-social-research-skill/ - Capture a TikTok video with its media as evidence: https://dedupedai.com/use-cases/socai-io-jev-social/tiktok-video-evidence-with-media/ - Compare public LinkedIn profiles and companies: https://dedupedai.com/use-cases/socai-io-jev-social/linkedin-profile-company-comparison/ ## How to build a source-cited social research report with Jev Social Repo: [socai-io/jev-social](https://github.com/socai-io/jev-social) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Run a read-only research goal across Instagram, TikTok, or LinkedIn and get a cited Markdown report. **Who it is for:** A market researcher or analyst who needs to understand what people are posting about a topic on one or more social platforms. **The problem:** Manually reading social feeds is slow, and findings are hard to trace back to specific public posts or profiles. **The outcome:** A report.md where each accepted finding cites a captured source, plus a history of every operation Jev chose. ### Steps 1. Install Node 22 or newer and sign in to Instagram, TikTok, or LinkedIn in Chrome. 2. `npx github:socai-io/jev-social#v0.1.13 onboard` 3. `npx github:socai-io/jev-social#v0.1.13` 4. Enter a research goal naming the platform, for example: find handmade art on Instagram. 5. Open the downloaded report.md and check that each finding links to a captured source. ### Prompt to paste into your agent ```text Use the socai-io/jev-social repo to research on in my signed-in Chrome. Expected output: a source-cited report.md. Verify that every finding links to a captured source URL and that any login gate is reported as a partial result, not a success. ``` ### Caveat Login gates and step limits produce partial results, and report synthesis may incur OpenRouter usage unless OPENROUTER_REPORT_MODEL=off is set. Risk, credentials: Jev runs in the Chrome profile you select, so use a separate profile or test account for sensitive research. 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/socai-io-jev-social/cited-social-research-report/ ## How to let Codex run browser-grounded social research with Jev Social Repo: [socai-io/jev-social](https://github.com/socai-io/jev-social) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Install the Jev Social skill into Codex so it can run cited social research for you. **Who it is for:** A developer already working in Codex who wants social research done inside that agent session. **The problem:** Switching between an agent and a separate research tool breaks the workflow, and raw run output is hard to use. **The outcome:** Codex returns source-linked evidence instead of raw run JSON, using the read-only Jev Social workflow. ### Steps 1. Install GitHub CLI 2.101 or newer. 2. `gh skill install socai-io/jev-social jev-social@v0.1.13 --agent codex --scope user` 3. Confirm a current socai CLI is installed and Chrome is signed in to the target platform. 4. Ask Codex to research a specific goal on Instagram, TikTok, or LinkedIn. 5. Check that returned findings cite captured source URLs and that platform availability was checked. ### Prompt to paste into your agent ```text With the jev-social skill installed in Codex, research on using the local socai CLI. Expected output: a short evidence summary with captured source URLs. Verify that login-gated or failed steps are reported as partial results. ``` ### Caveat The skill pins the v0.1.13 release and requires GitHub CLI 2.101 or newer, so older GitHub CLI versions will not work. Risk, credentials: The skill drives your signed-in Chrome session, so use a separate profile or test account for sensitive research. 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/socai-io-jev-social/codex-social-research-skill/ ## How to capture a TikTok video with its media as evidence with Jev Social Repo: [socai-io/jev-social](https://github.com/socai-io/jev-social) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Read a selected TikTok video and save its media offline when your goal explicitly asks for it. **Who it is for:** A trust and safety or content analyst who needs a saved copy of a specific TikTok video with its metadata. **The problem:** Video pages change or disappear, and a reviewer needs a stable record tied to the original URL. **The outcome:** Captured metadata, a downloaded MP4, and a poster image stored by socai, with the media intent kept in the operation history. ### Steps 1. Install Node 22 or newer and sign in to TikTok in Chrome. 2. `npx github:socai-io/jev-social#v0.1.13 onboard` 3. `npx github:socai-io/jev-social#v0.1.13` 4. Write the goal so it explicitly requests an offline copy of the video, because media download runs only when the goal asks for it. 5. Review the socai evidence and downloaded media, which are stored separately from Jev checkpoints, and delete only what you no longer need. ### Prompt to paste into your agent ```text Use the socai-io/jev-social repo to read the TikTok video at and save an offline copy of its media, since the goal explicitly requests it. Expected output: metadata, an MP4, and a poster in the socai evidence store. Verify that the media download appears in the operation history and note any missing comments. ``` ### Caveat A recorded TikTok run captured media successfully but comments were unavailable, so partial results are normal. 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/socai-io-jev-social/tiktok-video-evidence-with-media/ ## How to compare public LinkedIn profiles and companies with Jev Social Repo: [socai-io/jev-social](https://github.com/socai-io/jev-social) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Search LinkedIn for people or companies and read selected profiles, companies, and posts with citations. **Who it is for:** A sales or business development lead who needs a cited comparison of public LinkedIn profiles and companies for one market segment. **The problem:** Checking each profile and company page by hand is slow, and the notes are hard to verify later. **The outcome:** A cited report covering the profiles, companies, and posts Jev selected, with the steps it took recorded. ### Steps 1. Install Node 22 or newer and sign in to LinkedIn in Chrome, ideally with a separate profile or test account. 2. `npx github:socai-io/jev-social#v0.1.13 onboard` 3. `npx github:socai-io/jev-social#v0.1.13` 4. Give a goal that names the segment and the kind of result you want, such as people, companies, or posts. 5. Verify each comparison point against its cited source before using it. ### Prompt to paste into your agent ```text Use the socai-io/jev-social repo to search LinkedIn for companies and people in my signed-in Chrome and produce a cited comparison. Expected output: a source-cited report.md. Verify that each claim links to a captured profile, company, or post and that login gates are marked as partial. ``` ### Caveat LinkedIn results depend on the login state and the live site, so the comparison may be partial on a given run. Risk, credentials: Jev reads LinkedIn through your signed-in Chrome session, so use a separate profile or test account to limit exposure. 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/socai-io-jev-social/linkedin-profile-company-comparison/