Real AI agent use cases, with sources and setup prompts

Let your coding agent make images, video, speech and music from one CLI

saiitoshii points to gemini-api, a single binary that lets Claude Code, Codex or any shell agent generate images, video, TTS and music, saving files to disk and returning only the path.

See pricing page15 minIntermediateSource linked

Source

@saiitoshii on X · 2026-10-22

Written in our own words. Credit to the original author. Link checked 2026-10-24.

What they did

saiitoshii points to gemini-api, a single binary that lets Claude Code, Codex or any shell agent generate images, video, TTS and music, saving files to disk and returning only the path.

Result (as claimed)

Media generation inside agent workflows without extra glue code.

Tools they used

Gemini APIClaude CodeCodex

Cost: Pricing depends on the tools you pick; check each official pricing page.

Set it up

  1. Collect your inputs

    List what goes in (raw footage, script, topic list or audio) and the exact output you want, for example 5 vertical clips under 45 seconds. Put inputs in one folder.

  2. Set up the tools

    Open Gemini API, Claude Code, Codex. Connect accounts only where needed and note any per-minute or per-credit limits on the free plan before you start.

  3. Run one piece end to end

    Make a single output first. Check pacing, captions, voice and framing by watching it on a phone.

  4. Turn it into a repeatable recipe

    Save the prompts and settings that worked as a template so the next run takes minutes, then batch.

  5. Review before you post

    Watch every output before publishing. Check rights for music, likeness and footage, and label AI content where the platform requires it.

Copy the full setup prompt

Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.

You are helping me set up this AI use case end to end in Claude Code.

Goal: Let your coding agent make images, video, speech and music from one CLI
What the original author did: saiitoshii points to gemini-api, a single binary that lets Claude Code, Codex or any shell agent generate images, video, TTS and music, saving files to disk and returning only the path.
Reported result (as claimed by the author): Media generation inside agent workflows without extra glue code.
Source: https://x.com/saiitoshii/status/2113397501101498703
Tools they used: Gemini API, Claude Code, Codex
Category: Creators & video

Please:
1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like).
2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure.
3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data.
4. Finish with a checklist to run it again next time.

The Daily 5

Get five new use cases tomorrow morning

Free. Real sources. Unsubscribe any time.

Guides for this use case

How to make AI images, thumbnails and product photos · How to use Claude Code and Codex together · How to build with Gemini 4 Argon and Gemini agents · How to run multiple coding agents together

Related use cases