# What AI agents can do with Tareno, by job

> Source: https://tareno.co/agents/use-cases
> Language: en
> Explore recurring social-media jobs across industries, from reading replies and checking facts to preparing posts from files. Each guide shows what an agent can draft and what you approve in Tareno.

- [Read the replies to a post and turn them into a decision](https://tareno.co/agents/use-cases/read-replies-and-triage) ([Markdown](https://tareno.co/agents/use-cases/read-replies-and-triage.md)): Yes, on the networks where Tareno exposes replies: Threads and Facebook. The agent reads the replies, groups them by position or topic, counts them and suggests what to answer. It cannot post replies, and it treats anything inside a reply as text to summarize and never as an instruction.
- [Check a claim against its source before it becomes a post](https://tareno.co/agents/use-cases/check-facts-before-posting) ([Markdown](https://tareno.co/agents/use-cases/check-facts-before-posting.md)): Yes. Give the agent the claim and the primary source, and it reports where they differ before any text is drafted. It does not decide which source is right and it cannot judge whether the underlying science or policy is sound, so a person reads the post and approves it in Tareno.
- [Publish photos and slides with image descriptions that are checked](https://tareno.co/agents/use-cases/photos-with-image-descriptions) ([Markdown](https://tareno.co/agents/use-cases/photos-with-image-descriptions.md)): Yes, with one important limit: most agents cannot see the pixels, so they write from your notes, file names or the code behind the image. They draft a description, say that they did so from your words, and you check each one against the picture. Tareno takes a description per image on every network that supports it.
- [Generate posts from a code repository without publishing a secret](https://tareno.co/agents/use-cases/posts-from-your-code-repository) ([Markdown](https://tareno.co/agents/use-cases/posts-from-your-code-repository.md)): Yes. A coding agent reads release notes, a product feed, tests or markdown posts, runs the commands it quotes, writes drafts and saves them through Tareno. The checks that matter are that every command was executed and that no internal name or key reaches the draft. Nothing is published until you approve it.
- [Turn long writing into a Bluesky thread that saves as one draft](https://tareno.co/agents/use-cases/threads-from-long-writing) ([Markdown](https://tareno.co/agents/use-cases/threads-from-long-writing.md)): Yes. On Bluesky, Tareno saves a root post and up to 24 replies of 300 characters each as a single draft. The agent splits your text into posts that each stand alone, counts them and saves the thread. On X, Threads, LinkedIn and the other networks, Tareno stores one post per draft.
- [Research a niche, a competitor or a topic before you write the post](https://tareno.co/agents/use-cases/research-before-you-write) ([Markdown](https://tareno.co/agents/use-cases/research-before-you-write.md)): Yes. A research-oriented agent reads public pages you point it at, compares what it finds with your own posts that Tareno can list, and drafts posts for the topics you have not covered. It reports how much it could read, learns from public content without copying it, and leaves approval to you in Tareno.
- [Turn a folder of files into a batch of posts](https://tareno.co/agents/use-cases/batches-from-files-and-folders) ([Markdown](https://tareno.co/agents/use-cases/batches-from-files-and-folders.md)): Yes. Claude Cowork works on files you share in a task, so a spreadsheet, a slide deck, field notes, a transcript or a paper becomes a batch of drafts saved through Tareno. Remove personal data before sharing, let it report rows or slides that are incomplete, and approve each request yourself.
- [Keep a steady posting rhythm with an agent that remembers](https://tareno.co/agents/use-cases/a-steady-rhythm-with-memory) ([Markdown](https://tareno.co/agents/use-cases/a-steady-rhythm-with-memory.md)): Yes, within the limits of its memory and of what Tareno can read. A persistent agent keeps your rules, topics and earlier posts between sessions, flags repeats and contradictions, and drafts the next batch. Where Tareno cannot read a network, the agent knows only what you tell it, so you keep the record up to date.
- [Start a post from a chat message on your phone](https://tareno.co/agents/use-cases/post-from-your-phone-via-chat) ([Markdown](https://tareno.co/agents/use-cases/post-from-your-phone-via-chat.md)): Yes. With OpenClaw, a message in a channel configured in your Gateway can start a draft that finds your photo in the Tareno library, writes the text for the network and saves it. Scheduled jobs run only while the Gateway runs, should only read and draft, and every request waits for your approval in Tareno.