# Can JetBrains Junie write a LinkedIn case study from an IDE session?

> Source: https://tareno.co/agents/junie/linkedin
> Language: en
> Last reviewed: 2026-10-24
> Connect JetBrains Junie to Tareno to turn an implementation lesson and public-safe evidence from your IDE into a LinkedIn case study, approved by you in Tareno.

## Connection facts

| Field | Value |
| --- | --- |
| Product surface | JetBrains Junie (junie) |
| Available connection | Custom MCP connection |
| Connection evidence | documented |
| Methods | mcp |
| Authentication | oauth |
| Setup | [Setup guide](https://tareno.co/docs/mcp) |
| Install or connect | [Open setup](https://tareno.co/docs/mcp) |
| Evidence observed | No dated observation recorded |
| Facts reviewed | 2026-10-25 |

Publication status and a working connection are separate facts. Evidence for one product surface does not establish installation or compatibility in another surface.

Agent: JetBrains Junie · Network: LinkedIn · Hub: [JetBrains Junie and Tareno](https://tareno.co/agents/junie)

## Short answer

**Can Junie turn an implementation lesson into a LinkedIn case study?**

Yes, once Tareno is added in Junie's MCP settings. Junie reads the code you changed, turns the lesson and the public-safe evidence you give it into a case study and saves it as a draft through Tareno. Tareno has not completed a client test for Junie, so the setup follows JetBrains' documentation. Scheduling needs your approval.

Teams that live in a JetBrains IDE tend to learn their lessons in refactorings, and those lessons rarely leave the repository. A case study for LinkedIn can carry them to people who face the same migration next quarter. Junie works inside the IDE, so it sees the changed code and the tests, which is the best raw material for a lesson that is concrete. This page follows a Kotlin backend team writing up a refactoring, including where Junie keeps its MCP settings, how to verify the connection and what must be checked before any code-derived detail goes public.

## Example: a Kotlin team writes up a refactoring of its payment module

Imagine a backend team that replaced callback-heavy payment code with coroutines. A developer asks Junie to summarize the change from the diff and the tests: what was removed, what was simplified and what got harder to debug. She gives the lesson she wants to share and a public-safe line about test runtime. Junie writes a 220-word case study for backend developers and flags a sentence that mentions a table name from the code as internal. She removes it, Junie confirms her profile with `list_accounts` and saves the draft through `create_drafts`. A teammate reads the post in Tareno, and she requests a Thursday 11:00 slot that waits as a pending action.

## Step by step

1. **Start in the Junie settings.** Inside the IDE, Tools, Junie and MCP Settings lead to an Add button. It opens mcp.json with an mcpServers entry to fill in, and JetBrains leaves the field details to the server's own documentation.
2. **Point it at Tareno.** Give the entry the name tareno and the hosted endpoint from the Remote MCP setup page. When the file is saved, Junie shows the server, its state and the tools it discovered.
3. **Verify the connection.** The MCP server list shows each server's status and tools. Ask Junie for `list_accounts` as a first read-only test; if your LinkedIn profile appears, the connection works.
4. **Give the lesson and what is public.** Tell Junie the lesson, the audience and which facts may go public. Ask it to flag identifiers from the code, such as table names, service names and hostnames.
5. **Draft and check the code-derived details.** Ask for a 220-word case study and for every detail that came from the code to be listed. Remove or generalize anything that identifies your system.
6. **Save, request and approve.** Junie saves the post through `create_drafts`. Give a date, a time and an IANA time zone, and approve the pending request in the Tareno dashboard.

## Prompts to copy

### Summarize the refactoring

```text
Summarize the changes in the last [three] commits of the payment module from the diff and the tests: what was removed, what was simplified and what became harder to debug. Do not invent reasons that are not in the commit messages or tests.
```

### Draft the case study

```text
Write a 220-word LinkedIn case study for [backend developers] about replacing callbacks with coroutines in a payment module. Use this lesson: [lesson] and this public-safe fact: [test runtime fell from 9 to 4 minutes]. List every detail that came from the code so I can check it.
```

### Strip identifiers

```text
List every identifier in the draft that comes from our code, such as table names, class names, service names or hostnames, and rewrite the sentences so that none of them appears. Show me the rewrite before you save anything to Tareno.
```

### Save the draft

```text
Use Tareno to confirm my LinkedIn profile [name] and save the final text as a draft. Return the draft ID and the text, and do not request a publishing time until I give you the day and the time zone.
```

## LinkedIn in Tareno

- Comments and posts that live only on LinkedIn are invisible to Junie through Tareno, so it has nothing to benchmark your refactoring write-up against.
- LinkedIn's documentation says posting as a member needs the w_member_social permission, granted when you connect your own profile in Tareno.
- Tareno's configuration allows up to 3,000 characters and up to 20 images per LinkedIn post, so a simplified diagram can go in next to a 220-word text.
- LinkedIn offers no transcripts through Tareno, so a conference talk about the refactoring has to be summarized in writing for Junie to use it.

Official rules ([Microsoft Learn: LinkedIn Posts API](https://learn.microsoft.com/en-us/linkedin/marketing/community-management/shares/posts-api), checked 2026-10-24):

- Organic posts can contain text, images, videos, documents, articles, several images or polls. Organic carousels are not supported by the Posts API; they exist only as sponsored content.
- Posting for a company page requires one of the page roles administrator, direct sponsored content poster or content admin. Posting as a member needs the w_member_social permission.
- An article post needs its title, description and thumbnail set explicitly, because the API does not scrape the link for a preview.
- Reading a member's own posts needs r_member_social, a restricted permission that is available to approved users only.

## Mistakes to avoid

- Leaving class or table names in the text. They reveal your architecture and are easy to overlook in a code-derived draft.
- Presenting a refactoring as a pure win. Readers learn more from what became harder than from what became shorter.
- Using a test-runtime number from a different machine or branch. State the conditions, or keep the number out.
- Editing mcp.json with the wrong fields. If no tools appear, check the schema in the Tareno docs, not Junie's.

## What does not work

- Junie cannot decide which identifiers from your code are safe to publish, so a person has to read the draft and remove them.
- It cannot read LinkedIn posts or comments through Tareno, because Tareno exposes neither for LinkedIn.
- It cannot publish by itself, since scheduling and publishing requests wait for your approval in the Tareno dashboard.

## Frequently asked questions

### Does JetBrains Junie support Tareno as an MCP server?

Yes, as an MCP server added under Tools, Junie, MCP Settings, according to JetBrains' documentation. Tareno has not completed a client test for Junie. The MCP server list shows the connection state and the tools it found.

### Where do the connection fields for a remote server come from?

JetBrains' documentation says the schema is in the documentation of the MCP server you add. For Tareno that is the Remote MCP setup page, which gives the hosted endpoint and the OAuth sign-in.

### How do I keep code details out of the post?

Ask Junie to list every identifier it took from the code and to rewrite sentences without them. Then read the draft in Tareno. Tareno only receives what Junie sends, so the check is a read of the text.

### Can Junie work from the diff alone?

It can summarize what changed, but reasons come from commit messages, tests and what you tell it. Ask it not to invent motives, and supply the lesson yourself.

### Does anything go live before I approve it?

No. A scheduling request becomes a pending action in Tareno. LinkedIn receives the post only after you approve it in the dashboard, and Junie can only report that it is pending.

### Does Junie need an API key?

No. The hosted endpoint supports OAuth, so you sign in with your Tareno account. Never paste a key or a token into a prompt or into a configuration file you commit.

## Tareno tools used

- `list_accounts`
- `create_drafts`

Approval model: Tareno saves drafts directly. Scheduling, publishing, edits to scheduled posts and deletions become pending actions that a person approves in the Tareno dashboard; no agent can approve them.

## Related

- [JetBrains Junie × Tareno overview](https://tareno.co/agents/junie)
- [LinkedIn with Tareno](https://tareno.co/channels/linkedin)
- [Approval workflows](https://tareno.co/features/approval-workflows)
- [Content boards](https://tareno.co/features/content-boards)
- [Remote MCP setup](https://tareno.co/docs/mcp)