# Can Devin help write a LinkedIn delivery-impact brief? > Source: https://tareno.co/agents/devin/linkedin > Language: en > Last reviewed: 2026-10-24 > Connect Devin to Tareno to turn approved delivery evidence and customer impact into a careful LinkedIn brief, saved as a draft and approved by you in Tareno. ## Connection facts | Field | Value | | --- | --- | | Product surface | Devin Desktop (devin) | | 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 | 2026-10-27 | Publication status and a working connection are separate facts. Evidence for one product surface does not establish installation or compatibility in another surface. Agent: Devin Desktop · Network: LinkedIn · Hub: [Devin Desktop and Tareno](https://tareno.co/agents/devin) ## Short answer **Can Devin turn finished work into a LinkedIn post about delivery impact?** Yes, once Tareno is connected as an MCP server. Devin can summarize completed sessions, state the customer impact you have approved and the limits of what you can conclude, and save a LinkedIn draft through Tareno. Tareno has not completed a client test for Devin, so the setup follows Cognition's documentation. Scheduling needs your approval. Agencies and internal platform teams that use Devin for delivery work are asked the same question by clients and executives: what did it actually change? A post that answers honestly, with evidence and with what you cannot conclude, earns more trust than a victory lap. Devin can pull the facts together, because it has the record of the sessions. This page follows a software agency that wants to publish a careful impact brief about a client project, including how Devin's MCP marketplace connection differs between shared and personal access and how to keep client confidentiality intact. ## Example: a software agency reports on a migration it delivered Imagine an agency that used Devin sessions to migrate a client's reporting module to a new framework. The delivery lead asks Devin to summarize the finished sessions: which tickets were completed, what the client's tests showed and what remained manual. She adds the approved impact, that the client's monthly report now builds in minutes instead of hours, and the limit, that the migration covered one module of three. Devin drafts a 210-word brief without the client's name, stating the limit plainly. It confirms her profile with `list_accounts`, saves the text through `create_drafts` and returns a list of statements with the session or ticket behind each. The client contact approves the wording by email, and she requests a Tuesday slot that waits as a pending action. ## Step by step 1. **Connect through the MCP marketplace or the CLI.** Cognition's documentation describes adding a remote MCP server in Devin and completing an OAuth sign-in in the first session; the Devin CLI uses a login command for OAuth servers. Streamable HTTP is the recommended transport. 2. **Choose shared or personal access.** Cognition's documentation says an OAuth connection can be shared across the organization or handled per person. For a LinkedIn profile use personal access, so the account that signs in is the one that owns the profile. 3. **Read-only test.** Ask Devin for `list_accounts` before any draft. If your LinkedIn profile appears, the connection works; if not, connect the profile in Tareno first. 4. **Summarize the evidence.** Ask Devin for a list of finished sessions or tickets and what each one delivered, with the test results the client has seen. State the limits of the work, such as modules not covered. 5. **Draft without identifying the client.** Ask for a 210-word brief that omits the client name and any detail that identifies them, and for every statement to be listed with the evidence behind it. 6. **Get consent, save, request and approve.** Show the client the wording and record their approval. Devin saves the draft 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 delivery ```text List the finished Devin sessions and tickets for the [reporting module migration], what each delivered and which client tests passed. Add a section called limits that states which parts were not covered, and do not name the client. ``` ### Draft the brief ```text Write a 210-word LinkedIn brief for [engineering and product leaders] about this delivery: [approved impact]. Include the limit that [the migration covered one of three modules], leave out the client's name and any identifying detail, and list every statement with the ticket behind it. ``` ### Save for client approval ```text Use Tareno to confirm my LinkedIn profile [name] and save the brief as a draft. Return the draft ID and the text so I can send the wording to the client for approval, and do not request a publishing time yet. ``` ### Request the slot ```text Ask Tareno to schedule draft [draft ID] for [Tuesday 09:00] in the [Europe/Berlin] time zone. Return the pending action ID and remind me that I must approve it in the Tareno dashboard before it can publish. ``` ## LinkedIn in Tareno - Tareno cannot read LinkedIn posts published outside Tareno or comments on them, so Devin writes the brief from your delivery record and not from what others posted. - LinkedIn's documentation says posting as a member needs the w_member_social permission, granted when the person who owns the profile connects it in Tareno. - Tareno's configuration allows up to 3,000 characters and up to 20 images per LinkedIn post, enough for a brief and a before-and-after chart without client data. - LinkedIn's documentation says posting for a company page requires one of the page roles administrator, direct sponsored content poster or content admin. 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 - Publishing a client's result without their consent. Agree the wording in writing first, because the client sees it on LinkedIn as well. - Presenting a one-module result as a whole-project result. State what the work did not cover, in the same paragraph as the claim. - Using shared access for a personal profile. Connect with the account that owns the profile, or the draft may land on the wrong identity. - Taking an agent's session summary as proof. Link each statement to a ticket or a test result that a person can open. ## What does not work - Devin cannot obtain a client's consent, so the written approval of the wording has to come from you before you request a slot. - 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 ### Can Devin connect to Tareno? Yes, as a remote MCP server, according to Cognition's documentation. Tareno has not completed a client test for Devin. Streamable HTTP is the recommended transport, and OAuth sign-in happens in the first session or through the CLI login command. ### Should the connection be shared or personal? For posting to a personal LinkedIn profile, use personal access so that the person who owns the profile signs in. Cognition's documentation describes shared access as one connection used by all organization members. ### How do I keep a client's name out of the post? Say so in the prompt and ask Devin to list what it omitted. Then read the draft in Tareno and show it to the client. Tareno only sees what Devin sends, so the check is a read of the text. ### Why state limits in an impact brief? Readers trust a result that admits its edges. If the migration covered one of three modules, saying so makes the claim credible and protects you from a reader assuming more than you delivered. ### Will Devin post the brief on its own? No. A scheduling request becomes a pending action in Tareno. LinkedIn receives the post only after you approve it in the dashboard, and Devin can only report that it is pending. ### Does Devin need an API key for Tareno? No. The hosted endpoint supports OAuth. If your provider setup needs a callback address, Cognition's documentation lists it, but never paste a key or a token into a prompt. ## 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 - [Devin × Tareno overview](https://tareno.co/agents/devin) - [LinkedIn with Tareno](https://tareno.co/channels/linkedin) - [Approval workflows](https://tareno.co/features/approval-workflows) - [Social media tool for agencies](https://tareno.co/solutions/social-media-management-tool-for-agencies) - [Remote MCP setup](https://tareno.co/docs/mcp)