Loading...
×Use a Paperclip retrospective agent with Tareno configured in its runtime to turn a month of run records and budget data into a LinkedIn retrospective that the manager edits and approves.
Yes, once Tareno is configured in the agent's runtime, because Paperclip has no MCP command of its own. A retrospective agent reads the month's run records and budget, drafts what worked, what failed and one change, and saves it through Tareno. The manager decides what to disclose, and a time request stays pending until approved.
Last reviewed 2026-10-25 · Markdown version for AI agents
Managers who run agents learn things that peers would value: which tasks the agents handled well, where they wasted budget, what a human still had to fix. The learning rarely gets written down. Paperclip keeps the material, with run records, costs and heartbeats, and a retrospective agent can turn a month of it into a first draft in the manager's voice. Paperclip does not add MCP servers itself, so Tareno is configured in the runtime the agent uses, and the draft lands in the manager's account for review. This page follows a head of operations who runs a small company of agents. She decides what the company is willing to say publicly, and she is the only one who can approve a time. Tareno has not tested this end to end.
Imagine a head of operations whose agents handle support triage and reporting. At month end her retrospective agent reads the run records and the budget summary and drafts a LinkedIn post: triage runs resolved most tickets without help, a reporting agent overspent on retries, and one change for next month is a cap on retries. She removes a customer's name and a ticket link and rewrites one sentence in her own voice. The agent confirms her profile with list_accounts and saves the text with create_drafts.
Follow the Paperclip overview: add Tareno in the Claude Code adapter's user scope or in Hermes's config, and complete the OAuth flow once as the user that runs the heartbeat. Paperclip itself has no command for this.
Check the server from the agent's working directory with the environment the heartbeat uses, then run a read-only list_accounts. Your LinkedIn profile in the answer is the check; an empty answer means it has to be connected inside Tareno.
Hand the retrospective agent the run records and the budget summary, and tell it to keep observed data apart from inference and to flag any figure missing from the records.
Read it as a stranger would. Strip internal ticket links, customer names and figures that nobody approved for publication, then put the closing change into your own words.
The agent checks your profile via list_accounts and files the edited text through create_drafts, which returns a draft ID. Nothing is scheduled.
Give a day, a time and an IANA zone; schedule_posts creates a pending action that you release in the dashboard.
Use Tareno to list my connected social accounts with platform and account name. Read only: do not create, schedule or publish anything. If you cannot reach Tareno from this run, say so clearly and report which tools you did have available.Read this month's run records and the budget summary for the support and reporting agents. List what the data shows about tasks handled without help, retries and cost, and mark anything you infer. Do not write the retrospective yet.Write a LinkedIn retrospective of about 220 words in the first person for the head of operations: what worked, what failed and one change for next month. Leave out ticket links, customer names and any figure marked as not approved, and list the records each claim rests on.Use Tareno to confirm my LinkedIn profile [name] and save the approved retrospective as one draft. Return the draft ID and the text, and request no time until I give you the day and the time zone.Take the draft [draft ID] and ask Tareno to schedule it for [last Friday of the month, 16:00] in [Europe/London]. Return the action ID and remind me that the request still waits for my approval in the Tareno dashboard.As configured in Tareno on 2026-10-24. The live rules for your own account come from the get_platform_schema tool.
Source: Microsoft Learn: LinkedIn Posts API, read on 2026-10-24. Platform rules change; check the page before you rely on a number.
https://tareno.co/api/mcpUse the same Tareno account across supported clients. Open the relevant setup guide for authentication, first use, reconnect, and revocation.
list_accountsChecked:
The manager's. The agent assembles facts and a first draft, but the opinion and the closing change should be rewritten in your own words before approval.
Whatever Paperclip exposes through its runtime: run records, issue history and budget summaries. Limit it to what it needs, since a draft built from tickets may carry customer details.
Yes. Keep the standing instruction that it only drafts, because Tareno holds every time request as a pending action that you approve in the dashboard.
Check the run viewer for the tool list of a real run, then ask for `list_accounts`. The steps come from Paperclip's own guide and Tareno's documented setups, and no one has run the whole chain end to end.
A first-person retrospective fits a personal profile. A page needs a LinkedIn role such as administrator for the connecting member, and it only appears in `list_accounts` once that role exists.
No. The agent can only draft, and each time request waits in the Tareno dashboard until you approve it. Afterwards `get_action_status` shows what LinkedIn answered.