// verdict · checked 2026-08-11 · LinkedIn ghostwriting tools, category survey Aug 2026

LinkedIn ghostwriter agents

the timeline

1/5
CRON JOB WITH EXTRA STEPS

Agree? ♻️ Repost if a scheduled prompt changed your life.

CAPABILITY
1/5 CRON JOB WITH EXTRA STEPS
PROOF
DOCS CLAIMEDThe vendor's documentation states it and we read the page; we did not watch it happen
TRACE ACCESS
UNAVAILABLENo step record reaches anyone outside the vendor
LEASH
Not measuredno execution record scored — measure it yourself

Compare → Download the card Bring a trace →

01

The five questions

the rules →
LOOPSruns until doneno Autopilot is a cron: it drafts N posts on a frequency the human sets, then stops; step count is fixed by the schedule, never re-decided by whether the task is done. DOCS CLAIMED source · confidence 8/10 · checked 2026-08-11 · ruled by hand
CHOOSESpicks its own toolsno In-app the chain is fixed (idea to draft to schedule to publish); MagicPost's 29-tool MCP server does allow runtime tool picking, but the chooser is the user's external LLM, not the product. DOCS CLAIMED source · confidence 7/10 · checked 2026-08-11 · ruled by hand
ACTSchanges the worldyes Confirmed: Taplio/Supergrow/MagicPost publish queued posts straight to the LinkedIn profile or company page via the official API at the set time — real state change, not text for a human. DOCS CLAIMED source · confidence 8/10 · checked 2026-08-11 · ruled by hand
RECOVERSfixes its own errorsno Failed posts land in an Errors list, and every documented fix (reinstall the extension, refresh the token, re-encode media, contact support) is a human action; nothing different is attempted. DOCS CLAIMED source · confidence 8/10 · checked 2026-08-11 · ruled by hand
UNSUPERVISEDnobody watchingno Publishing is gated per post: TeamPost states nothing posts without explicit approval, and the queue only defers a post the human already signed off, so no documented mode completes unattended. DOCS CLAIMED source · confidence 6/10 · checked 2026-08-11 · ruled by hand

Capability decisions combine documented behaviour and execution evidence. The proof label on each row shows which of the two decided it, and Leash is reported separately, only when it was measured from an execution record. Primary source: support.taplio.com. Tested against: LinkedIn ghostwriting tools, category survey Aug 2026. Our confidence in this dossier: 4/10.

02

Can you see it work?

the weakest of the five grades above

DOCS CLAIMED — The vendor's documentation states it and we read the page; we did not watch it happen. Trace access: UNAVAILABLE — No step record reaches anyone outside the vendor.

Drafts, a posting queue and analytics only; no vendor exposes a step-level run record.

Where we looked: Docs/help centers for Taplio, Supergrow, ContentIn, Oiti, FinalLayer, MagicPost, EasyGen, Devi; searched run logs, traces, audit logs, step APIs. Found only queue + analytics. · see the evidence → · re-checked by a second pass built to overturn it

03

Revision history

rss for this product
  1. 2026-08-11
    2/5 WRAPPER WITH AMBITION → 1/5 CRON JOB WITH EXTRA STEPSPre-launch adjudication: every criterion the verdict depends on was re-checked by hand against the published rules.editorial correction — no case was filed
04

Badges

earned, never for sale

VERDICT CORRECTED

These render from the live dataset, so a badge cannot outlive the verdict it claims. If the verdict changes the badge changes with it, and an unearned one returns 409 rather than an image. No sponsor can buy one, at any price.

05

Think this is wrong?

bring evidence, not opinion

Name the criterion and link a trace, a doc, or a recorded run that shows the behaviour. A verdict changed by evidence is the best thing that can happen to this site, and the change goes on the public record with your reason attached. Vendors are welcome, and a vendor's own filing is labelled as such rather than buried.