They share one memory, so nothing is said twice
Three layers: directive, orchestration, execution
One piece of work, adapted per platform and posted on schedule. Agentic social distribution: comment triggers turn a public reply into a direct message without anyone sitting in the inbox.
The SOP, written down. Goals, inputs, the tools to use, the outputs and the edge cases — in plain language, versioned like code. When we learn an API limit the hard way it gets written here, so it is never learned twice.
The only probabilistic layer. It reads the directive, calls the tools in order, handles the errors and asks when something is genuinely ambiguous. It does not do the work itself.
Deterministic scripts. Same input, same output, every run. Ninety per cent accuracy per step is fifty-nine per cent over five, so anything that must be right lives down here instead.
A schedule that silently stops is worse than no schedule at all. This one is measured against what is genuinely live on the platform, so a bad day costs you a delay rather than the post.
Also connects to
Read-only wherever read-only is enough. Nothing gets write access it doesn't need, and every write is logged.
Four hashtags maximum on any variant — truncated if the generation overruns.
The post is confirmed live on the platform, not merely accepted by the queue.
Private replies only inside the platform-permitted window.
That consistency is the whole point. The same checks and the same artifacts on every run, so when a number moves you know it moved because your site moved — not because the method did.
| Spec | Standard | Deployable |
|---|---|---|
| Where it runs | Our infrastructure | Yours |
| Who holds the API keys | Us, scoped per client | You |
| Cadence | Monthly, or weekly | Any schedule |
| Raw data retention | Rebuilt each run | Your policy |
| Artifact delivery | Your Drive and tracker | Your choice |
| Source code access | — | Full |
| Runs unattended | Yes | Yes |
| Failure alerting | Slack and email | Your channels |
Deployable hands over the software, the hosting and the keys. You run it; we stay on for support.
LinkedIn, Instagram, Facebook and X. Each post is adapted to the platform from the same source article rather than cross-posted identically, because the same wording rarely works in two places.
Yes, by default. Variants are generated and scheduled, and approval can be required before anything publishes — the automation is in the production, not in the decision to post.
A public comment containing a keyword you choose triggers a direct message carrying whatever you promised in the post. It runs on the platform’s own private-reply mechanism, inside the response window the platform permits, rather than through an unofficial workaround.