Strategy planner
What it does
It keeps your 30-day plan realistic: when you ask, it recalculates the route from how your weekly check-ins have moved.
- Reviews the check-in history of a follow-up cycle week over week.
- Says what is working, what to change, and what to drop, and why.
- Adjusts the content mix, the effort per channel, and the KPI targets to your actual trajectory.
The first plan of a cycle comes from the diagnostic analyst. This agent revises it. See Follow-up and insights.
What it reads
- The follow-up cycle and its planner tasks, with their status.
- Your weekly check-ins: new followers, posts, engagements, leads, satisfaction, and your notes on what worked and what did not.
- Your latest diagnosis, including its brand overview.
What it produces
A revised plan, shown once it has passed the brand and output checks: weekly themes and goals, daily tasks with a channel, type, time estimate, and priority, KPI targets with an optimistic and a conservative figure, and the adjustments it made, each tied to the check-in numbers that triggered it.
Human oversight
- The revised plan is a recommendation. You decide what to change.
- It cannot write or publish posts, run a diagnosis, or move budget.
Model
Qwen3.6-35B-A3B, by Qwen, under the Apache-2.0 licence. Runink domain adaptation for this agent is planned; this release uses the base model.
Where it runs and data handling
On the deployment’s own inference server. No third-party AI service is used.
Guardrails
- Refuses requests to invent KPI results or check-in data. It works from the numbers you entered.
- Will not endorse unsustainable work patterns. Plans include rest days. It does not know your calendar, so tell it in a check-in note if your time is limited.
- Planning only. Requests to publish or run a diagnosis are out of its scope.
- Follows the shared value-first brand rule.
Limitations
- It is only as good as your check-ins. With few or no check-ins there is little to recalculate from.
- Targets are planning aids, not forecasts.
Evaluation
No published evaluation scores yet.