The 7am briefing your COS used to write, before you didn't have a COS.

What this actually looks like.

How you'd actually build it.

Each step is its own agent-or-pipeline component. Don't try to do this in one giant prompt — the failure modes compound.

1. Ingest at 6am local

   Pull from TMS (deliveries, exceptions, capacity), WMS (inventory deltas, picks behind), ERP (orders, AP, AR), support (open tickets by tier), Slack (incidents, blockers). This is the cron-triggered fetch pipeline.
2. Synthesize by urgency, not by source

   Cluster items by what they actually mean: exceptions needing decision, blockers on owned workstreams, customer escalations. Sort by revenue at risk and SLA pressure, not by which tool the item came from. This is the synthesis agent.
3. Format the briefing

   Markdown in four sections: today's exceptions / decisions due / team status / customer escalations. Each item has context, owner, recommended action, source link. This is the writer.
4. Deliver with one-click actions

   Slack DM and email at 7am. Top three items have inline buttons: approve, escalate, reassign, defer. Morning catch-up becomes a 6-minute read with three clicks.

What it runs on.

No vendor lock-in. Every piece is replaceable. The orchestration outlasts the model — when Claude 5 or GPT-6 ships, swap the model, keep the pipeline.

What this actually returns.

Calibrated to mid-market scale (50–1000 staff, $1M–$200M revenue). Your numbers will vary; the framework gives you the order of magnitude to plan against.

Build it yourself, or have us ship it.