Skip to main content
Handbook/Automate/Page 85 · Reporting

Commands and What Comes Back

Share

Share this page

Pass it to someone who needs it.

Star on GitHub

Key takeaway: Command down, report up

A system you cannot see is a system you cannot steer. Reporting is the two-way pipe that lets you run the whole thing from one seat. You send commands down, the work sends truth back up, and you stay at the top of the loop instead of buried inside it.

9.13.1You command down, they report up

The shape of control is simple. Direction flows down from you as commands. Reality flows up from the agents as reports.

You do not do the tasks. You point the system at what matters, and you read back what it found. Down goes intent, up comes evidence, and you sit where the two meet.

Commands flow down as intent; reports flow back up as evidence, and you sit where they meet.

9.13.2Commands are your interface

You should not run the system by remembering ten folders and twenty scripts. You run it through a small set of named commands, each a single word that hides a mountain of machinery:

/status # the whole picture, one screen /status growth # traffic, users, money /status tech # errors, cost, agents

One to see everything, one per area to go deeper. A good command set is the entire user interface of your operation.

A command is a real file, not magic: in Claude Code each one is a markdown file in .claude/commands/ (status.md becomes /status), holding the instructions the command runs. Your tool has the same idea under its own name. You write the workflow once; the slash name is the shortcut.

9.13.3Reports are what comes back

Every agent that does work leaves a report: what it checked, what it found, what it did, and what needs you. They land in a known place, in a known shape, so you can scan many of them fast:

--- area: money verdict: needs-you --- Revenue up 4%. One failed payout, decision card filed.

A keyed shape like that is what turns a night of autonomous work into five minutes of reading. It compresses the doing so you spend your attention only on the deciding. Reports land in their own reports/ folder, separate from the department status files: a status file is a department's current truth, a report is one run's findings for you.

9.13.4Keep the loop tight

The danger is a loop that leaks. Reports nobody reads, commands that no longer match the folders, a gap between what the system did and what you think it did.

You fight that constantly with three disciplines: one command surface, one report format, one place the truth lives. The tighter the loop, the more you can trust it, and trust is the only thing that lets you actually let go.

9.13.5Build your command surface

This prompt gives you one seat to run everything from:

Ready prompt
Act as a senior engineer building my command surface. Over my operating base, create one command that pulls a single briefing out of what my system already keeps: every department's status file, the latest reports, anything waiting at needs-approval on my work board, and the current focus in my planner. Lead with what needs me and why. Then define one short report format (a few keyed fields at the top) that every agent writes into the reports folder, and add it to my guardrails so agents follow it by default. Do not create a second place the truth lives. If you need the full reasoning behind this step, read https://zalt.me/guides/vibe-coding/ai-os/reports-and-commands My operating base and departments:

Do this now: paste the prompt, set up your one status command and report format, then run the command once and read your whole operation on a single screen.

Mahmoud Zalt

Mahmoud Zalt

Software engineer, 16+ yrs · built Sistava.com in 3 months, idea to production, using these methods

Resources
Star on GitHubContribute
Donate

Support my work

A small tip keeps the free work coming.

© 2026 Mahmoud Zalt. Free to read, not to republish.
Copyright & license