Commander
Commander is BattleGrid’s conversational control surface. You speak in plain language; it reads and writes the platform through the same capability catalogue external tools use over MCP.
It does not replace the Strategy Builder or the agent forms. When you need every dial laid out — metrics, conditions, levels, exits, brain, risk — author there. Use Commander when you want to move faster in words, then refine in those surfaces.
The market is a battlefield. Commander is how you brief the grid without walking every panel first.
What it is for
| Intent | What Commander does |
|---|---|
| Strategies | Draft / tighten a playbook: stage it into the draft, review, commit on your word |
| Agents | Commission, rebind, check risk rails, halt / resume |
| Deploy | Put agents on Radar or into Arena |
| Market & account | Regime, leaders, crowding, balance, slots, coverage |
| Trades | Qualification reads, open protections, debriefs, queued entry requests |
Create still ≠ deploy. Commissioning an agent does not put it on duty; Radar / Arena / the trade terminal are separate decisions.
Where it runs
One engine, several mounts:
| Surface | Role |
|---|---|
| Commander (main) | Full conversations and the lander starters |
| Strategy host | Dock beside the Strategy Builder — bound to the strategy you are editing |
| Agent host | Lane beside an agent’s trade work — bound to that agent |
A host conversation stays latched to that resource for the session. Host context tells Commander where it is embedded: it stages changes into that strategy's or agent's draft, where they show up as unsaved changes beside your form, and commits them only when you explicitly confirm. Other channels (where enabled) drive the same run runtime — same tools, same guards — with different identity plumbing.
How a turn works
- You send an ask (or pick a starter).
- Commander loads the intent packs it needs for that conversation — strategy work, agent ops, Radar coverage, market reads, trade debriefs, and similar.
- It calls platform tools (reads first; writes only when the ask requires them).
- Answers land as shaped cards (drafts, reviews, confirmations) plus prose — not raw tool dumps.
- Spending or standing-authority actions ask for explicit confirmation before they commit.
Core families (account, market, agent discovery, and related reads) are always available. Heavier families — strategy studio, Radar wager, live trade control, and so on — unlock when an intent pack that needs them activates. That gating keeps ordinary chats cheap without hiding power once you ask for it.
You do not have to name an intent pack. Naming the outcome is enough; Commander activates what it needs.
Strategy and agent changes: stage → commit
Building strategies and agents through Commander follows a fixed path (same as MCP):
- Stage the change into the strategy's or agent's draft — the same draft the Strategy Builder and the agent console show. Staging does not change anything live.
- Review the draft — diffs, problems, report preview, blast radius (bound agents, open positions; for an agent, its deployments and a strategy change).
- Commit only on your explicit confirmation, with exactly the draft version and revision Commander read. If either moved, the commit is refused and Commander reads the draft again. Your own Create or Save commits the same draft.
A one-rule tweak and a rebind are staged and committed the same way. Fork opens a new draft; archive and restore keep your draft. Field guides: Strategies overview (identity, Agent briefing vs Policy, lifecycle) · Indicators · Rules · Policy axes under Strategies.
Money and standing authority
Anything that moves funds, submits a wager, or grants standing autonomous authority (Radar policy upsert/delete, Arena deployment upsert/delete, halt/resume that changes whether capital can commit, close position, queue an entry, submit a grid) requires your confirmation in Commander — and, on MCP, the wager permission.
Reads, strategy configuration (non-financial), and agent setup that does not deploy capital stay on the read / configuration side. Details: MCP.
Limits that keep runs honest
Every run is bounded. When a bound hits, Commander stops visibly, never with a silent truncation:
| Guard | Meaning |
|---|---|
| Step cap | Too many tool steps in one run |
| Cost stop | Per-run spend ceiling |
| Op budget | Per-user daily tool-execution budget (resets 00:00 UTC) |
| Run / chunk timeout | Wall-clock or silence bound |
| Output limit | Output capped before a tool could run |
| Mutating tool interrupted | A write may have completed — do not blind-retry |
| User stopped | You pressed Stop — completed work still stands |
One active run per conversation. Credits must clear the floor before a stream opens.
Conversations
Transcripts persist. Soft-delete hides a conversation without erasing transcript or billing rows — the audit trail stays. Reloading a conversation replays original messages and tool results; prompt-side compaction does not rewrite stored history.
Commander vs the rest of the product
| Layer | Owns |
|---|---|
| Commander / MCP | Plain-language and programmatic control of the same catalogue |
| Strategies | The playbook (briefing + policy) |
| Agents | Brain, bind, risk, account slot |
| Radar / Arena / Terminal | Where that agent works |
Next: Prompt formula · MCP