# Know your burn across research sprints

> Query balance and daily quota mid-sprint — plan heavy research days around what's actually left.

- For: Team admin
- Category: Agent & Workflow Automation
- MCP tools: get_credit_status
- HTML version: https://veridive.com/mcp/use-cases/know-your-burn

## The problem

Metered tools create a specific low-grade dysfunction: nobody knows the number. "Do we have credits for this?" becomes a Slack question aimed at whoever owns the account; heavy research days get planned on vibes; and the choice between running the deep analysis now versus next sprint gets made without the one input that should decide it.

The number is one free call away. Making it *ambient* — checked at sprint planning, checked before heavy days, checked by anyone without asking anyone — is less a workflow than a habit. But it's the habit that separates teams who use their research budget from teams who fear it.

## How veridive MCP helps

**get_credit_status** returns the live state — wallet balance, plan tier, today's remaining free quota — to whoever asks, free, in any connected assistant. That's the whole mechanism; the value is in where the habit installs it:

Sprint planning ("what's the budget line this cycle?"), the morning of a heavy research day ("size today's ambitions"), mid-sprint pulse checks ("are we pacing?"), and the end-of-cycle read that turns usage into next cycle's plan. The Slack question to the account owner dies; in its place, a number everyone can see and plan against — which is what a budget is supposed to be.

## How to run it

1. **Connect veridive MCP** — One-time setup: add the veridive MCP server to Claude, ChatGPT, Cursor or any MCP client and generate your API key. Takes about two minutes.
2. **Make the check ambient** — Anyone, any time, free — the number stops being the admin's private knowledge.

   ```
   What's my veridive credit status — balance, tier, and today's remaining quota?
   ```
3. **Plan the heavy days against it** — Before a deep-research day: read the meter, size the ambition.

   ```
   Given the current balance, how should I sequence these research tasks today — deep runs where they earn it, lighter passes elsewhere? <task list>
   ```
4. **Close the loop each cycle** — The end-of-sprint read: what the burn was, what it bought, what next cycle should budget.

   ```
   Check credits and compare to where we started the sprint — summarize the burn for the retro.
   ```

## Problems it solves

- 'Do we have credits?' is a Slack interrupt aimed at one person.
- Heavy research days get planned on vibes instead of the meter.
- Run-it-now vs next-sprint decisions lack their one deciding input.
- Usage arrives as an invoice event instead of a planning number.

## Why it's valuable

- The number becomes ambient — free to check, visible to everyone, owned by no one.
- Research ambition sizes itself to reality on the heavy days.
- Sprint retros get a burn line; next cycle's budget stops being a guess.
- The habit underpins every guard pattern — floors only work when someone knows the level.

## Example prompts

```
Credit status: balance, tier, today's quota?
```

```
Sequence today's research against the current balance: <tasks>
```

```
Sprint burn summary for the retro.
```

## FAQ

**Does checking cost anything?**

No — get_credit_status is free, which is what makes the ambient habit viable.

**Whose balance does it show?**

The account behind the API key — for a shared team key, that's the shared wallet, which is exactly the number the team should be planning against.

**How does this differ from the budget-guard use cases?**

Same meter, different consumer: the guards put the check inside agent loops; this puts it in human rituals — planning, pacing, retros. Teams end up with both.

## Related use cases

- [Give your research agent a spending limit](https://veridive.com/mcp/use-cases/budget-guarded-agent.md) — The agent checks remaining credits before each deep run and degrades to lighter tools when the budget thins.
- [Run a budget-guarded research desk](https://veridive.com/mcp/use-cases/budget-guarded-research-desk.md) — Let analysts run deep research while an agent checks remaining credits before each heavy run — ambition with a spending cap.
- [Run a cost-aware transcript pipeline](https://veridive.com/mcp/use-cases/free-tier-transcript-pipeline.md) — Batch transcript pulls are free for imported videos; a credit check keeps the paid steps intentional.

---

Part of the veridive MCP use-case library: https://veridive.com/mcp/use-cases.md
Server docs for agents: https://veridive.com/mcp.md