Last verified: September 22, 2026
What You Can Now Do
Context Memo customers can now view their usage details directly in the simulator when they exceed their budget, instead of being prompted to book a call with sales. Previously an over-budget configuration ended the session: you saw a wall, not a number. Now the simulator sends you to your usage view, where you can see your own consumption and work out what drove the overage. The decision this changes is immediate. Rather than waiting on a sales conversation to learn whether a scan is worth running, you look at the consumption yourself and either trim the scan scope or decide the spend is justified.
Where It Is in Context Memo
The change lives in the simulator. When a paid tenant configures a scan that exceeds the available budget, the simulator routes to the usage page rather than the previous booking flow. That page shows your consumption for the account, so the same screen answers both questions you had at the point of the block: how much you have used, and what it went to.
How to Use It
- Open the simulator and configure the scan you intend to run: models, prompts, personas. The estimated cost is checked against your budget before anything executes.
- If the configuration exceeds budget, follow the usage route the simulator now presents. You land on your usage page instead of a calendar link.
- Read your consumption on that page and identify what accounts for the bulk of it. In most accounts the driver is model count multiplied by prompt volume, so one of those two is usually the lever.
- Return to the simulator and reduce scope against what you just saw. Cutting models, tightening the prompt set, or narrowing personas all lower the estimate.
- Re-run the simulator to confirm the revised configuration fits inside your remaining budget, then execute it.
- When the scan you need genuinely requires more budget, start the sales conversation with the usage page open. You arrive with your own figures, which shortens the discussion to the actual limit rather than discovery.
Why We Built It
Customers told us plainly that they should not have to contact sales to understand why they had exceeded their budget. The old flow made a routine operational question into a scheduled meeting, which meant a scan that could have been trimmed and run the same afternoon sat idle for days. For teams running weekly multi-model scans, that delay is lost measurement: prompts go unscanned, competitor movement goes unrecorded, and the gap in your citation data is permanent. Self-service review removes the wait and keeps the budget conversation where it belongs, as a commercial decision rather than a diagnostic one.
What It Does Not Do Yet
The new route applies to paid tenants. Trial accounts that hit a limit still follow their existing path, so if you are evaluating Context Memo and want to see the usage view, ask us and we will walk you through the account you are testing in.
Changing your budget is also still not self-service. The usage page tells you what you spent and lets you re-scope a scan to fit, but raising a limit remains a conversation with us. That is deliberate for now: budget changes on enterprise agreements touch contract terms, and we would rather those be explicit than one-click.
Finally, the usage view reports consumption. It does not recommend which models or prompts to cut. That judgment stays with you, and it should, because the right trim depends on which competitor comparisons and buyer questions matter most this quarter. If you want a second read on scope, your share of voice data is the better guide: keep the models where you are losing citations, and drop the ones where your position is already stable.