> ## Documentation Index > Fetch the complete documentation index at: https://docs.corepillar.ai/llms.txt > Use this file to discover all available pages before exploring further. # Simulations > The list of every Cost Calculator run in a project, with each run's progress, model, pass/fail breakdown, grader categories and links to the traces behind each scenario. Simulations is the read side of the [Cost Calculator](/agenthub/cost-calculator). Every run you start there, and every batch of traces you import there, appears here as a **simulation run**, so you can come back to a run's grader results without reopening the calculator. Page subtitle: "View simulation runs, grader results, and pass/fail breakdowns for each evaluation." The **+ New Run** button opens the Cost Calculator. ## What a simulation run is A simulation run is one Cost Calculator run for one model: a batch of scenarios plus, once executed, one result and one trace per scenario. | You did this in the Cost Calculator | Rows it adds here | | - | - | | Created a project from a template | One **Draft** row holding the template's configuration | | Clicked **Generate Scenarios** | One **Generated** row | | Clicked **Run scenarios** with one model | That row moves to **Running**, then **Complete** or **Failed** | | Clicked **Run scenarios** with three models | The original row plus two more, one per extra model, each with its own copy of the scenarios. All three share one simulation ID. | | Ran extra passes from the Agent Audit | Additional rows for the extra passes | | Used **Import & analyze** | One **Complete** row whose scenarios are your real traces | | Applied Agent Audit fixes and re-ran | A new row re-testing the same scenarios | ## The runs table Runs are listed newest first, 20 at a time. **Load more** fetches the next page. | Column | Content | | - | - | | **Run ID** | The first 8 characters of the run ID. Hover for the full ID. | | **Status** | Draft, Generated, Running, Complete or Failed | | **Progress** | Executed scenarios out of the scenario count, for example `27/30`. A run that has not executed shows `0/30`. | | **Model** | The model identifier the run executed on (or its provider), "—" if none | | **Created** | Local date and time | Click a row, or focus it and press Enter or Space, to open its detail panel beside the list. Click the row again, or press Escape, to close it. On a wide screen the list and the panel sit side by side with a draggable divider, and the Model and Created columns hide to make room. **Empty state:** "No simulation runs yet — Run a cost analysis first — every scenario run there shows up here as a simulation run." with **Go to Cost Calculator**. **Error state:** if the list can't load, an error message with a retry button. ## Run detail panel The panel header reads **Simulation run**, the first 12 characters of the ID, and a status. In the panel, a complete run is labelled **Evaluated**. Underneath: the model, the creation time, and the number of scenarios. **Close** hides the panel. ### Task success The share of executed scenarios that passed, for example "90%" and "27 of 30 passed", with a pass/fail bar and counts ("● 27 pass", "● 3 fail"). Only scenarios that actually ran are counted. When nothing has run yet: "No scenarios executed yet — run this simulation to see task success." ### Grader categories Average scores across the executed scenarios, from 0 to 100%. Bars are green at 80% or above, amber from 50%, red below. | Category | What it averages | | - | - | | **Tool Accuracy** | Whether the agent called the tools the scenario expected | | **Response Quality** | How well the response did the task. When the judge graded the scenario, this is 60% task completion and 40% correctness from the judge; otherwise a keyword-overlap heuristic. | | **Task Completion** | The judge's instruction-following score when the judge graded the scenario; otherwise a constraint-compliance heuristic. | A category with no scores is left out. "No grader scores yet — run this simulation to see category results." when there are none at all. The pass/fail here is each scenario's recorded outcome. The Cost Calculator's results page shows the richer judged verdict, including **Partial**, the quality score and the judge's reason. Open the run there (from the Cost Calculator's **Recent** strip, the Overview page, or `?run=` on the Cost Calculator URL) for the full picture. ### Simulation results Tabs filter the scenario table: **All *N***, **Pass *N***, **Fail *N***. A tab with a count of zero is disabled. | Column | Content | | - | - | | **Scenario** | Scenario name | | **Category** | Happy path, Edge case, Refusal, Tool failure, Multi-turn (or, for imported runs, the category read from the trace) | | **Task success** | **Pass**, **Fail**, or **Not run** | | **Trace** | **View trace**, which opens the scenario's trace in [Traces](/agenthub/traces) | "No scenarios in this filter." when a tab is empty. Click a scenario row to open the scenario drawer: its conversation plan, its score profile, and **Monitored parameters**, the deterministic 0 to 1 scores for Tool Accuracy, Response Quality and Task Completion on this scenario. ## Latency The Simulations page doesn't show latency. AgentHub does not store a separate latency figure for a simulated scenario; latency is the sum of the durations of the scenario's spans (each model call and each simulated tool call). To see it: * open the scenario's trace with **View trace** for the full span waterfall and timings, or * open the run in the Cost Calculator, whose results show per-model and per-scenario latency computed from those spans. ## Simulations and traces Every executed scenario is a real trace with `source = simulation`, tagged with its category, `cost-calculator`, the batch's simulation ID and the model identifier. That makes them searchable in [Traces](/agenthub/traces) and usable with [evaluation collections](/agenthub/evaluation/overview) like any production trace. Imported runs link to your original OpenTelemetry traces instead. ## Permissions Any AgentHub user in the organization can view Simulations. Starting runs needs `run_agents` or `manage_agents` in the Cost Calculator. See [Roles and permissions](/agenthub/settings/roles-and-permissions). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.