> ## Documentation Index
> Fetch the complete documentation index at: https://docs.atomscale.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Act

> Turn real-time process intelligence into decisions, interventions, and control

The final step in the Atomscale workflow is acting on the information extracted from your
process data.

The [Analyze](/platform/get-started/analyze) step gives you the insights:
similarity trajectories, derived metrics, and within-run uniformity. This page covers what you do with those insights: detecting problems automatically, deciding how to respond, and progressively closing the loop toward automated control.

## Alerts and Changepoint Detection

Atomscale's alerting system operates on our derived intelligence layer that holistically
profiles growths, allowing them to catch problems that are invisible to conventional
monitoring that operates on fixed combinations of sensors.

<Accordion title="Technical Dive: How Atomscale Alerts Differ">
  Traditional alerting operates on tool state: temperature out of range, pressure spike, flow rate deviation. Atomscale alerts operate on **materials state**: the derived metrics that describe what's actually happening to the film being deposited.

  | Traditional Alerting         | Atomscale Alerting                                        |
  | ---------------------------- | --------------------------------------------------------- |
  | Temperature exceeds setpoint | Predicted composition drifting from target                |
  | Pressure outside range       | Surface reconstruction deviating from expected sequence   |
  | Flow rate drop               | Run trajectory diverging from process fingerprint library |
  | Manual RHEED observation     | Quantitative lattice spacing or spot count anomaly        |

  <Note>
    Atomscale's anomaly detection has demonstrated **greater than 96% accuracy** and can flag issues **40 seconds earlier** than manually monitoring the same process visually.
  </Note>
</Accordion>

### Types of Alerts

<Tabs>
  <Tab title="Changepoint Detection">
    Atomscale continuously scores each run against your process fingerprint library. When a run's trajectory diverges from expected behavior, an alert fires, even if every individual tool parameter looks normal.

    This is particularly valuable for catching subtle defects like compositional drift or surface quality degradation that don't manifest in any single sensor reading.
  </Tab>

  <Tab title="Drift Tracking">
    Beyond single-run anomalies, Atomscale tracks trends across runs. If your process is gradually shifting (for example, source depletion causing a slow composition drift over days or weeks), drift alerts flag the trend before any individual run fails.
  </Tab>

  <Tab title="Threshold Alerts">
    For specific derived metrics, you can set explicit thresholds. Unlike raw parameter thresholds (which any SCADA system handles), these operate on Atomscale's extracted quantities:

    * Predicted composition outside target range
    * Surface roughness estimate exceeding specification
    * Lattice spacing deviating from expected value
  </Tab>
</Tabs>

### Setting Up Alerts

<Steps>
  <Step title="Choose an Alert Type">
    Select from changepoint detection (automatic, model-driven), drift tracking (cross-run trending), or
    threshold-based (explicit limits on derived metrics).
  </Step>

  <Step title="Define Scope">
    Specify which data streams, runs, or recipes the alert applies to. Alerts can be scoped to a
    specific tool, material system, or recipe family.
  </Step>

  <Step title="Set Severity and Notification">
    Assign a severity level (**Info**, **Warning**, or **Critical**) and configure how you're
    notified: in-app, email, or webhook for integration with external systems.
  </Step>

  <Step title="Tune Sensitivity">
    Start with conservative thresholds and tighten as you build confidence in normal process
    variation. Atomscale provides alert history to help you calibrate sensitivity and reduce false
    positives.
  </Step>
</Steps>

## Respond to Anomalies

When an alert fires, the next step is deciding what to do. Atomscale supports a range of responses depending on the severity and your integration level.

### Operator-in-the-Loop

For most teams starting with Atomscale, the initial workflow is operator-assisted: Atomscale detects and surfaces the issue, and a human decides what to do.

<CardGroup cols={2}>
  <Card title="Investigate" icon="magnifying-glass">
    Click through from an alert to the Analyze view. Compare the flagged run against reference runs
    to understand exactly what diverged and when.
  </Card>

  <Card title="Annotate" icon="pen">
    Log observations and decisions directly on the run timeline. These annotations feed back into
    your process library for future reference.
  </Card>

  <Card title="Adjust" icon="sliders">
    Use the alert context to decide on recipe adjustments: modify setpoints, extend or shorten
    growth stages, or compensate for detected drift.
  </Card>

  <Card title="Abort" icon="circle-stop">
    For critical anomalies, decide to terminate a run early rather than wasting time and materials
    on a doomed process.
  </Card>
</CardGroup>

### Run Disposition

After a run completes, Atomscale's analysis helps with go/no-go decisions before
committing to downstream processing or characterization. Rather than waiting days or weeks
for ex-situ measurement results, you can use in-process predictions to triage runs
immediately.

## Integrating Process Control

For teams ready to move beyond operator-assisted monitoring, Atomscale supports
progressively tighter integration with AI-driven process control.

<Warning>
  Closed-loop control requires careful validation. Most teams start with monitoring and alerting,
  build confidence in Atomscale's predictions, and then incrementally close the loop. The
  integration roadmap below reflects this progression.
</Warning>

### Integration Levels

<Steps>
  <Step title="Monitor and Alert">
    Atomscale observes and notifies. All decisions and actions are made by operators. This is where
    most teams start.
  </Step>

  <Step title="Recommend">
    Atomscale suggests specific adjustments based on detected deviations. For example, recommending
    a flux correction when predicted composition drifts from target. Operators review and execute.
  </Step>

  <Step title="Assist">
    Atomscale sends adjustment commands to the process controller via SECS/GEM or tool API, with
    operator approval required before execution.
  </Step>

  <Step title="Autonomous Control">
    Atomscale continuously monitors and adjusts the process in real-time without operator
    intervention. The system optimizes for consistency of output (the target material properties)
    rather than consistency of tool setpoints.
  </Step>
</Steps>

### Agent-Based Process Control

At the most advanced integration level, Atomscale's AI agent acts as a process copilot. The agent combines real-time derived metrics with the full process fingerprint library to make context-aware decisions.

Key capabilities include:

* **Real-time recipe adjustment**: Modify growth parameters mid-run to correct for detected deviations, such as adjusting source temperatures to maintain target composition.
* **Natural language customization**: Configure agent behavior and decision context using natural language instructions, adapting the scope and sensitivity of automated control without code changes.
* **Audit trail**: Every automated action is logged with full context: what was detected, what the agent decided, and what command was sent. This provides complete traceability for process validation.

## Track and Review

Acting on process data is only valuable if you can measure whether those actions improved outcomes. Atomscale provides tools to close the learning loop.

### Run Reports

Each run generates a summary that includes:

<Check>Derived metrics timeline with key events and transitions highlighted</Check>
<Check>Comparison to target values and reference baselines</Check>
<Check>Any anomalies detected and actions taken (manual or automated)</Check>
<Check>Annotations and operator notes</Check>

### Process Improvement Tracking

Over time, track how interventions, whether manual adjustments informed by Atomscale or automated corrections, affect yield and process stability. This historical record is what transforms individual run insights into systematic process improvement.

## Next Steps

You've completed the getting started guide! Continue exploring:

<CardGroup cols={2}>
  <Card title="Detect Anomalies" icon="bell" href="/platform/guides/detect-anomalies">
    Detailed guide on configuring anomaly detection for active runs.
  </Card>

  <Card title="Diagnose Run Differences" icon="code-compare" href="/platform/guides/diagnose-run-differences">
    Compare runs and understand what changed when results differ.
  </Card>

  <Card title="Characterization Workflows" icon="microscope" href="/platform/characterization">
    Set up monitoring and analysis for specific characterization methods.
  </Card>

  <Card title="Python SDK" icon="python" href="/sdk">
    Programmatic access to Atomscale's analysis and control capabilities.
  </Card>
</CardGroup>