> ## Documentation Index > Fetch the complete documentation index at: https://docs.plurai.ai/llms.txt > Use this file to discover all available pages before exploring further. # Scan stage > Read the Scan stage of the report: your digital twin, which systems are real and which are mocked, and the knowledge base your agent answers from. The **Scan** stage (`#scan`) shows what the simulation will put around your agent. **Your digital twin** shows which of the systems your agent calls are real and which are mocked. **Your knowledge base**, when your agent answers from documents, shows those documents and the questions planted in them. Check both before you read any results. A wrong mock or a wrong document makes every result after it wrong too. The stage fills in when you [scan your agent](https://docs.plurai.ai/guides/scan-your-agent.md). The knowledge base is added when the suite build creates it. The stage tab counts what it found, for example `4 mocked`. ## Your digital twin *What the Agent really reaches, and the mocked surfaces standing in for the rest, so every scenario stays controlled and free of side effects.* ![The Scan stage](https://mintcdn.com/plurai/V3XeGRFO5iyJejs5/images/report/scan.png?fit=max\&auto=format\&n=V3XeGRFO5iyJejs5\&q=85\&s=4a831f3b68ffe30f8525a594d0d470d7) The Scan stage: your agent flow graph, with what runs for real and what is mocked. The figure shows your agent wired the way the [harness](https://docs.plurai.ai/concepts.md) runs it. Each pin is one surface your agent reaches: a tool, a skill, a sub-agent or a retrieval source. Point at a pin to read why it sits where it does. | Label | Meaning | | - | - | | **Your systems** | Surfaces the agent reaches for real during the simulation. Calls go to your system. | | **Mock environment** | Surfaces the mock environment stands in for. Calls never reach production. | | **Seeded world** | The records and state the mock environment starts each scenario with. | | **Nothing mocked** | Every surface runs for real. The suite tests your agent against your live systems. | | **live probe** | A mocked surface that also has a live check against your system. | | **Grounding** | Whether the agent **Answers from your documents** or **Answers without documents**. | The section header counts what it found, for example `4 mocked` or `6 surfaces`, and lists the kinds it wired: *3 tools, 1 sub-agent*. ### The surface table Open a pin, or use the **Lens** control to switch between **live**, **mocked** and **live probes**, to read each surface in detail: | Column | Meaning | | - | - | | **Surface** | The tool, skill, sub-agent or source. | | **Kind** | What kind of surface it is. | | **Why** | Why the scan made it live or mocked. | | **Reach** | What a call can change: your live systems, the seeded world, or nothing, and any side effects such as shell commands, files or network calls. | | **Probe** | Whether it has a live probe, or is eligible for one. | | **Needs** | What it needs before it can run for real, such as your consent. | ### What to check * Every surface that writes to production, sends messages or moves money is under **Mock environment**. A surface under **Your systems** is called for real on every conversation. * The **Seeded world** matches the records your agent expects, such as accounts, orders or tickets. * If the agent answers from documents, **Grounding** reads **Answers from your documents** and [Your knowledge base](#your-knowledge-base) appears below. To change what is mocked or seeded, say so in chat, or run `/edit-env`. See [Build the suite](https://docs.plurai.ai/guides/build-the-suite.md) and [Ground in real records](https://docs.plurai.ai/guides/real-records.md). In a conversation, each tool call says who answered it: **served by the twin** or **your system**. See [Run results](https://docs.plurai.ai/report/run-results.md#the-conversation-drawer). ## Your knowledge base This section appears below **Your digital twin** when your agent retrieves from documents and a [knowledge base](https://docs.plurai.ai/guides/knowledge-base.md) was built for it. Link to it with `#knowledge`. ![Your knowledge base, as the Scan stage shows it.](https://mintcdn.com/plurai/V3XeGRFO5iyJejs5/images/report/knowledge-base.png?fit=max\&auto=format\&n=V3XeGRFO5iyJejs5\&q=85\&s=01e17c1edc1d2acc051c44962a92c3d7) Your knowledge base, as the Scan stage shows it. *Every document a spine, its passages hung in reading order under their section titles and indented by section.* The header counts the documents and passages, for example *3 documents ยท 214 passages*. If a file could not be read, it says so, for example *1 file not ingested*. | Element | Meaning | | - | - | | Spine | One document. Its passages hang under it in reading order. | | Passage | One chunk of the document. In some layouts, taller means longer. | | **holds an answer** | A planted question's answer is in this passage. | | **grounds a question** | A planted question is built on this passage. | | **never asked** | No planted question touches this passage. | | **In the corpus, outside the knowledge base** | Material that was ingested but isn't part of what the suite asks about. | Point at a passage to see where it sits and what asks about it. Select it to read it. The passage view shows its **Section**, the text, and **Asked in this Suite**: each planted question, the scenario, and the turn that asks it. Use the arrow keys to move between passages. The **Suite** stage header tells you how much of the knowledge base the suite tests, and links back here with **See it on Scan**. See [the coverage line](https://docs.plurai.ai/report/suite.md#knowledge-coverage). To fix a wrong fact or a bad question, say so in chat or run `/edit-env`. See [Use a knowledge base](https://docs.plurai.ai/guides/knowledge-base.md). ## Next steps > [card] [Suite and traces stages](https://docs.plurai.ai/report/suite.md) > > Your agent flow graph, every scenario and eval, and the production failures the suite replays. > [card] [Scan your agent](https://docs.plurai.ai/guides/scan-your-agent.md) > > How the scan maps your agent and decides what to mock. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.