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

# 2. Add hardware context

> Datasheets, BOM, schematics, supporting docs, compliance standards, and the SEB.md project brief — everything Seb needs to know before it writes a line of code.

Give Seb the knowledge it needs to make good decisions — chips, BOM, schematics, design docs, and the compliance standards you target.

<Note>
  **Where:** Platform → project **Context** page.
</Note>

## Hardware

Three upload slots:

* **Schematics** — `.SchDoc` (Altium), `.kicad_sch` (KiCAD), `.sch`, or XML.
* **Datasheets** — PDFs of the chips, sensors, and modules in your build.
* **BOM** — XLSX, CSV, or ODS. Upload kicks off a Nexar datasheet fetch per MPN; misses are reported per-line so you can fill the gap manually.

## Supporting docs

Design notes, SOPs, ICDs, test plans. PDF, DOCX, or Markdown. Seb reads them as project context whenever it reasons about your codebase.

## Target a compliance standard

Pick the standards your project is held to — DO-178C, ISO 26262, IEC 62304. These drive the traceability rules used by gap analysis.

## Requirements and gap analysis

Skip if you're not under formal compliance and have no structured spec to grade code against — the agent loop in [step 3](/guide/run-agents) works without requirements.

Upload on the Context page's **Requirements** card:

* **CSV** — a mapping preview confirms which columns are id / text / level / safety class.
* **PRD / DOCX / PDF / MD / TXT** — Seb extracts shall-statements and proposes a requirement list; you accept it before it lands.

Gap analysis runs automatically once requirements land. It walks the codebase, finds traces to each requirement, and writes verdicts on two axes:

* **Code**: `resolved` / `stub` / `broken` / `no_trace`
* **Test**: same scale

Verdicts appear on the **Verification** page (`/requirements`) as a status board with a coverage bar. Click any card to read the verdict, resolve ambiguous traces, or hit **Launch agent** to fix the gap. Launching opens the same New Agent chat as [step 3](/guide/run-agents), pre-scoped to that requirement.

Hit **Sync** to rerun. Hideout also auto-reruns when a trace points at a file that's changed since the last run.

## SEB.md

An auto-generated project brief — what the project is, the major subsystems, conventions to follow. Generated on first connect from the repo and kept current as the codebase evolves. Edit it directly as Markdown; Seb reads it before every task.

<Tip>
  Treat SEB.md like an onboarding doc for a new teammate. The more concrete it is about how *your* codebase is laid out, the less Seb has to guess.
</Tip>

## Next

[Guide → 3. Run agents](/guide/run-agents).