Draft Getting Started overview page for docs

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

docs/getting-started/overview.mdx

@@ -3,3 +3,75 @@ title: "Overview"
 description: "Why Arc?"
 ---
 
+Arc is the software factory for small teams of expert engineers. It replaces the prompt-wait-review loop with version-controlled workflow graphs that orchestrate AI agents, shell commands, and human decisions into repeatable, long-horizon coding processes.
+
+## The problem
+
+AI coding agents have transformed software engineering productivity, but the surrounding toolchain hasn't kept up:
+
+- **Developers work for the agents.** The prompt-wait-review loop idles engineers while agents run, then demands constant babysitting to course-correct.
+- **Unpredictable agents force oversight.** Non-deterministic guardrails create an explosion of failure modes. Engineers compensate by watching every step.
+- **Verification is overwhelmed.** Agent throughput exceeds human review capacity. CI pipelines designed for pass/fail signals can't keep pace with the volume or nuance of AI-generated code.
+- **Token costs are primed to explode.** ROI per token diverges wildly across tasks, models, and harnesses. Every unnecessary frontier token is one that can't be spent where it matters.
+- **The continuous improvement loop broke.** Data is lost at every sub-process boundary. Organizations can't train LLMs the way they train people, and memory files make no guarantees.
+
+## How Arc solves this
+
+Arc gives you a deterministic harness around non-deterministic AI. You define **workflow graphs** in DOT files that specify exactly what happens, in what order, with which models, and where humans weigh in. Arc handles orchestration, parallelism, model routing, verification, and observability.
+
+<Columns cols={2}>
+  <Card title="Version-controlled workflows" icon="diagram-project">
+    Define workflows as code in Graphviz DOT. Nodes are agents, shell commands, or human input gates. Fan out, loop, branch, and resume — all traceable and repeatable.
+  </Card>
+  <Card title="Multi-model orchestration" icon="microchip">
+    Route tasks to the right model using CSS-like stylesheets. Cross-critique with fresh eyes, delegate simple tasks to fast models, and fail over automatically when providers go down.
+  </Card>
+  <Card title="Human-in-the-loop" icon="hand">
+    Steer while the agent runs, not after. Approval gates, interviews, and steering let you intervene at the right moments without waiting for a pull request.
+  </Card>
+  <Card title="Adaptive verification" icon="shield-check">
+    Combine LLM-as-judge, test suites, third-party tools, and human review. Verifications act as an eval suite tailored to your organization, building confidence over time.
+  </Card>
+  <Card title="Observability" icon="magnifying-glass-chart">
+    Every tool call, agent turn, and shell command is captured in a unified event stream. Query run data with SQL via DuckDB and generate automatic retrospectives.
+  </Card>
+  <Card title="Open source" icon="code-branch">
+    Licensed under AGPL. Written in Rust with minimal dependencies. Runs on a single node with no databases to set up.
+  </Card>
+</Columns>
+
+## What a workflow looks like
+
+Workflows are defined in Graphviz DOT, a simple graph description language:
+
+```dot
+digraph PlanImplement {
+    graph [goal="Plan, approve, implement, and simplify a change"]
+
+    start [shape=Mdiamond, label="Start"]
+    exit  [shape=Msquare, label="Exit"]
+
+    plan      [label="Plan", prompt="Analyze the goal and codebase. Write a step-by-step plan.", reasoning_effort="high"]
+    approve   [shape=hexagon, label="Approve Plan"]
+    implement [label="Implement", prompt="Read plan.md and implement every step."]
+    simplify  [label="Simplify", prompt="Review the changes for clarity and correctness."]
+
+    start -> plan -> approve
+    approve -> implement [label="[A] Approve"]
+    approve -> plan      [label="[R] Revise"]
+    implement -> simplify -> exit
+}
+```
+
+This workflow plans a change, asks a human to approve it, implements the plan, and simplifies the result. If the human rejects the plan, the agent revises it. The entire process is version-controlled, repeatable, and resumable.
+
+## Next steps
+
+<Card
+  title="Quick Start"
+  icon="rocket"
+  href="/getting-started/quick-start"
+  horizontal
+>
+  Install Arc and run your first workflow in minutes.
+</Card>