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

# Learn AI-Assisted Software Planning and Review

> Practical, source-backed guides to planning and specifications, agent instructions, Markdown collaboration, code review, and AI-development workflows.

Use these guides to make plans, specifications, agent instructions, review evidence, and handoffs easier to inspect and maintain. Learn pages explain a durable question. Product commands stay in [Open Source](/open-source/), and reusable artifacts stay in [Templates](/templates/).

## Planning and specifications

<CardGroup cols={2}>
  <Card title="What is a product requirements document?" icon="file-signature" href="/learn/planning/what-is-a-product-requirements-document">Define product intent, review it with people and agents, and stop before technical design.</Card>
  <Card title="Approve an AI coding plan before execution" icon="list-checks" href="/learn/code-context/approve-ai-coding-plan-before-execution">Choose the right planning depth, annotate the proposal, and inspect revisions before implementation.</Card>
  <Card title="Plan Diff: see what changed" icon="clock-rotate-left" href="/learn/plan-diff-see-what-changed">Compare revised plans without rereading every unchanged section.</Card>
  <Card title="HTML vs Markdown for agent work" icon="file-code" href="/learn/code-context/ai-agent-html-vs-markdown">Choose durable text or an interactive explainer based on the decision readers need to make.</Card>
  <Card title="Living documentation for AI agents" icon="book-open" href="/learn/code-context/living-documentation-for-ai-agents">Keep current system truth separate from the plans and decisions that produced it.</Card>
</CardGroup>

## Agent instructions

<CardGroup cols={2}>
  <Card title="Write a good AGENTS.md" icon="robot" href="/learn/ai-development/how-to-write-a-good-agents-md">Give agents exact commands, boundaries, and references without creating an instruction dump.</Card>
  <Card title="Compound plan feedback" icon="arrows-rotate" href="/code-context/compound-with-plannotator">Find repeated local feedback and turn the useful patterns into maintained instructions.</Card>
  <Card title="Design a coding-agent handoff" icon="arrow-right-arrow-left" href="/learn/code-context/ai-coding-agent-handoff">Connect returned work to the request, revision, evidence, risks, and next action.</Card>
</CardGroup>

## Markdown and document collaboration

<CardGroup cols={2}>
  <Card title="Annotate a website or HTML file" icon="browser" href="/learn/annotate-any-web-page-or-html-file">Import a URL or render local HTML for agent feedback, or use App Notes to annotate a live page.</Card>
  <Card title="Understand AI-generated code before shipping" icon="magnifying-glass" href="/learn/code-context/understand-ai-generated-code-before-shipping">Connect intended behavior, implementation, validation, and current documentation.</Card>
</CardGroup>

## Code review

<CardGroup cols={2}>
  <Card title="Local diff review for coding agents" icon="code-branch" href="/learn/local-diff-review-for-coding-agents">Return line-specific feedback from a local browser diff.</Card>
  <Card title="What is a revision diff?" icon="code-compare" href="/learn/code-review/what-is-a-revision-diff">Understand cumulative review across pushes, rebases, and force-pushes.</Card>
  <Card title="What are code review artifacts?" icon="images" href="/learn/code-review/what-are-code-review-artifacts">Use screenshots, video, HTML, Markdown, and other evidence beside code.</Card>
  <Card title="Review pull request artifacts" icon="photo-film" href="/learn/code-review/review-pull-request-artifacts">Check whether visual and operational evidence matches the current revision.</Card>
  <Card title="Why AI pull requests are harder to review" icon="robot" href="/learn/code-review/why-ai-generated-pull-requests-are-harder-to-review">Control review load without trusting a generated summary as proof.</Card>
</CardGroup>

## AI-development workflows

<CardGroup cols={2}>
  <Card title="Stay in the loop and own quality" icon="shield-check" href="/learn/ai-development/stay-in-the-loop-own-quality">Keep human attention at the points where intent becomes code and code becomes a shipping decision.</Card>
  <Card title="What is an AI artifact?" icon="shapes" href="/learn/ai-development/what-is-an-ai-artifact">Distinguish inspectable outputs from chat responses and source records.</Card>
  <Card title="What is context rot?" icon="brain" href="/learn/ai-development/what-is-context-rot">Recognize when more context reduces an agent's ability to use the right evidence.</Card>
  <Card title="What is an LLM codebase wiki?" icon="book" href="/learn/ai-development/what-is-an-llm-codebase-wiki">Use generated repository maps without confusing them with maintained authority.</Card>
  <Card title="Long-horizon tasks for AI agents" icon="route" href="/learn/ai-development/what-are-long-horizon-tasks-for-ai-agents">Preserve state, evidence, and stop conditions across long-running work.</Card>
  <Card title="Run an AI agent night shift" icon="moon" href="/learn/ai-development/how-teams-run-ai-agent-night-shift">Prepare a bounded goal and inspect real outputs the next morning.</Card>
</CardGroup>

*Reviewed July 18, 2026. Maintained by the Plannotator documentation team.*