# Branchpost

> Generate audience-aware MDX drafts that respect your components, frontmatter, and repo structure. Branchpost opens blog-file PRs you control.

## Pages

- [Home](https://branchpost.dev/): Branchpost overview, how it works, and pricing highlights.
- [About](https://branchpost.dev/about): Why Branchpost exists and what we believe about AI-assisted publishing.
- [Pricing](https://branchpost.dev/pricing): Credit-based plans, top-ups, and FAQ.
- [Changelog](https://branchpost.dev/changelog): Versioned release notes.
- [Blog](https://branchpost.dev/blog): Articles on developer publishing, AI-assisted content, and the GitHub-as-CMS workflow.
- [Security](https://branchpost.dev/security): GitHub scopes, encryption, subprocessors, responsible disclosure.
- [Privacy](https://branchpost.dev/privacy): How we collect, use, and share your data.
- [Terms](https://branchpost.dev/terms): Terms of Service.
- [RSS Feed](https://branchpost.dev/feed.xml): Subscribe to new posts.

## Blog Posts

- [Why blog posts belong in your monorepo, not a SaaS dashboard](https://branchpost.dev/blog/blog-posts-belong-in-monorepo): Content is code-adjacent. It ships with releases, needs review, and benefits from version history. Here's why the dashboard is the wrong surface for AI writing tools, and what changes when drafts arrive as pull requests instead.
- [GitHub App permissions: designing for least privilege when AI writes to your repo](https://branchpost.dev/blog/github-app-permissions-least-privilege): The exact scopes Branchpost requests from GitHub, why each one is justified, and the scopes we deliberately refused even when they would have made the product easier to build.
- [Frontmatter as a contract between AI and your CMS](https://branchpost.dev/blog/frontmatter-as-a-contract): Why the YAML block at the top of every MDX file is the most important interface in an AI content pipeline, and what breaks when you treat it as decoration.
- [How to review an AI-generated draft before you merge it](https://branchpost.dev/blog/how-to-review-ai-drafts): A code-review mental model, ported to prose. What to read for, what to ignore, and where AI drafts most often fail in ways line-by-line review misses.
- [The cost shape of an AI content pipeline](https://branchpost.dev/blog/cost-shape-ai-content-pipeline): Where tokens actually go in a Branchpost generation run, why retries dominate the bill more than people expect, and how prompt caching changes the math.
- [Writing prompts that produce code-aware blog drafts](https://branchpost.dev/blog/writing-code-aware-prompts): How Branchpost turns repo signals into prompt inputs so drafts reference real files, real commits, and real decisions instead of generic AI filler.
- [Why we make every blog draft a pull request](https://branchpost.dev/blog/why-prs-are-the-review-surface): Review tools already exist for code. They're called pull requests. Here's what happens when you point that same machinery at content — and why it changes the tone of AI-assisted writing.
- [How we cut our blog build time from 9s to 1.4s](https://branchpost.dev/blog/how-we-cut-blog-build-time): A walkthrough of the bottlenecks we found in our MDX pipeline and the cache strategy that fixed them.
- [Publication context: the missing input for AI writing tools](https://branchpost.dev/blog/publication-context): Why 'site type, audience, tone, claims to avoid' matters more than any prompt-engineering trick.
- [Notes against AI slop in developer blogs](https://branchpost.dev/blog/notes-against-ai-slop): A practical taxonomy of the patterns we filter out — and the ones that need a human to catch.