DocsAI — Full PRD

DocsAI — Product Requirements Document

One-liner

AI-native client deliverable portal for agencies. AI agents publish markdown → clients see branded, access-controlled pages with view tracking.

The Problem

Every company using AI agents (Claude Code, Cursor, Copilot) generates markdown files that sit in git repos, invisible to anyone who doesn’t cat files in a terminal. The output is trapped.

For Cofoundy specifically:

• Claude Code writes meeting notes, brand guides, proposals, project docs, deliverables — all as .md files
• Those files live in repos that clients never see
• Today we send PDFs on WhatsApp or links to Google Docs — things get lost, there’s no single source, no branding, no access control
• Team members write CLAUDE.md files that are rich with knowledge, but nobody reads them because raw markdown in a repo is hard to navigate

For the market broadly:

• Every agency, consultancy, and dev shop using AI coding tools has this problem
• The gap between “AI generated a great document” and “client can see it professionally” is manual work: copy to Notion, export to PDF, upload to Drive, send link
• That manual step kills the speed advantage of AI

The Insight

Documents shouldn’t be edited by humans anymore. They should be authored by AI agents and published automatically. The human’s job is to review, approve, and share — not to format, upload, and manage links.

The defensible version isn’t “we render markdown better” — it’s “we are the only platform purpose-built for agencies to publish AI-generated deliverables for clients, with workflow depth that documentation platforms won’t build.”

Analogy: DocSend meets GitBook, but for AI-native agencies. Content stays in git (zero vendor lock-in), platform handles branding, access control, view tracking, and client-facing workflows.

Competitive Landscape (March 2026 Research)

Why not just use an existing tool?

The whitespace

No existing tool combines: markdown-from-git + branded client pages + view tracking + approval workflows + AI agent API. GitBook has the tech but not the workflow. Qwilr has the workflow but not the tech. We need both.

Emerging signal

5+ Show HN projects in 2025 solving “markdown → shareable URL” (mdto.page, md2.website, wrds.cc). One commenter explicitly requested an API “for agents to share content.” An OSS project (waynesutton/markdown-site, 598 stars) positions itself as “publishing for AI agents.” None became SaaS products with RBAC or agency workflows.

Market Sizing

The initial market is narrow but growing explosively with AI agent adoption.

Users & Personas

Priority order: AI Agent > Client reader > Team member > Public visitor

Core Concepts

Document

A markdown file in a project folder with YAML frontmatter:

src/content/docs/{project}/{slug}.md

---
title: "Brand Guidelines — Acme Corp"
role: client          # team | client | public
version: 3
author: andre
created: 2026-03-22
tags: [branding, deliverable]
---

# Brand Guidelines
...

Note: project is determined by the folder name, not frontmatter. This prevents slug collisions across projects.

Project Space

Documents are grouped by folder. Maps 1:1 to Cofoundy’s project structure:

• docs/cofoundy/ → docs.cofoundy.dev/cofoundy/ — internal docs (team only)
• docs/client-acme/ → docs.cofoundy.dev/client-acme/ — client deliverables
• docs/blog/ → docs.cofoundy.dev/blog/ — public content

Access Roles

What We Have Now (MVP — Built 2026-03-22)

Goal

Cofoundy uses it internally for 1 week. Claude Code can publish. Team can read.

Shipped

1. Astro 6 static site with Zod-validated content collections

   • Full markdown rendering: GFM, syntax highlighting (Shiki dual-theme), tables
   • Mermaid.js diagram rendering (client-side, theme-aware)
   • Table of contents auto-generated per doc
   • Nested folder routing: src/content/docs/{project}/{slug}.md → /{project}/{slug}

2. Cofoundy branding

   • Header: Cofoundy logo (white/dark variants) + “docs” label
   • Footer: isologo + cofoundy.dev link
   • Fonts: Space Grotesk (headings), Inter (body), JetBrains Mono (code)
   • Colors: brand tokens matching @cofoundy/ui (#46A0D0 primary, #020b1b dark bg)
   • Dark/light theme switcher (persisted to localStorage, respects system preference)
   • Print-friendly CSS (clean PDF via browser print)

3. Frontmatter schema (validated at build time)

   • title (required), role (required: team/client/public), version, author, created, tags
   • Project derived from folder name — no frontmatter duplication, no slug collisions

4. Deploy: Cloudflare Pages

   • Repo: github.com/cofoundy/docs-ai (private)
   • Production: docs-ai-dc7.pages.dev
   • Custom domain: docs.cofoundy.dev (live, SSL provisioned)
   • Manual deploy via wrangler pages deploy dist

5. /publish skill (cofoundy-toolkit v1.9.1)

   • Input: path to .md file + --project + --role
   • Reads source, generates/merges frontmatter, copies to docs/{project}/{slug}.md
   • Commits + pushes → deploys
   • Returns live URL
   • Tested e2e: published PRD from repo to live site

6. Index pages

   • Global index: grid of all projects with doc counts + role badges
   • Per-project index: doc list sorted by date with role badges

Not yet done (MVP remaining)

• GitHub Actions auto-deploy (currently manual wrangler pages deploy)
• Cloudflare Access policies for role: team / role: client protection

Not in MVP

• Web UI for editing
• Versioning UI (version field exists in frontmatter)
• Client auth beyond Cloudflare Access email lists
• PDF download button
• Search
• Analytics
• API (skill uses git push directly)

V1 Features (Month 1 — After Internal Validation)

Goal

First client sees their deliverables on the platform. Replace “PDF on WhatsApp” workflow.

1. Client spaces

   • Client gets a link: docs.cofoundy.dev/client-acme/
   • Sees only their project’s role: client docs
   • Branded with Cofoundy identity (white-label in V2)

2. Versioning

   • Frontmatter version: N tracked
   • “Last updated” shown on page
   • Version history dropdown (git-backed, rendered in UI)

3. Simple REST API

   • POST /api/docs — create/update a document (markdown body + frontmatter)
   • GET /api/docs/{project}/{slug} — get rendered HTML or raw markdown
   • GET /api/docs/{project} — list docs in project
   • Auth via API key per team
   • This is what the /publish skill calls instead of git push

4. PDF download button

   • “Download PDF” on every doc page
   • Uses same rendering + Cofoundy footer/header
   • Reuse /md2pdf infra from toolkit

5. Search

   • Full-text search across all accessible docs
   • Pagefind (static search, no server needed)

V2 Features (Month 2-3 — If Traction)

This is where we diverge from a generic docs platform into an agency deliverable portal.

1. View analytics — “Client opened the proposal at 3:47 PM, spent 4 minutes on page 2.” This is the DocSend killer feature that no markdown-native tool offers. Enables follow-up timing and engagement signals.

2. Comments & approval — client can comment on a doc. Team gets notified. “Approve” button for deliverables that need sign-off. Replaces the “reply to this email with your approval” workflow.

3. Notifications — email/WhatsApp when a new doc is published to a client’s space. Configurable per project.

4. White-label — client’s own branding on their space. Custom domain: docs.acmecorp.com → their project space. This is the enterprise upsell.

5. Web editor — simple markdown editor for team members. Monaco/CodeMirror with live preview. Not a priority until non-technical team members complain.

6. LaTeX compilation — /publish --type latex compiles .tex → branded PDF, uploads to platform. No local texlive needed. Pain point: LaTeX deps are hard to install, compilation is slow and error-prone. Nobody else offers this in a markdown-native platform.

7. Multi-tenant SaaS — other agencies sign up, get their own workspace. This is the startup inflection point.

Technical Architecture

MVP (live now)

Claude Code ──/publish skill──► docs-ai repo (Astro 6 + .md content collections)
                                     │
                                git push to github.com/cofoundy/docs-ai
                                     │
                            wrangler pages deploy dist
                                     │
                              Cloudflare Pages CDN
                                     │
                         docs-ai-dc7.pages.dev (→ docs.cofoundy.dev)
                                     │
                    ┌────────────────┼────────────────┐
                    │                │                │
                 /team/           /client/         /public/
              (CF Access)      (CF Access)      (open access)

Stack: Astro 6, Shiki, Mermaid.js, Cloudflare Pages, GitHub

V1 adds: GitHub Actions auto-deploy, Cloudflare Access policies, API server (Workers).

V2 adds: Database (D1/Turso) for multi-tenant, user management, analytics.

Risks (from March 2026 deep research)

Open Questions

1. Name — “DocsAI” is generic. Need something sharper. Candidates: Folio, Publi, Inkwell, Quill?

2. Positioning — Research says “DocSend for AI-native agencies” is more defensible than “Vercel for documents.” Validate with agencies in Week 3.

3. Pricing model — Benchmarks: GitBook $65/site/mo, Mintlify $300/mo, DocSend $10-65/user/mo. Likely: free for public, $29/mo per client workspace, $99/mo for white-label.

4. File downloads beyond PDF — should client spaces also serve raw files (zip of assets, brand packages)? This edges into “file hosting” territory.

5. Build vs. integrate — should the web editor (V2) be built from scratch or embed an existing OSS editor (HackMD, CodiMD)?

6. When to pursue as startup vs. keep as internal tool — the go/no-go decision in Week 4 of the validation framework is critical. Don’t over-invest before signal.

Validation Framework

Week 1: Build MVP + Internal Dogfood (started 2026-03-22)

• Build the Astro site + /publish skill
• Deploy to Cloudflare Pages (live at docs-ai-dc7.pages.dev)
• Test e2e: publish PRD via /publish workflow → live URL
• Custom domain docs.cofoundy.dev live (CNAME + SSL provisioned 2026-03-23)
• Cofoundy branding: logo, dark/light theme switcher, brand tokens
• Unified Cloudflare API token (CLOUDFLARE_API_TOKEN) — settings.json, GitHub org secret, .env.required
• Set up GitHub Actions auto-deploy on push
• Publish 10 real Cofoundy docs (meeting notes, project briefs, deliverables)
• Track: how often does the team use it vs. going to the repo directly?

Week 2: First Client Test

• Pick 1 active client
• Publish their deliverables to a client space
• Share the link instead of sending PDF on WhatsApp
• Track: does the client actually open it? Do they ask questions about it?

Week 3: Market Signal

• Talk to 5 other agencies/consultancies
• Ask: “How do you share deliverables with clients today?”
• Ask: “If Claude Code could auto-publish docs to a branded page with a link, would you use it?”
• Track: excitement level (1-10), current pain, willingness to pay

Week 4: Go/No-Go Decision

• If internal usage is high + client liked it + 3/5 agencies show interest → Go: build V1, pursue as product
• If internal usage is medium + client indifferent → Pivot: keep as internal tool, don’t productize
• If nobody uses it → Kill: the problem isn’t real enough

Why This Could Be a Startup

1. Timing — AI coding agent adoption is growing 25-28% CAGR. Cursor went $0→$2B ARR in 18 months. The volume of AI-generated markdown is exploding, and the “last mile” to non-technical stakeholders will only get worse.

2. Wedge — Start with agencies (Cofoundy = customer zero). The sharpest pain: multiple clients, multiple projects, professional output matters. No markdown-native tool serves this workflow today.

3. Counter-positioning — Content stays in git, not proprietary blocks (vs Notion) or a managed editor (vs GitBook). Zero vendor lock-in on content. For teams already working in IDEs with AI agents, this aligns with existing workflows.

4. Moat is workflow, not tech — Tech is commodity (1-3 months to replicate). Moat is agency workflow depth: per-client spaces, view tracking, approval flows, white-label — plus AI agent ecosystem positioning. Once /publish targets this platform from every major agent, switching costs are real.

5. Revenue — Free for public docs. $29/mo per client workspace. $99/mo for white-label + custom domains. Benchmarked against GitBook ($65/site), DocSend ($10-65/user), Mintlify ($300/mo).

6. Expansion — Agency deliverables → consulting firms → legal (contracts) → marketing (content) → any team that uses AI to write for external stakeholders.

What the research validated

• Mintlify ($10M ARR, 150% NRR, 10x YoY) proves “markdown in → beautiful pages out” works as a business
• 5+ Show HN projects in 2025 solving this exact problem — demand is real, no winner yet
• A consultant (Dale Rogers) reported reducing a 20-document engagement from weeks to days using markdown→deliverable automation — the exact workflow we enable

What the research warned

• 6-12 month window before incumbents close the gap
• “Thin wrapper” risk — VCs avoid products that sit as a rendering layer without owning content or distribution
• Must build agency workflow depth fast to be more than a rendering layer