Where do these guides come from?

From the product. These pages read the counts, the stage names, the scopes and the plan limits from the same catalogs the app runs on, and the screenshots come from the running interface, so a change in the product shows up here.

Is there a reference for the API?

Yes. The API and MCP reference lists every endpoint under /v1 and every MCP tool. It also covers scopes and rate limits by plan, each error code the API can return, and the signed webhook payload.

Can an agent read these docs?

Every guide is plain HTML with headings, tables and FAQ blocks, and the site publishes an llms.txt that lists them. The MCP server's own instructions tell an agent the order to call its tools.

Something on a page is wrong. Where do I say so?

Write to hello@writerdean.com with the page and the section. Each guide shows the date of its last update.

Documentation

How WriterDean works, stage by stage

Set up a brand, run the pipeline, read the trace, publish. The guides here come from the product's own code and copy, so what they say is what the app does.

Start with the first hour API and MCP reference

Everything the app does is written down here, from the first brief to the sign off.

Start here

The first hour, in four steps

Each step links to the part of the getting started guide that walks it.

1Create the accountEmail, a one time code, Google or GitHub. The first sign in creates your workspace on the free plan.Read the step
2Build the brand documentGive the wizard your website and it drafts the twelve sections in under a minute. Check the proof points by hand.Read the step
3Run the first piecePick a template, write two sentences of notes, approve the outline when the run pauses for you.Read the step
4Read it beside its trace, then publishThe editor shows the draft with every stage that made it. Connect a channel and schedule it from the calendar.Read the step

The pipeline

Nine stages, and what each one leaves behind

Every long form run walks these stages in this order. The ladder fills the way the run page fills, with the skills and the tokens of each stage, and the artifact the live demo's run left.

One run, nine stages Stage 1 of 9.

69,889 tokens and $0.012 for the captured run

1
Brand Context
product-marketing
The twelve sections of the brand document every later stage reads. No model call.
2
Research
content-strategy
A research brief: intent, questions, entities, gaps, and query variants, with every fact sourced or marked.6,734 tokens
3
Strategy
content-strategy
Buyer stage, a score, a place in the hub and spoke map, and ten title options.6,930 tokens
4
Outline
content-strategy, copywriting
Headings in sentence case, answer block positions, FAQ questions and a target length, plus the internal links to place.9,011 tokens
5
Draft
content-strategy, copywriting
The full piece, with a direct answer up front and a source on every number and claim.9,701 tokens
6
SEO layer
ai-seo, seo-audit, schema
The revised article plus its title, meta description, slug and share text, with the FAQ and the JSON-LD.18,841 tokens
7
Copy edit
copy-editing
Seven sweeps for clarity, voice, proof, and specificity, with no facts added.7,402 tokens
8
Humanize
humanizer
The final text, rewritten for every tell and scored again by the lint.11,270 tokens
9
Quality gates
no model call
Gate results: humanizer lint, SEO preservation, readability, facts, links, alt text, safety.