Content engineering platform

The content engineering platform you don't have to build first.

Content engineering is the knowledge base, agents, workflows, and publishing that turn one idea into a week of on-brand content. Contengi ships every piece of it ready to run, so you bring the strategy and skip the six-month build.

Request beta accessInteractive demo$50 / MONTH · BYOK · NO LOCK-IN
Trusted by
Flux RoboticsLattéanuahCXLFiskalRoiSPRMRKT
Weekly thought leadership
Runs every Monday at 7am
Running
Fetch this week’s transcript
get_transcript · weekly-standup.md
Compose the thought leadership draft
search_console · knowledge_base
Wait for your approval
Email the summary
Summary lands in your inbox when it finishes.

Definition

What is a content engineering platform?

A content engineering platform packages the systems a content engineer would otherwise build by hand. A structured brand knowledge base, an AI agent for each format, workflows that chain research, drafting, checking, and publishing together, and the data connections that tell you what to write next.

Contengi is one, built for founders, solo marketers, and small teams who know what good content looks like and don't have an engineer to spare. Think of it as Canva for agentic content: the hard parts are absorbed, and the output still looks like it came from a team of 10.

Already wired in Contengi

A brand knowledge base every agent reads
Agents for blogs, social, email, PR, and video
Workflows with approval gates, on a schedule
Slop filters and your hard rules on every draft
Publishing to your site, plus Search Console and GA4

The whole stack, layer by layer.

Every layer is what you would build yourself in Claude Code, with scripts, handoffs, and a lot of weekends. Here it's built, tested on real brands, and kept up to date when the models change.

Three ways to get a content engineering stack.

Build it yourself

First on-brand draft
Weeks of prompts, scripts, and handoffs
Skills you need
Claude Code, APIs, and prompt design
Who keeps it running
You, every time a model or API changes
Brand voice
As good as your prompts on the day
Cost
Your time plus tokens

Enterprise content platform

First on-brand draft
Weeks, often with a solutions team
Skills you need
An ops person to configure the workflows
Who keeps it running
The vendor, on their roadmap
Brand voice
Brand kits and style settings
Cost
Priced for marketing departments

Contengi

First on-brand draft
Days, after one working session on your knowledge base
Skills you need
Knowing what good content looks like
Who keeps it running
We do, and model updates land without you touching a thing
Brand voice
A knowledge base plus hard rules, checked on every draft
Cost
$50 a month plus Claude tokens at cost

Agents for every format, all running on one brand brain.

Marketing assistantCHAT
Brief it in plain English. It picks the tools and files.

The assistant reads your knowledge base, your Search Console data, and the live web before it answers. You describe the outcome you want and it decides which tools to call, then shows you every call it made.

Reads the knowledge base before it writes a word
Calls Search Console, web search, and your files
Every tool call is shown, not hidden
SEO blog writerBLOG
Keyword in, researched article out, published to your site.

Queue a keyword or a topic and the writer researches, drafts, lints against your hard rules, resolves every link, and publishes to your site. Updates to an existing post go back to the same URL.

Editorial and listicle playbooks
Hard-rule linter runs before you see the draft
Publishes and updates at the same URL
Social writerSOCIAL
One idea, reshaped per platform, in your cadence.

One argument becomes a LinkedIn post, an X thread, and a short-form script, each written to the platform's rhythm rather than pasted across all three.

Per-platform length and cadence
Same argument, not the same sentences
Banned phrases enforced everywhere
NewsletterEMAIL
A weekly issue assembled from what you shipped.

It assembles an issue from the week's published work, adds the context a subscriber needs, and leaves the send button to you.

Built from posts you actually published
Your tone of voice file, applied
Nothing sends without your approval
PRPRESS
Announcements written the way trade press reads them.

Announcements structured the way a trade journalist reads them: the news in the first line, the proof underneath, quotes that sound like a person.

News first, narrative second
Quotes drawn from your transcripts
Boilerplate held in the knowledge base
TranscriptsAUDIO
Turn a call into source material the agents can use.

Drop in a call or an interview and it becomes a file in the knowledge base, with your own phrasing preserved for every agent to draw on later.

Calls, interviews, and voice notes
Your phrasing kept intact
Becomes a knowledge base file
Research studioRESEARCH
Live web and search data, cited, before a word is written.

Live web results and your own search data, gathered and cited first, so the draft argues from evidence instead of from the model's memory.

Live web search with citations
Your Search Console data included
Sources attached to the draft
Thought leadershipOPINION
Your point of view, argued properly, not summarised.

It takes the position you hold, finds the strongest case for it, names the counter-argument, and answers it. Length follows the argument rather than a word count.

Starts from your position, not a consensus
Counter-arguments named and answered
Written to the argument, not to a length

Engineered on Claude, on your own key, at cost.

ClaudeCONTENGI MCP
Queue three blogs for this week from the gaps in Search Console.
contengi.search_console_gaps
contengi.knowledge_base
contengi.queue_blog ×3
Three briefs written against your hard rules and queued. Nothing publishes until you approve it.
Inside Claude
Your agents show up as tools in Claude. Same knowledge base, same hard rules.
Sonnet for volume, Opus for judgment
Drafting and updates run on Sonnet. Strategy, briefs, and the hard calls run on Opus. You are not paying Opus prices to write a meta description.
The tools are already wired
Search Console, web search, your knowledge base, and your site's publishing endpoint are connected on day one. There are no MCP servers for you to run.
Your key, your data, no lock-in
You bring your own Anthropic API key and pay Anthropic directly for tokens, with no markup on top. Export the knowledge base and it is a folder of files you can take anywhere.

The platform comes with a strategist to set it up.

Stefan Maritz
Built by a content marketing veteran
Stefan Maritz
Brand strategist · content engineer
A seasoned brand strategist sits with you, builds the knowledge base from what you already have, and stays on it until the drafts sound like you.
A working session to build the knowledge base
Hard rules and banned phrases written with you
Agents tuned against your first real drafts

FAQ

Common questions

What is a content engineering platform?

Software that packages the systems a content engineer would otherwise build by hand: a structured brand knowledge base, AI agents for each format, workflows that chain them together, quality checks, and connections to your website and analytics. You run it from a normal interface.

How is it different from an AI writing tool?

An AI writing tool gives you a model and a text box. A content engineering platform wraps the model in everything else a publishing operation needs, from the knowledge base it reads to the workflow that researches, drafts, checks, publishes, and later refreshes the piece.

Do I need technical skills to use Contengi?

No. The agents, prompts, model routing, and quality checks are already built. You work in a web app, and your knowledge base is built with you during setup.

Which AI models does Contengi use?

Claude from Anthropic does the writing and every call that needs judgement. A faster model handles conversation and lookups, and a separate model checks drafts for AI patterns. You connect your own Anthropic API key and pay for tokens at cost.

Can I run the platform from Claude?

Yes. The Claude connector puts more than 60 Contengi tools inside your own Claude, so you can brief a blog, edit a live post, or run a workflow from a chat.

How much does Contengi cost?

The beta is $50 a month plus your Anthropic usage, with no seats and no lock-in. The pricing page shows what different levels of API spend produce.

Keep exploring

Related features and reads

Skip the build. Keep the output.

The stack is already engineered. Bring the strategy and the taste, and a strategist sets up the rest with you.