# What happens between your request and a piece you'd put your name on. > How Contengi splits work between GPT-6 Luna, Claude, and Jev, the four filters that strip AI slop from every draft, and what each piece costs to run. Source: https://contengi.com/how-it-works How it works Contengi runs a small team of models, each on the job it does best, with your knowledge base in the middle and four filters between the first draft and you. This is the whole flow. [Request beta access](https://contengi.com/beta-access)See the models[Watch the demo](https://contengi.com/demo) ## It all starts with your knowledge base Every model in Contengi reads from the same brand file: your strategy, point of view, audience, tone of voice, writing guide, hard rules, approved sources, and sitemap. We build it with you during setup, and it's the reason a quick LinkedIn post and a 2,000-word guide sound like the same brand. Each model gets the slice it needs and nothing more. The writer gets your voice and rules, research gets your competitors and approved domains, and the link step gets your sitemap. Less to read means less to pay for, and less for a model to get distracted by. ## The right model for each job One model doing everything is either expensive or sloppy, so Contengi splits the work. A fast model does the looking up, Claude makes every call that needs taste, a checking model reads what comes out, and plain code handles the rules with one right answer. LeadOn us ### OpenAI GPT-6 Luna - Runs the conversation in the Marketing Assistant - Looks things up in Search Console, Analytics, your knowledge base and your library - Picks the right tool and writes the brief for the writer Fast and cheap, so it takes the legwork. It never writes a word your readers see. WriterYour key ### Anthropic Claude - Every draft, rewrite, and edit - Blog research and fact checks, workflows, and automations - The brand voice and anti-slop passes Anything that needs judgement runs here, with your full brand voice loaded. CheckerOn us ### TypeSafe Jev - Reads finished text for the patterns that give AI writing away - Checks it against your brand's own never-rules - Points at the exact sentences to fix A model built to check writing, so it gives a straight yes or no for each pattern. CodeFree ### Plain code - Counts every em dash, emoji, and banned phrase - Tests every link and drops the dead ones - Applies fixes exactly where they were flagged Where a rule is black and white, a model has no business deciding it. What we learned the hard way We tried giving blog editing to the cheaper model too. On a real post it added a TL;DR the article already had and put new content above the title, so editing went straight back to Claude. We tested moving workflow research over as well, and kept it on Claude because checking facts is judgement. The fast model earns its place in conversation and lookups, where it's quick, cheap, and more than good enough. ## How we get the slop out AI writing gives itself away in patterns, and a banned-word list only catches the obvious ones. So every piece goes through four filters, each one catching what the last one can't. 1In the brief Every writer starts with Contengi's anti-slop standard and your brand's hard rules in its instructions. They're on for every brand and can't be switched off. 2The editor's pass Claude re-reads the draft as an editor, strips the patterns it finds, and keeps every fact, example, and link where it was. The length has to stay within 10% of the draft. 3The exact scan Plain code counts every em dash, emoji, and banned phrase, and swaps em dashes for spaced hyphens. No model gets a vote on a rule that is black and white. 4The slop check Jev reads the finished piece for the tells a word list misses, like a sentence that sets up a straw man just to knock it down. It points at the exact sentences, Claude rewrites those, and Jev checks again. A real fix from a real run. Only the flagged sentence changes, so the parts that were already good stay yours. 04 ## The same standard, wherever you write The checks live in one shared pass, so every writer inherits them. Connect Contengi to your own Claude and it hands your Claude the same voice guide, rules, and slop findings, so a draft written there meets the same bar. The Marketing Assistant The SEO blog writer and playbooks Social, newsletter, PR, thought leadership, and YouTube writers Workflows and automations Fix hard rules in the editor Your own Claude, through the Contengi connector ## The cost of running on Contengi Your Claude key pays for the writing, at Anthropic's own prices with nothing added on top. Everything marked included runs on Contengi's bill. What you make Runs on Typical cost An SEO blog post, researched, written, checked, and linked Claude, Jev about $0.40 A thought leadership article Claude, Jev about $0.10 A newsletter issue Claude, Jev about $0.06 A LinkedIn post Claude, Jev about $0.04 An edit to a blog post through the assistant Claude about $0.05 A question to the Marketing Assistant GPT-6 Luna Included A Search Console or Analytics analysis GPT-6 Luna Included An LLM tracking scan, once a month Five AI engines Included Images, 30 a month FLUX Included Measured on real runs with a full-size knowledge base, at Anthropic's September 2026 prices. Longer pieces and heavier research cost a little more, shorter ones less. ## Your data stays yours Writing and editing run on your own Anthropic key, and Anthropic does not train on data sent through its API The included AI runs with zero data retention, so nothing you send it is stored or used for training GPT-6 Luna runs on Microsoft Azure through Vercel AI Gateway, and Jev runs through the same gateway on the same terms Your knowledge base, drafts, and analytics stay in your workspace, and none of it is used to train anything Every provider we use is listed in our [privacy policy](https://contengi.com/privacy). FAQ ## Common questions ### Which AI models does Contengi use? Three, each on the job it does best. OpenAI's GPT-6 Luna runs the Marketing Assistant's conversation and lookups, Anthropic's Claude does every piece of writing, editing, and research that needs judgement, and TypeSafe's Jev checks finished text for AI slop. Plain code handles the rules that are black and white, like em dashes and dead links. ### Do I still need my own Claude key? Yes, for the writing. Drafts, rewrites, and edits run on your Anthropic key, so you always get Claude at full strength on the words your readers see. The assistant's conversation, lookups, and the slop check run on Contengi's own AI, included in your plan. ### What is Jev? A model built to check writing. Contengi asks it a set of yes-or-no questions about a finished piece, one per known AI pattern plus your brand's never-rules, and it points at the sentences that fail. Only those sentences get rewritten. ### Will the slop check change my whole draft? No. It only touches the sentences it flags, and a fix has to match one exact spot in the text or it is skipped. Everything else stays exactly as written, links and formatting included. ### What happens if the included AI runs out? Nothing stops. Your Usage page shows how much of the month you have used, and if you ever use it all, the assistant carries on through your own Claude key until the month resets. ### Does Contengi train AI on my content? No. Your writing runs on your own Anthropic key, which Anthropic does not train on, and the included AI runs with zero data retention. The full list of providers is in our privacy policy. Keep exploring ## Related features and reads In the platform [### Knowledge base The brand file every model reads from.](https://contengi.com/features/knowledge-base) [### Marketing assistant Where the model split does most of its work.](https://contengi.com/features/marketing-assistant) [### Content and SEO agents The writers that run the pipeline above.](https://contengi.com/features/content-agents) From the blog [What is a content operating system?](https://contengi.com/blog/what-is-a-content-operating-system) [Agentic AI content workflows for small business](https://contengi.com/blog/agentic-ai-content-workflows-for-small-business) [How to choose a content engineering tool](https://contengi.com/blog/how-to-choose-a-content-engineering-tool) [See all posts](https://contengi.com/blog) ## See the whole flow run on your brand We build your knowledge base with you during setup, then every model on this page works from it. [Request beta access](https://contengi.com/beta-access) [Try it out](https://contengi.com/demo)