What is a marketing knowledge base?
A marketing knowledge base is the store of what a company knows about its product, market and customers, kept fresh by feeds. Why one store beats many.
By Max Gillespie, founder of Oetzi
A marketing knowledge base is the store of what a company knows that a post, a reply or a pitch might need: what shipped and when, the numbers the company can stand behind, what customers say to support, what the trade press and the research say about the category. It is different from a content library, which holds what was published, and from a brand guide, which holds how to say things. The knowledge base holds what is true, with a date and a source, so the next piece of content can be specific instead of generic.
What goes in a marketing knowledge base?
Four kinds of thing, and they age differently. Facts about the product and the company, which stay true until someone changes them. Documents, such as a paper, an article or a page, which are worth citing for a month or three. Events, such as a release, a deal, a support conversation, which matter for days. And metrics, such as a customer count or a page's traffic, which are stale within a week. A good store knows the difference, so a two-year-old customer count never outranks last week's.
How does it stay fresh?
By feeding it rather than filling it. Typing facts by hand works for a dozen. After that, the store needs feeds: a news search on a schedule, a library like Alexandria for research and structured data, and the company's own tools through an integration layer like Pipedream, so a release or a milestone writes itself into the store the hour it happens. Oetzi keeps one such store per workspace on its Brain Sources tab and reads it before every draft (knowledge sources).
Why one store and not one per project?
Because every use asks the same question: what do we know that is close to this, and how fresh is it. That is one query over one table with a "which feed wrote this" column. Separate stores per campaign or per team multiply the plumbing and split the answer. The Stanford retrieval-augmented generation literature reached the same conclusion for language models: one index, ranked by relevance, beats hand-routed silos.
Questions
Is a marketing knowledge base the same as a CRM?
No. A CRM stores who, a knowledge base stores what. The two meet when a deal won in the CRM becomes an event in the knowledge base and then a customer story in a post.
How does it reach a post?
Retrieval. The topic of the post is embedded, the closest fresh items come back, and the writer, human or model, gets them as a short dated list. In Oetzi that list is the "what we know" block on every drafting run.
Oetzi is an AI growth hacker for founders. It finds the threads where people ask for a product like yours, checks whether the AI engines recommend you, and drafts replies, posts, and short video in your voice. You approve everything. 100 credits included, 10 free to try with no card, 50 bonus credits with the first payment.
- GEO vs AEO vs SEO: what is the difference?SEO earns a rank in search results, AEO earns the answer box, GEO earns a place in an AI engine's written answer. How the three differ and where a founder should spend effort.
- Share of model vs share of voiceShare of voice counts how much of a category's media mentions you. Share of model counts how often AI engines name you. How the two differ and which one to track.
- What is a "what do you use" thread?A what do you use thread asks a community which tool to pick. How these threads work, why the first hour decides the shortlist, and how to answer one well.
- What is a buying intent signal?A buying intent signal is a public post showing someone is actively choosing what to buy. What they look like, where they appear, and how to answer one well.
- What is a keyword alert?A keyword alert is a standing search that pings you when a word appears in a public post. What alerts do well, why people mute them, and how to make them work.