Grab Adam's free build guide for building, packaging, and selling your first AI knowledge base: https://corey-ganim.kit.com/a49b7bd19d
Adam Sandler from Viable Edge is back on the pod, and this time he walks through the full blueprint for selling AI-powered knowledge bases as a service. The pitch to clients is simple: I will clean up all of your company knowledge, organize it, structure it, and turn it into a living asset that powers every AI tool you use going forward. No Obsidian, no RAG, no vectors. Just markdown files on a local machine. Adam builds the whole thing live on screen using Claude Code with a fictional company, shows the seven note types every knowledge base needs, and breaks down the pricing tiers from a $750 audit to a $4,700 premium build. The real insight is that the knowledge base is not the end product. It is the foundation that opens the door to every future engagement with that client.
Join our AI Operator Academy Community where we help entrepreneurs start and scale a profitable AI services business: https://www.skool.com/aioperatoracademy/about
Timestamps
01:18 – Why Adam leads with the knowledge base on every engagement
02:55 – Knowledge base as a tripwire offer, same concept as the AI audit
04:12 – The pitch: clean up your company knowledge and make it a living asset
04:57 – You don't need Obsidian or RAG to start, markdown files are enough
06:12 – Why a provider-agnostic knowledge base protects clients from platform risk
07:00 – Token cost savings as a selling point for teams and enterprise
08:45 – Anthropic enterprise going to pay-as-you-go and why that matters
09:34 – The seven durable note types every knowledge base needs
13:19 – How the seven types simplify the what do I include question
14:13 – The spine concept: one foundational schema everything ladders up to
15:58 – Module-by-module walkthrough of Adam's mini course
16:58 – No client needs to touch Claude Code, this works in Cowork
18:06 – Coaching moments as value-adds during the build
18:29 – Live build: establishing the foundation with discovery prompts
20:16 – The discovery questions mapped to the seven note types
22:00 – Applying structure: from raw answers to schema
25:31 – Summary of the build process so far
27:01 – How to maintain the knowledge base after the initial build
27:38 – Pricing: audit, core build, and premium build tiers
29:09 – The knowledge audit as a foot-in-the-door offer
30:10 – Positioning options: department-by-department builds for larger clients
30:52 – The first knowledge base files and the index file
34:50 – Three layers of context: hot, durable, and disposable
35:47 – Setting up Cowork global instructions to recognize the knowledge base
38:33 – The ingest skill: automating information intake from multiple sources
39:47 – The curate skill: weekly health checks on the vault
41:26 – Provider portability as a major selling point
42:18 – Handling sensitive client information
43:41 – Upselling from the knowledge base: let the data tell you what to build next
46:16 – Light bulb moment: the knowledge base recommends its own next project
47:08 – Value-add opportunities: competitive insights, call transcript analysis
48:25 – Why solo practitioners can compete with startups in this space
50:09 – Second brain as a service is going to be one of the hottest AI offers
51:58 – Where to find Adam and the free guide
Key Points
The knowledge base solves the foundational problem every AI engagement runs into: where is the client's information and how is it organized? Starting here sets up every future project to succeed and gives you a reason to keep working with the client.
There are seven durable note types that form the starting schema for any client: snapshot, people and contacts, ongoing conversations, preferences and rules, project history, decisions and rationale, and open loops. This framework answers the question of what to include and what to leave out.
The spine is the one foundational piece of data everything else ladders up to. For most clients, it is their annual goals or objectives. Every other note in the knowledge base should be traceable back to it.
No fancy technology is required to start. The entire build runs on markdown files. No Obsidian, no RAG, no vector databases. You can add sophistication later, but a simple implementation still delivers massive value and is easy to sell because there is zero technical friction for the client.
The sales flow mirrors the AI audit model: a $750 knowledge audit maps where the client's information lives and what the schema should look like, then upsells into a $3,500 core build or $4,700 premium build. The audit fee gets credited toward the build.
Two skills keep the knowledge base alive after the initial build. The ingest skill automatically processes new information from sources like Gmail, calendar, and an inbox folder. The curate skill runs weekly to flag stale notes, contradictions, open items, and gaps.
The biggest upsell comes from the knowledge base itself. Once all of a client's context is in one place, you can query it for the top opportunities to implement AI next, and the client does not need to be sold because the data is making the case.
If this episode was valuable to you, it would mean a lot if you left a rating and review on Apple Podcasts or Spotify. It helps more entrepreneurs find the show.
FIND ME ON SOCIAL
X/Twitter: https://x.com/coreyganim Instagram: https://www.instagram.com/coreyganim/ LinkedIn: https://www.linkedin.com/in/coreyganim/ YouTube: https://www.youtube.com/@coreyganim
FIND ADAM ON SOCIAL
YouTube: https://www.youtube.com/@viableedge
Brasil