The non-technical track

Business users building skills and simple agents in Advisor or from a chat app.

This track is for business users building in Advisor, or reaching the Company Brain from ChatGPT or Claude via the MCP.

The core idea: the people who do the work understand their pain points better than anyone. Empowering them to build is both the fastest path to useful skills and the single best way to drive cultural change.

This track builds skills and simple agents. Compound agents are the technical track.

Run a recurring hackathon ritual

Bring people together on a regular cadence, in person or virtual, to build. In the session they use Advisor and the MCP to turn their own repeated work into skills and reusable prompts. The act of building together is what creates fluency and buy-in. It cannot be lectured into a team.

Find the thing my team repeats most in monthly close that a skill could take
off our plate.

Turn the best version of how we handle a customer refund into a reusable
skill, and show me the before-and-after workflow.

Choose your surface

Either works, with a clear tradeoff.

Advisor has strong awareness of what makes a good skill and how to spot repeated usage worth formalizing, and it produces a before-and-after diagram of the workflow so the value is visible. Best when you want guidance and a clean artifact.

The MCP brings the Company Brain into the chat app a person already uses, so the build can also draw on the other context and connectors they have there. Best when the work reaches beyond Klarity.

From Claude, using the Klarity MCP plus my email and Slack, draft a skill that
handles an inbound vendor request end to end.

Chain with other connectors covers that pattern in more detail.

Stand up an AI committee

A small cross-functional committee reviews the use cases and skills coming out of sessions and identifies the best ones to formalize and promote. It’s a lightweight governance layer that keeps quality high and surfaces the highest-value builds.

Make it recurring

Run the build ritual and the committee review on a regular cadence. Both cultural change and skill quality compound with repetition. A one-off event does not move an organization.

Keep a skills repository

Store the good skills in one place. A simple GitHub repository works well.

Ship the skills

Two options. Ship them directly into your AI platform as organizational skills available to everyone, or publish them to a separate repository people can download from. Either way, recommend the best ones so adoption spreads.

Klarity support

Klarity’s FDEs can facilitate the hackathon, curate the skills that come out of it, and take the best ones to production with your team.

Why this drives culture

For AI to succeed it has to be adopted by people, and this track is the best way to drive that. Two patterns separate the organizations that make it stick: leadership actually using AI themselves rather than only sponsoring it, and a recurring hands-on ritual.

The act of doing is paramount. Fluency comes from building, not from a workshop or a lecture.