Practical AI adoption insight, every week. Subscribe to aiblBRIEF
aibl
  • Practical AI Insights
    • The research
      • Benchmark your AI ROI (Beta)
      • State of UK AI Adoption 2026
      • What our research says
      • AI analysis
      • Leadership Series report
      • Newsletter archive
    • Learn and apply
      • AI explained
      • AI case studies
      • AI build stories
      • AI playbooks
      • AI workshop guides
      • Boardroom findings
      • AI leader interviews
  • aiblLIVE
    • 2026 session library
    • aiblLIVE 2027
  • Find AI enablement partners
    • AI Enablement Directory
      • Search the directory
      • Register your business
    • By Category
      • AI Strategy & Readiness
      • AI Implementation & Deployment
      • AI Training & Capability Building
      • AI Agents & Agentic Workflows
      • AI Governance & Risk
      • Generative AI Applications
      • Data & Analytics
      • Process & Document Automation
  • Partner with aibl
    • For enablement partners
    • For AI platforms and vendors
    • Insights for vendors
    • Market insights reports
  • About
    • About Us
    • AI For business leaders
Subscribe to aiblBRIEF
  • Practical AI Insights
    • The research
      • Benchmark your AI ROI (Beta)
      • State of UK AI Adoption 2026
      • What our research says
      • AI analysis
      • Leadership Series report
      • Newsletter archive
    • Learn and apply
      • AI explained
      • AI case studies
      • AI build stories
      • AI playbooks
      • AI workshop guides
      • Boardroom findings
      • AI leader interviews
  • aiblLIVE
    • 2026 session library
    • aiblLIVE 2027
  • Find AI enablement partners
    • AI Enablement Directory
      • Search the directory
      • Register your business
    • By Category
      • AI Strategy & Readiness
      • AI Implementation & Deployment
      • AI Training & Capability Building
      • AI Agents & Agentic Workflows
      • AI Governance & Risk
      • Generative AI Applications
      • Data & Analytics
      • Process & Document Automation
  • Partner with aibl
    • For enablement partners
    • For AI platforms and vendors
    • Insights for vendors
    • Market insights reports
  • About
    • About Us
    • AI For business leaders
  • Subscribe to aiblBRIEF

AI knowledge base: how Metomic’s CEO built her own AI brain

Downloads | AI case studies

An AI knowledge base works best when the AI builds and files it for you, says Beth Ayers, CEO of Metomic. Nearly 100 skills were using up a third of her context in every new window. She explained how she rebuilt it at aiblLIVE London 2026.

Her set-up is a folder of markdown files that Claude organises itself, with a small index that loads first. A work ledger lets any new window carry on where the last one stopped. Here is how it works.

Beth Ayers’ set-up in numbers

  • Nearly 100 skills, plus many connectors, were loading into every window before the rebuild.
  • About 25,000 tokens of her own context now load in a new window.
  • About 16 named specialists, each mixing skills with her preferences.
  • 150 to 200 lines is the most she lets any memory file grow to.

All figures as stated on stage by Beth Ayers.

How does the AI knowledge base work?

It splits thinking from memory. The model does the thinking, and markdown files on a local drive, synced to Google Drive, hold the memory. Each new window reads only a top layer of rules, an index and a roster of specialists. Claude then pulls in project files and connectors as needed.

My brain has two elements. It has a thinking element, which is the model, and then you have your memory, which is all of your files.

Beth Ayers, CEO, Metomic

What is the work ledger?

A running record of what each session produced and where the files live. It means Ayers can start a board pack in one window and finish it in another days later, without hunting for the old chat. She trims it to about the last couple of months, to keep it short.

How does she keep the system improving?

Through ordinary conversations. She compares Claude’s draft with her own rewrite and asks why they differ, which surfaces rules she had never stated. After long sessions, she asks Claude what it learned and how to codify it, then updates an agent, skill or rule.

How does she keep it private and tidy?

With a private-by-default rule and fortnightly housekeeping. Every file is marked private or public, after Claude once wrote candid notes into files shared with the company. Every fortnight, Claude culls duplicates and dead files, trims old material and merges repeated rules.

Start with one folder, one thing you want to do, one set of rules, and then just collaborate with your AI and figure out what you want to do.

Beth Ayers, CEO, Metomic

Key takeaways

  • Load an index, not everything. A small top layer keeps each window light.
  • Let the AI do the filing. Claude designed its own file structure.
  • Keep a work ledger. Any new window can pick up the work.
  • Make private the default. Public versions carry no names.

About the speaker

Metomic logo

Beth Ayers is CEO of Metomic. A heavy Claude user who describes herself as disorganised, she rebuilt her own AI set-up around a markdown knowledge base that Claude organises for her. She spoke on the Efficiency track at aiblLIVE London on 20 October 2026.

What’s in the full case study

If you keep repeating yourself to AI, this is the set-up to copy. The full PDF goes deeper than this page, in Ayers’ own words.

  • The architecture, from the top layer of rules and index to the 16 named specialists.
  • How the work ledger was built, and how it carries work between windows.
  • The privacy and housekeeping rules that stop the system leaking or bloating.
  • Five actions to take back to your own organisation.

For founders, CEOs, operators and anyone who uses Claude or ChatGPT every day. Six pages, about an eight-minute read.

Make every AI window remember you

AI knowledge base: how Metomic’s CEO built her own AI brain
aibl
Subscribe to aiblBRIEF

Explore

  • For business leaders
  • For AI platforms and vendors
  • About
  • Contact

AI Insights

  • All articles
  • AI case studies
  • Interviews
  • UK AI adoption research

Events

  • aiblLIVE 2026 session library
  • aiblLIVE 2027

More

  • aiblCONNECT
  • AI Enablement Directory
  • aibl Information Pack for AI’s
  • The State of AI Adoption Key Findings
© 2026 AIBL MEDIA LIMITED (DBA: aibl | AI for business leaders), Company registration number: 16634894 - The organisers of aiblLIVE do not, under any circumstances make attendee data available to third parties for resale. Should you receive an email offering data purporting to be from aiblLIVE – or any other event organised by aibl media limited – please delete the message, block the sender, and do not respond or interact in any way.
  • Privacy Policy