Mick Zijdel

An AI Safety organisation had its contact, alumni, and donor data spread out across various tables and spreadsheets. I designed and built the system that brought it together.

Catalyze Impact incubates new AI Safety organisations. I was their first employee, and for a year and a half I co-ran the incubation program:

• Recruitment: finding promising founders through personalised outreach and social media campaigns.
• Selection: reviewing applications and test tasks, and interviewing candidates.
• Program design and logistics: designing the program, arranging speakers and venues, and organising events and trips.
• Participant support: handling requests from founders during, before and after the program.

I also built the systems everything ran on using Airtable bases and Python scripts that automated the repetitive parts of recruitment and selection, and I made some really great spreadsheets.

ML4Good runs 10-day intensive bootcamps that take people from “interested in AI Safety” to actually working on it. I was a teaching assistant at the March 2025 Europe camp where I taught the sessions on AI Agents, Adversarial Attacks, and AI Safety strategy, and coached participants through the rest of the curriculum.

Because the atmosphere at a bootcamp is just as important as the curriculum, I also ran the social side, including a welcome event, a murder mystery, lightning talks, and a Scottish ceilidh.

Operations work lives in Word documents, Excel sheets, and PDFs, which AI agents cannot open from the command line. Readoc fills that gap with three CLIs: readoc extracts the contents of a .docx, .xlsx, or PDF as structured text, readir explores and searches whole folders of mixed documents, and editdoc makes targeted edits to Office files without mangling their formatting.

Point an agent at a shared drive full of policies, budgets, and reports, and it can finally do something useful with them.

I built it for my own operations work, where “can the agent read the document” turned out to be a surprisingly common blocker.

Left to their own devices, AI agents write Rails code like the average of the internet: fighting the framework instead of using it. Rails Toolkit is a set of Claude Code skills that encode modern Rails 8 conventions and my own project rules, so agent-written code comes out idiomatic: thin controllers, concern-based models, Solid Queue jobs, Stimulus controllers with modern JavaScript, Hotwire/Turbo patterns, and fixture-based tests.

It also includes some larger workflows: a full application audit that combines the individual skills into a severity-ranked health report for inherited codebases, a database performance review, and an upgrade analyser covering breaking changes from Rails 2.3 through 8.1.

I maintain Rails applications (including the administration system behind a 150-year-old theatre company), and this toolkit is how I keep AI agents productive on them without the code turning into a mess I have to untangle later.

Many small organisations run on Airtable, but it has no built-in tooling for the questions an admin needs to ask: what changed in this base since last month? Does our structure follow our own conventions? Who has access to what?

Airtable Utils answers those:

• Schema export: dump a base’s full structure (tables, fields, views) to JSON for documentation and version control.
• Schema diff: compare two exports to see what was added, removed, renamed, or retyped.
• Standards check: validate a base against a written set of naming and structure conventions.
• Access audit: list collaborators and permissions across bases to see who can touch what.

It also includes an agent skill for writing Airtable scripts (both scripting-extension and automation scripts) that encodes the API’s quirks and limits, like the 50-fetch ceiling in automations, so generated scripts are correct the first time.

These grew out of my CRM and database work for AI Safety organisations, where the Airtable base often is the institutional memory, and an unnoticed schema change quietly breaks something downstream.

Artwork from “Ethics Town” podcast

I compose music for theatre and other performance and narrative art.

Podcasts

Themes for audio fiction podcasts.

Short Scoring Projects

Sketches

Short pieces I made for university assignments but did not develop into a full piece.

Theatre Composing

Theatre Sound Design

Other

I wrote my dissertation on “Ancient Rock Music”: the sound stalactites make when hit by a rubber mallet. The project was inspired by a visit to Luray Caverns, Virginia, home of the “Great Stalacpipe Organ”: an instrument that plays the cave itself.

The work had three parts: a physical simulation of struck stalactites using finite-difference and modal methods (approximating them as cantilever bars of variable diameter, in Matlab), a field trip to record real stalactites, and a virtual instrument built in C++ with JUCE so anyone can play a cave from their Digital Audio Workstation.

Photo from “Mary: A Gig Theatre Show”. Credit: Carla Watson

I work as a freelance sound designer and general organiser in theatre. See also the theatre I did as a student.

Theatre

• Mary: A Gig Theatre Show: Sound Designer
  • Bedlam Theatre (January 2024)
  • Edinburgh Fringe (August 2024): reviewed by The Stage and A Young(ish) Perspective
  • Traverse Theatre (December 2024)
  • Duns Play Fest (May 2025)
  • Edinburgh Fringe (August 2025)
• 25th Annual Putnam County Spelling Bee: Edinburgh Fringe (August 2024)

Running a venue at the Edinburgh Fringe means welcoming hundreds of performances in a month, and having to turnaround between them in minutes. I’ve done it in several roles:

• theSpaceUK 2022 (Deputy Venue Manager): co-ran the Triplex’s 130-seat and 65-seat spaces for four weeks: a team of 10 technicians and Front of House staff, and around 22 companies a day, changing over every week.
• Bedlam Fringe 2023 (Front of House Manager & Programmer): I led the planning for Bedlam Theatre’s return as a Fringe venue after the pandemic, including setting up the management structure and allocating the £50,000 budget. I programmed and liaised with 23 shows from multiple countries for the 90-seat theatre, and recruited, trained, and led a Front of House team of 7.
• Bedlam Fringe 2024 (Front of House Manager): back for a second season, running Front of House and Box Office operations and consolidating the procedures based on last year’s experience.
• Bedlam Fringe 2026 (Production Manager): currently production-managing the venue for this year’s festival.

The Edinburgh Festival Fringe has around 3,500 shows. I used to read the programme cover-to-cover, but that still didn’t tell me much about the shows themselves and which ones I should really go see, so I built the tool I wanted instead: a chat interface where you can just ask the programme what you should go see.

Under the hood it’s a RAG pipeline which does semantic search over the festival data with ChromaDB vector storage, category filtering, and a FastAPI backend serving a React/TypeScript frontend.

ImpAmp is the soundboard Bedlam Theatre uses for live improv comedy, where a sound effect is only funny if you can find it before the performers move on. It supports multiple soundbanks, instant search, arming tracks, multiple sounds per pad, and Google Drive sync so you can share your soundbanks with the whole team.

This third version was also an experiment in AI-driven development: I built it in Next.js using Claude 3.7 Sonnet and Gemini 2.5 back when agentic AI coding was just a month old. It has been running real shows ever since.