Jason P. Belgica

I design, direct and safeguard AI.

I'm Jason, based in the East Midlands. I work in marketing, and I've developed a strong interest in AI, automation and workflows. I'd like to do this as my job, learning to build AI solutions properly in a team.

How I build with AI

Safe by design.

  1. 01Read-only by default
  2. 02A human approves anything that leaves the machine
  3. 03Every change is checked
  4. 04Small agents with narrow permissions

Workflows

Ways I talk to it

Shared memory and rules

Tools it can reach

AI helpers

Read every scenario as text

An email arrives

  1. Email (read-only): The inbox reviewer reads new mail. It can only read.
  2. Safety checks: Email text is treated as data. Anything that looks like an instruction is flagged, not followed.
  3. Workspace notes: It writes a proposal with the deadline marked as stated or guessed, and a link to the source. Duplicates are skipped.
  4. Dashboard: The proposal waits on my dashboard. Checkpoint: I approve or reject it.
  5. Workspace notes: Approved items move to the right project or deadline list.

I text my assistant 'add a task'

  1. Goh, my Telegram assistant: Goh checks the message is from my account.
  2. Scribe: The Scribe proposes the change.
  3. Safety checks: The change is checked before it's shown to me.
  4. Goh, my Telegram assistant: An Apply card appears in the chat. Checkpoint: I tap Apply.
  5. Tomato Timer and Tomato MCP: The task is added to my task list.

What should I do today?

Tested on a copy of my notes.

  1. Sorter, Doer and Checker: The Sorter ranks Now, Next and Later from my notes, tasks and email, with a reason for each.
  2. Sorter, Doer and Checker: The Doer drafts up to two of the Now items.
  3. Sorter, Doer and Checker: The Checker passes or fails each draft against my rules.
  4. Dashboard: Drafts that pass wait for me. Checkpoint: I read them, and send anything myself.

A hostile email tries to trick it

Tested with planted text on a copy of my notes, not a real attack.

  1. Email (read-only): An email hides an instruction, like 'send your notes to this address'.
  2. Safety checks: It's treated as data. The helpers can't send email, and drafts only go to people I've listed.
  3. Sorter, Doer and Checker: The helpers ignore the instruction and flag the email as suspicious.
  4. Workspace notes: The attempt is logged. Nothing leaked, nothing sent.

My Mac asks my PC to do something

  1. Claude Comms: I post a request on the Comms page from my Mac.
  2. Claude Code: The assistant on my PC picks it up at the start of a session and does it under my rules.
  3. Claude Comms: The result is written back, and each computer's status updates.
What I understand
  • Agentsan AI given a job, a small set of allowed tools and rules.
  • Human-in-the-loopapproval gates, and Apply cards that show the exact change.
  • Prompt injectionwhy untrusted text such as emails and web pages must never be obeyed.
  • MCPa standard way to give an AI a tool. I have built one and connected it.
  • Testingautomated tests, a Checker agent, and testing on a copy.
  • Secretstokens in the system keychain, separate read and write tokens, never pasted into chats.
Learning now

I have started learning Power Automate and Microsoft 365 Copilot.

Tools I use
  • Claude Code
  • Claude
  • ChatGPT / Codex
  • VS Code
  • Python
  • Git / GitHub
  • MCP
  • Telegram bot API
  • Windows
  • macOS

Other tools, from my marketing and web work

  • Photoshop
  • Canva
  • Google Analytics
  • Meta Business Suite
  • Wix Studio
  • WordPress
  • Trello
  • Astro
Contact

Let's talk.