Skip to content

The Lab

Where I test what I sell

Live demos of systems I have built, the patterns behind them, fair profiles of the harnesses people build agents with, and my own research. Every entry says honestly whether it is in production, built in the lab, or studied.

Jump to the live demos

My flagship research is Aura, an AI companion with an inner life.

Start here

New to agent systems? Four short reads, in this order.

  1. Routing and specialist agentsRouting means one agent reads each request and hands it to the specialist best placed to handle it, such as finance, operations or sales.4 min read
  2. The tool layer and MCPAI agents reach real systems through tools: named functions such as "find invoice" that the model asks to run, while ordinary code does the actual work.4 min read
  3. Agent memoryAI agents remember in layers: short-term context is what the model can see in the current conversation, and long-term memory is stored outside the model and fetched back in when relevant.4 min read
  4. Human approval gatesHuman approval gates sort every action an AI agent can take into three levels: draft only, needs a person to approve, or allowed to run automatically.4 min read

Live demos

Nine small demos based on systems I have built. Pick one and watch the work get done.

Northgate Commandcommand.northgate.example
Done

A chief of staff AI for a managing director. A request is typed into the command bar: sort the overnight emails, reply to a supplier about a delay, and ask the finance director agent about Q4 cashflow. A live trace shows the router sending the work to specialist agents. Eleven emails are triaged and a call is added to today's actions. A reply to the supplier is drafted and waits for approval. The board pack is summarised. The finance director agent reports £412k projected cash at year end, 9 percent ahead of plan, and flags two invoices over 45 days. The executive approves the reply and it is sent.

Done

  • 11 emails triaged
  • 1 reply approved and sent
  • Board pack summarised
  • Finance assessment ready

A team of AI agents that runs the executive admin, briefs you every morning and waits for your approval on anything that matters.

See the real build

Have something like this in mind?

Book a call

Demos are illustrative. Names, companies and figures are invented.

Browse the Lab

24 entries

Patterns13

One capability of a modern agent system, explained properly.

  • Heartbeats and schedules

    AI agents work without being asked when something other than a person wakes them: a schedule, a regular heartbeat check or an incoming event. Each wake-up gives the agent a fixed job, a time budget and a way to report back, so it can chase, prepare and flag things before anyone thinks to ask.

    4 min read
  • Agent memory

    AI agents remember in layers: short-term context is what the model can see in the current conversation, and long-term memory is stored outside the model and fetched back in when relevant. Vector stores find memories by meaning, graph stores by how people, records and events connect.

    4 min read
  • Self-improving skills

    Self-improving agents get better by writing down what worked as reusable skills: short procedures, checklists or scripts they load next time a similar task comes up. The model does not change; the library of procedures around it does, ideally with a person reviewing each change.

    3 min read
  • Routing and specialist agents

    Routing means one agent reads each request and hands it to the specialist best placed to handle it, such as finance, operations or sales. Each specialist has its own instructions, tools and permissions, which keeps answers sharper and access tighter than one agent trying to do everything.

    4 min read
  • Sub-agents and parallel work

    Sub-agents are helper agents that a lead agent starts for one well-defined piece of a larger job, each with its own fresh context, instructions and tools. Several can run at once and report back short findings, which makes broad tasks faster, at the price of more model usage.

    4 min read
  • The tool layer and MCP

    AI agents reach real systems through tools: named functions such as "find invoice" that the model asks to run, while ordinary code does the actual work. MCP, the Model Context Protocol, is an open standard for offering those tools and data to any AI application in the same way.

    4 min read
  • Human approval gates

    Human approval gates sort every action an AI agent can take into three levels: draft only, needs a person to approve, or allowed to run automatically. The agent prepares, a person signs off anything that matters, and the system refuses any action that does not match what was approved.

    4 min read
  • Long-running jobs

    An AI agent can follow a task for days or weeks only if the task lives outside the agent, as a saved record of goal, progress and next step that survives restarts. The agent wakes, reads the record, does one step, writes it back and sleeps, so nothing depends on one long conversation.

    4 min read
  • Agents in your channels

    You put an AI agent in email, WhatsApp, Slack or Teams by connecting it to each platform's official messaging interface, so people message it where they already work. One core agent sits behind thin adapters that handle each channel's rules, such as WhatsApp's 24-hour reply window.

    4 min read
  • Traces and audit logs

    You see what an AI agent did and why by recording a trace of every run, each model call, tool call and decision as a timed step, plus a separate audit log of every action that changed something and who approved it. Traces are for debugging; the audit log is the permanent record.

    4 min read
  • Agent safety

    You make an AI agent safe by limiting what it can do, not by trusting what it says. Give it the narrowest tools and permissions, run risky work in a sandbox, require a person to approve consequential actions, and treat every email, document and web page it reads as possibly hostile.

    4 min read
  • Agent cost control

    You control AI agent costs by sending routine work to small, cheap models and saving large ones for hard steps, caching repeated prompt content, and putting hard budgets and caps on every key, agent and job. Clients can then pay providers directly on their own keys or use a managed allowance.

    4 min read
  • Testing agents

    You test AI agents with evals, a set of realistic tasks with clear pass or fail checks that you run every time the agent, its instructions or its model changes. The best tasks come from real failures, and each one runs several times because agents do not behave the same way twice.

    4 min read

Harness profiles8

Well-known agent harnesses and frameworks: what each one is and what it does best.

  • OpenClaw

    OpenClaw is an open-source, self-hosted AI assistant that runs on your own machine and answers you in the chat apps you already use, such as WhatsApp, Slack, Teams and Telegram. It is best for one person or a small trusted team who want an always-on assistant with scheduled jobs, skills and tools under their own control.

    4 min read
  • Hermes Agent

    Hermes Agent is an open-source AI agent from Nous Research that runs on a server or your own machine, talks to you through the terminal or chat apps, and writes reusable skills from the work it does. It suits people who want a long-lived agent that remembers, runs scheduled jobs and improves with use, on any model provider.

    4 min read
  • DeepSeek Harness

    DeepSeek Harness (dsh) is DeepSeek's open-source agent harness, in public preview, built on the idea that every feature is a plugin. It suits developers who want a self-hosted coding and task agent they can reshape, running DeepSeek models or any provider that speaks a supported API.

    4 min read
  • Claude Code and Agent SDK

    Claude Code is Anthropic's agentic coding tool that reads a codebase, edits files and runs commands from the terminal, IDE, desktop app or browser. The Claude Agent SDK packages the same agent loop and tools as a Python and TypeScript library, for building your own agents on Claude.

    4 min read
  • OpenAI Agents SDK

    The OpenAI Agents SDK is an open-source library, in Python and TypeScript, for building agents that use tools, hand work to each other and pause for approval. It suits teams that want a light agent loop with tracing built in, rather than a full orchestration platform.

    4 min read
  • LangGraph

    LangGraph is an open-source framework from LangChain for building stateful agents as graphs of steps, with saved checkpoints so a run can pause, wait for a person and resume. It is best for long-running, multi-step work where you want explicit control over every path.

    4 min read
  • CrewAI

    CrewAI is an open-source Python framework for building teams of agents, each with a role, a goal and tools, that work through tasks together. It is best for work that splits naturally into roles, wrapped in event-driven Flows that keep the overall process under control.

    4 min read
  • Microsoft Agent Framework

    Microsoft Agent Framework is Microsoft’s open-source framework for agents and multi-agent workflows in .NET and Python, and the direct successor to both AutoGen and Semantic Kernel. It is best for teams on Azure or .NET that want typed, checkpointed workflows with approvals and OpenTelemetry tracing.

    4 min read

Experiments3

My own research systems, built to find out what is possible.

  • Built in the lab

    Aura

    Aura is an open-source AI companion with a state of mind that carries from one moment to the next: emotions that obey physics, memory that remembers how things felt, and five language models thinking in layers.

  • Built in the lab

    Magent

    Magent is a no-code platform for creating, customising and deploying voice and text agents for customer support, workflow automation and personal assistance. Agents answer from their own knowledge base, search the web, and listen and speak.

  • Built in the lab

    Discord guardian

    The Discord guardian is a moderation bot that times out unwanted links and answers questions in English and Bulgarian, using Google Gemini. Slash commands set what it watches, so a community runs itself without a moderator online.

Configurator

Sketch your own system

Answer a few questions and watch a diagram of your system build as you go. It lives on the Blueprint page.

Open the designer
Ask it yourself

Question the assistant

The circle in the corner is a small example of what I build. Ask it about agents, integrations or what a system for your business would look like.