Generative AI is has taken a few forms to this point.

We first had the chatbot interface, which today still remains quite dominant. It is the one that people tend to be most familiar with, cementing its place with the release of ChatGPT in November 2022.

We then had auto-completion, particularly with coding. This made interaction with the model more indirect; you simply start typing your code in the editor and the model suggests what the rest of the code should look like.

Agents take this ambience further. With agentic architectures, models become the engines that power a wider system that operates autonomously usually with little human direction.

AI agents are designed to go beyond simple single-turn, input-then-output interactions. They can identify the steps required a complete task, access the right tools and data, and use feedback loops to verify that it has completed the task set.

Why are we moving more toward these agentic architectures? Because the chatbot form factor is difficult for most people to use. They do not always know what questions to ask and often struggle to unlock the full capabilities of the model sitting behind the text box.

Agents close this capability gap.

As I wrote previously:

[Agentic architectures] leverage AI capabilities to autonomously execute the right instructions, gather and use the relevant context, and complete actions on behalf the user. Agentic AI could bring into existence the kind of ambient digital assistants that help users navigate their digital world in a way that demonstrates the extent of the capabilities of these strange black boxes.

But for agents to work effectively, they need to be surrounded by other components. Agents are systems consisting of different parts that do not just instruct the model on what to do and how to do it, but also provide it with the resources to enable the completion of the task.

How those components are fitted together is crucial. As talks about in her newsletter on AI agents in knowledge work:

The broader point is that the debate is shifting from “which AI is smartest” to “which system can actually get work done inside an organization.” When intelligence is commoditized, the new scarcity is agency, and the ability to act across systems, with the right permissions, in the right sequence, with accountability attached. That is workflow. That is what the refineries are really selling.

So how do we build whole systems that can get work done?

Harness engineering.

Prompt engineering focuses on crafting detailed natural language instructions for the task the model should complete. Context engineering focuses on providing models with the relevant information to complete tasks with.

Harness engineering is the practice of building the scaffolding around the model that enables it to go beyond just producing text. It is what gives the model the ability to browse the web, run code, read files, remember what happened in previous sessions and take multiple steps toward a goal.

But harness engineering is not just about making models more capable. It is also about making models safer and more reliable.

And this is where AI governance comes in.

Governance work typically lives on paper: policies, inventories and risk assessments scattered across Word documents, spreadsheets and slides.

But this paperwork means nothing if it is not accompanied by methods for its practical implementation. Governance stays stuck as just words on paper.

Harness engineering is what transforms governance from mere paperwork into executable rules for AI agents.

It becomes a way to achieve governance-by-design, producing the safe and reliable AI agents that users and enterprises are ultimately looking for.

In this post, I break down what harness engineering entails and how it can be used to implement three core aspects of AI governance.

Read more

Homomorphic encryption (HE) is a solution for performing functions on encrypted data without decrypting it.

To quote a previous post of mine explaining how encryption works:

...encryption is a method for transforming data from one format into another. The way encryption does this makes it a common security measure across diff…

Read more

This newsletter is about differential privacy. It looks at what it is, how it works and some practical applications of this solution, including for the development of machine learning models.

Here are the key takeaways:

• Differential privacy is about quantifying the information leakage of an algorithm. This leakage is measured by using the algorithm i…

Read more

1. Encrypting your internet connections

2. Hiding your IP address

To use a VPN, you can install software (i.e., a VPN client) from a VPN service provider. The client connects to the VPN server of the provider, and bot…

Read more

Encryption involves three main elements:

1. The plaintext

2. A cipher

3. A key

4. An algorithm

5. The cipher text

Encryption takes plaintext (i.e., the data to be encrypted), and applies an a…

Read more

This newsletter is about machine unlearning. It looks a potential implementation of this that could be used to comply with data protection law.

Here are the key takeaways:

• Training data extraction attacks reveal the personal data contained in the web-scraped datasets that LLMs like ChatGPT are trained on.

• Using personal data for training requires a su…

Read more

These are my notes on end-to-end encryption (E2EE) and Bugs in Our Pockets, a paper on the risks of client-side scanning (CSS). The authors of this paper include some well-known experts and researchers in the cryptography space; one of them, for example, is Whitfield Diffie, who is one of the creators of the Diffie-Hellman key exchange protocol (al…

Read more

This post explores how hash-based detection tools work and how they are used for content moderation on internet platforms.

In a previous post I explained what content moderation is and given an overview of how it generally works across different internet platforms:

Content moderation is where an internet platforms reviews content or communications on…

Read more

One of the keys to the effective implementation of a privacy programme within an organisation is ‘the company buy-in’; getting stakeholders to believe in the programme and contribute to its success. To do this, some may cite the fines imposed for non-compliance, particularly under the GDPR. However, with such an approach, the impression that one may dev…

Read more