Hiring AI agents in 2026

How we’re building a multi-agent system at Deriv, where AI agents register, collaborate, and safely access enterprise tools.

May 8 • Kaveh Mousavi Zamani

1

April 2026

Beyond last-click: building an attribution engine people could trust

How we connected ad-platform data to downstream business outcomes, and why trust mattered more than the model

Apr 26 • Harsh Solanki and Haroon

1

Write for the AI that doesn't exist yet

How I built a real-time trading game with AI using specs, an AI manager, and almost no human coding.

Apr 9 • Kaveh Mousavi Zamani

2

1

Why half your AI SAST findings are wrong (and how to fix them)

AI-powered SAST catches patterns fast, but without context it produces false positives. Here’s why security teams need static analysis, authorization…

Apr 1 • Rotimi Akinyele

3

March 2026

How we built an AI agent security swarm for offensive security testing

Deriv built a multi-agent offensive security system that automates source code review, dynamic testing, AI pentesting, and bug bounty triage to find…

Mar 31 • Rajesh TV

8

Automated security code reviews with Claude Code and GitHub Actions: How we did it at Deriv

How Deriv automated security code reviews with Claude Code and GitHub Actions to scan every pull request, flag vulnerabilities, support interactive PR…

Mar 31 • Vishal Panchani

2

Do security prompts make AI-generated code safer? I tested it.

Same model, same prompts, one key difference: a security prompt. Here’s what changed in the generated code, explained.

Mar 24 • Tan Weng Onn

1

From long waits to instant support: How our AI agent Amy changed affiliate engagement

Inside Deriv’s AI partner support for web chat and WhatsApp across 190+ countries and 57 languages.

Mar 16 • Mahantesh

2

The red team tradecraft behind hard-to-detect AI phishing

How threat actors can combine Claude Code execution, trusted email delivery, and modern phishing TTPs to bypass security controls.

Mar 13 • Dhiraj Mishra

4

February 2026

How we replaced a 20-year-old back office — twice

From legacy to low-code to an AI-powered system

Feb 26 • Shafi Trumboo

3

Operations automation boosts Deriv MT5 reliability

By Andreas Potamitis, Basel Mohmmad, and Andrew Spiteri

Feb 16

1

Security through transparency

Why we open-sourced our AI sandbox

Feb 10 • Christopher Hernandez

5