Selected work

Real projects. Real decisions moved.

A selection of engagements delivered personally by Dr Ahmed Younes — some through AYD, others earlier in his career — across advocacy, disinformation, conversational AI and customer insight, for research institutions, governments and businesses.

Emotech · Contract 7 → 42

LLM-as-a-Judge Evaluation Framework for Conversational AI

An automated evaluation pipeline for a customer-service voice AI — GPT generates adversarial scenarios, drives live conversations and judges outputs across design bugs, logic bugs and quality. Scaled from 7 to 42 test cases across 14 categories.

LLM-as-a-Judge Gen AI Conversational AI Rasa CALM
Read the full case study →
AxessAll · Self-employed Beta

RAG Autocomplete System for Accessibility Audits

Built and deployed a RAG service that auto-drafts structured fields for accessibility audit issues — retrieving the most similar past incidents and drafting a grounded completion rather than inventing detail. Currently in beta ahead of full rollout.

RAG FastAPI Qdrant NLP
Read the full case study →
AxessAll · Self-employed 22K+

NLP Analytics Pipeline for Unstructured Text

Built a portable topic-modelling and RAG analytics pipeline — 22,000+ records indexed in Qdrant, a multi-page Dash dashboard, and agentic thematic allocation making the data directly accessible to stakeholders.

Topic Modelling UMAP HDBSCAN Plotly Dash
Read the full case study →
AxessAll · Self-employed Research

Agentic Accessibility Scanner

An LLM tool-call layer over deterministic Playwright automation that detects WCAG violations and captures targeted screenshots — validated against real Wikipedia pages, catching a real detection bug along the way.

Agentic AI Playwright WCAG 2.2
Read the full case study →
AxessAll · Self-employed 7-layer

AI Strategy & Roadmap for a National Accessibility Platform

Led AI strategy and roadmap planning for a national government digital accessibility programme — a seven-layer platform architecture, a three-agent automation model, and direct contribution to bid and proposal development.

AI Strategy Systems Architecture Roadmapping
Read the full case study →
EMIF / ISD 7.8M

Pro-Kremlin Influence Network Mapping

Mapped pro-Kremlin influence networks across 7.8 million Telegram posts in France, Germany and Italy.

NLP Topic Modelling Contrastive Learning Python
Read the full case study →
Gates Foundation 43,000

Global Fund Advocacy Evaluation

Evaluated social-media advocacy for the Global Fund's 7th replenishment across 5 markets and 43,000 posts.

Social Media Analysis Thematic Framework NLP
Read the full case study →
FCDO / BII

Investor Sentiment in South African Energy

Built an investor-sentiment index for South Africa's energy sector, validated as predictive of investment flows.

Sentiment Analysis Transformers NLP Python
Read the full case study →
Swedish Institute 9 countries

Sweden's Global Image Under Pressure

Analysed the impact of two sensitive international incidents on Sweden's image across 9 countries and 7 languages.

Multilingual NLP Topic Modelling Machine Translation
Read the full case study →
Ofcom Profiling

Disinformation Landscape Mapping

Built a multilayered topic-modelling system to profile disinformation actors on social media.

Topic Modelling BERTopic Actor Profiling
Read the full case study →
BBC Monitoring 432,800

China's Public Diplomacy on Twitter & Facebook

Mapped China's diplomatic social-media activity — 432,800 messages across 372 accounts, with 102,883 classified across 9 themes in 4 languages.

Python scikit-learn Twitter API Plotly
Read the full case study →
Spike Insight 0.95 F1

Customer Review Topic, Theme & Sentiment Analysis

Analysed ~13,000 customer reviews for a guided-walking-holiday operator — topic modelling, thematic annotation and a zero-shot correction layer lifted macro-F1 from 0.69–0.79 to 0.85–0.95.

Topic Modelling BERTopic Zero-Shot Sentiment
Read the full case study →
Emotech · Contract 7 → 42

LLM-as-a-Judge Evaluation Framework for Conversational AI

An automated evaluation pipeline for a customer-service voice AI — GPT generates adversarial scenarios, drives live conversations and judges outputs across design bugs, logic bugs and quality. Scaled from 7 to 42 test cases across 14 categories.

LLM-as-a-Judge Gen AI Conversational AI Rasa CALM
Read the full case study →
AxessAll · Self-employed Beta

RAG Autocomplete System for Accessibility Audits

Built and deployed a RAG service that auto-drafts structured fields for accessibility audit issues — retrieving the most similar past incidents and drafting a grounded completion rather than inventing detail. Currently in beta ahead of full rollout.

RAG FastAPI Qdrant NLP
Read the full case study →
AxessAll · Self-employed 22K+

NLP Analytics Pipeline for Unstructured Text

Built a portable topic-modelling and RAG analytics pipeline — 22,000+ records indexed in Qdrant, a multi-page Dash dashboard, and agentic thematic allocation making the data directly accessible to stakeholders.

Topic Modelling UMAP HDBSCAN Plotly Dash
Read the full case study →
AxessAll · Self-employed Research

Agentic Accessibility Scanner

An LLM tool-call layer over deterministic Playwright automation that detects WCAG violations and captures targeted screenshots — validated against real Wikipedia pages, catching a real detection bug along the way.

Agentic AI Playwright WCAG 2.2
Read the full case study →
AxessAll · Self-employed 7-layer

AI Strategy & Roadmap for a National Accessibility Platform

Led AI strategy and roadmap planning for a national government digital accessibility programme — a seven-layer platform architecture, a three-agent automation model, and direct contribution to bid and proposal development.

AI Strategy Systems Architecture Roadmapping
Read the full case study →
EMIF / ISD 7.8M

Pro-Kremlin Influence Network Mapping

Mapped pro-Kremlin influence networks across 7.8 million Telegram posts in France, Germany and Italy.

NLP Topic Modelling Contrastive Learning Python
Read the full case study →
Gates Foundation 43,000

Global Fund Advocacy Evaluation

Evaluated social-media advocacy for the Global Fund's 7th replenishment across 5 markets and 43,000 posts.

Social Media Analysis Thematic Framework NLP
Read the full case study →
FCDO / BII

Investor Sentiment in South African Energy

Built an investor-sentiment index for South Africa's energy sector, validated as predictive of investment flows.

Sentiment Analysis Transformers NLP Python
Read the full case study →
Swedish Institute 9 countries

Sweden's Global Image Under Pressure

Analysed the impact of two sensitive international incidents on Sweden's image across 9 countries and 7 languages.

Multilingual NLP Topic Modelling Machine Translation
Read the full case study →
Ofcom Profiling

Disinformation Landscape Mapping

Built a multilayered topic-modelling system to profile disinformation actors on social media.

Topic Modelling BERTopic Actor Profiling
Read the full case study →
BBC Monitoring 432,800

China's Public Diplomacy on Twitter & Facebook

Mapped China's diplomatic social-media activity — 432,800 messages across 372 accounts, with 102,883 classified across 9 themes in 4 languages.

Python scikit-learn Twitter API Plotly
Read the full case study →
Spike Insight 0.95 F1

Customer Review Topic, Theme & Sentiment Analysis

Analysed ~13,000 customer reviews for a guided-walking-holiday operator — topic modelling, thematic annotation and a zero-shot correction layer lifted macro-F1 from 0.69–0.79 to 0.85–0.95.

Topic Modelling BERTopic Zero-Shot Sentiment
Read the full case study →

Your project could be next.