
Cem Dilmegani
Cem has been the principal analyst at AIMultiple for almost a decade.
Cem's work at AIMultiple has been cited by leading global publications including Business Insider, Forbes, Morning Brew, Washington Post, global firms like HPE, NGOs like World Economic Forum and supranational organizations like European Commission. [1], [2], [3], [4], [5]
Professional experience & achievements
Throughout his career, Cem served as a tech consultant, tech buyer and tech entrepreneur. He advised enterprises on their technology decisions at McKinsey & Company and Altman Solon for more than a decade. He also published a McKinsey report on digitalization.
He led technology strategy and procurement of a telco while reporting to the CEO. He has also led commercial growth of deep tech company Hypatos that reached a 7 digit annual recurring revenue and a 9 digit valuation from 0 within 2 years. Cem's work in Hypatos was covered by leading technology publications like TechCrunch and Business Insider. [6], [7]
Research interests
Cem's work focuses on how enterprises can leverage new technologies in AI, automation, cybersecurity (including network security, application security), data collection including web data collection and process intelligence.
Cem's hands-on enterprise software experience contributes to his work. Other AIMultiple industry analysts and tech team support Cem in designing, running and evaluating benchmarks.
Education
He graduated as a computer engineer from Bogazici University in 2007. During his engineering degree, he studied machine learning at a time when it was commonly called "data mining" and most neural networks had a few hidden layers.
He holds an MBA degree from Columbia Business School in 2012.
Cem is fluent in English and Turkish. He is at an advanced level in German and beginner level in French.
External publications
- Cem Dilmegani (September 28, 2017). Post-AI Banking: Millions of jobs at risk as banks automate their core functions. International Banker
- Cem Dilmegani, Bengi Korkmaz, and Martin Lundqvist (December 1, 2014).Public-sector digitization: The trillion-dollar challenge.McKinsey & Company
Conference & other event presentations
- Real Estate and Technology, presented by Hofstra University’s Wilbur F. Breslin Center for Real Estate Studies and the Frank G. Zarb School of Business in 2023 and 2024.
- Radar AI session (June 22, 2023): "Increasing Data Science Impact with ChatGPT".
- Generative AI Atlanta meetup (March 10, 2023): Generative AI for Enterprise Technology.
Sources
- Why Microsoft, IBM, and Google Are Ramping up Efforts on AI Ethics, Business Insider.
- Microsoft invests $1 billion in OpenAI to pursue artificial intelligence that’s smarter than we are, Washington Post.
- Empowering AI Leadership: AI C-Suite Toolkit, World Economic Forum.
- Science, Research and Innovation Performance of the EU, European Commission.
- EU’s €200 billion AI investment pushes cash into data centers, but chip market remains a challenge, IT Brew.
- Hypatos gets $11.8M for a deep learning approach to document processing, TechCrunch.
- We got an exclusive look at the pitch deck AI startup Hypatos used to raise $11 million, Business Insider.
Latest Articles from Cem
Best 7 AI Testing Agents for QA
We evaluated AI testing agents; most were overhyped Selenium/Playwright with marketing. A few were capable of writing/maintaining test cases or visual testing, though even these tools still have notable limitations. From these, we selected 7 agents and categorized them by their primary focus areas. Our evaluation is based on real-world application readiness.
LCMs: From LLM Tokenization to Concept-level Representation
Large concept models (LCMs), as introduced by Meta in their work on “Large Concept Models,” represent a fundamental shift away from token-based prediction toward concept-level representation.
Best AI Context Window Models
We analyzed the context window performance of 22 leading AI models by testing them using a proprietary 32-message conversation that includes complex synthesis tasks requiring information recall from earlier in the conversation. Our findings reveal surprising performance patterns that challenge conventional assumptions.
Authorization for AI Agents: Permit.io, Descope & more
I have been exploring agent identity and the authentication/authorization platforms that could support it, while also examining how standards like OAuth 2.0 and frameworks such as Keycloak might apply. Below, I listed the best AI agent–specific platforms and features, categorized by their primary focus.
How we Moved from LLM Scorers to Agentic Evals?
Evaluating LLM applications primarily focuses on testing an application end-to-end to ensure it performs consistently and reliably. We previously covered traditional text-based LLM evaluation methods like BLEU or ROUGE. Those classical reference-based NLP metrics are useful for tasks such as translation or summarization, where the goal is simply to match a reference output.
Top 10 Backup Management Software: Key Features & Benefits
With cybercrime costs reaching $10.5 trillion globally in 2025 and the backup software market projected to reach $18.2 billion by 2032 (growing at 8.9% CAGR), choosing the right backup solution can protect you from data loss that could cripple your business operations.
Top 9 IT Documentation Software to Streamline Your Workflow
Effective IT documentation is crucial for organizations to maintain operational efficiency, ensure compliance, and facilitate knowledge transfer. We analyzed over 18,000 recent user reviews and tested the key features of the nine leading platforms, from dedicated MSP vaults to integrated RMM solutions.
Benchmarking Agentic AI Frameworks in Analytics Workflows
While agentic frameworks share the goal of empowering LLMs with tool usage and reasoning, their architectures reveal critical differences in decision-making, error handling, and data processing. We had previously benchmarked agentic frameworks across different use cases, but we wanted to observe how these frameworks would behave and perform on a more complex task.
Vision Language Models Compared to Image Recognition
Can advanced Vision Language Models (VLMs) replace traditional image recognition models? To find out, we benchmarked 16 leading models across three paradigms: traditional CNNs (ResNet, EfficientNet), VLMs ( such as GPT-4.1, Gemini 2.5), and Cloud APIs (AWS, Google, Azure).
Top 40+ AI Developer Tools for Software Development
We have been experimenting with AI development tools in our code generation and code editing benchmarks for months. We have seen that AI agents like Claude Code are highly capable of software development, achieving ~%90 success rate.
AIMultiple Newsletter
1 free email per week with the latest B2B tech news & expert insights to accelerate your enterprise.