Hamza
Mostafa

I write about agents, systems, and how intelligence becomes useful in the real world.

Featured essay

Agent Systems

Most Agents Are Bullsh*t

Most agent projects break in the work around the model: defining the job, constraining its actions, evaluating failures, and improving it from production.

August 8, 2026

6 min read

Read essay

Selected writing

The archive

All essays

06EvaluationEvals Are Bullsh*tMost evals measure whether an agent looks good. Good evals measure whether it does the job your business actually needs.August 1, 20266 min read

05Agent SystemsThe Model Is the Wrong Thing to OwnEnterprises should own their intelligence. That means accumulating domain knowledge every new model can inherit, not training a model of their own.July 24, 20265 min read

04EvaluationSalesBench: The Long-Horizon Agent-to-Agent EvalA long-horizon RL environment where a small model learns to manage an insurance sales pipeline against an LLM buyer, scored by revenue closed instead of by an LLM judge. The trained model vastly outperforms the untrained base, and the gap widens as the eval gets harder.May 14, 202612 min read

03Agent SystemsThe Agent Research LoopWhat Karpathy's autoresearch really means, where agent systems are headed, and an open-source harness that ran 550 experiments over a weekend.March 16, 20268 min read

About / Now

Building, studying, and writing in public.

Background

I'm a builder and tinkerer. Previously on the Agent team at OpenAI. On leave from CS at the University of Waterloo, KP fellow.

Current questions

Right now I'm exploring multi-agent systems, long-horizon agents, and continual learning.

The common thread is simple: how do capable systems become useful, dependable, and better with experience?

Contact

Say
hello.

The fastest way to reach me is a DM on X or a note on LinkedIn. Interesting questions are always welcome.

X@hamostaf04 ↗GitHubHamza-Mos ↗LinkedInhamza-mostafa ↗

HamzaMostafa

Most Agents Are Bullsh*t

The archive

Sayhello.

Hamza
Mostafa

Say
hello.