Orply.

Ara Khan

Ara Khan is a founding engineer at Cline, an AI coding-agent platform. He writes and speaks about building production-quality AI agents, including agent maturity, evaluation, context engineering, and reliable agent design.

Coding Agents Are Improving Their Harnesses, Not Their Models

Ara Khan of Cline argues that as coding agents improve, engineers should focus on problems that benefit from stronger models without being made irrelevant by them. A Cline benchmark demonstration showed an agent improving the tools and execution logic around a fixed model—not changing the model itself—by testing harness adjustments against task failures. Khan sees that measurable improvement loop extending into evaluation, inference, training and hardware, and advises engineers to work closer to those bottlenecks.

AI EngineerNov 11, 20268 min read

Cline’s Terminal-Bench Gains Came From Harness Tuning, Not Model Switching

Ara Khan of Cline argues that AI evals are too noisy to treat as truth but too useful to replace with vibes. Using Cline’s Terminal-Bench work as the case study, he says the company’s jump from 43% to 57% came from harness changes — container CPU and memory, longer timeouts, and model-family-specific prompting — rather than a better model. His prescription is to run evals skeptically, inspect failed traces, allocate failures by cause, and improve only the levers that survive contact with product behavior.

AI EngineerJun 6, 202611 min read

Every Addition to an AI Agent Can Make It Worse

Ara Khan of Cline argues that agent maturity is less about adding autonomy than about knowing what not to add. In a talk structured around four levels of agent building — from frameworks to state machines, Kanban-managed workflows and cloud deployment — Khan says frontier models increasingly reward simpler prompts, deliberate architecture and visible human control. His central warning is that every extra instruction, abstraction or automation layer can make an agent worse.

AI EngineerMay 19, 202613 min read