AI Dev 26 x SF | Ara Khan: Evals Are Broken Use Them Anyway

DeepLearningAI · Intermediate ·🤖 AI Agents & Automation ·2h ago

Skills: Agent Foundations80%Tool Use & Function Calling60%

This talk by Cline's Ara Khan explains why they went from "evals are useless" to using them as a core part of my agent improvement loop. I share practical heuristics for interpreting, running, and creating evals, and why doing them anyway is better than pure "vibes".

Watch on YouTube ↗ (saves to browser)

Sign in to unlock AI tutor explanation · ⚡30

More on: Agent Foundations

View skill →

Build and Deploy an Agent with Reasoning Engine in Vertex AI

Adding a Phone Gateway to a Virtual Agent

From Zero to Working AI Agent in 60 Seconds

From Zero to Working AI Agent in 60 Seconds

Create An AI Agent With Replit That Automates Your Sales

Create An AI Agent With Replit That Automates Your Sales

Capstone: Autonomous Runway Detection for IoT

Capstone: Autonomous Runway Detection for IoT

AI Agents with Model Context Protocol & Typescript

AI Agents with Model Context Protocol & Typescript

Related AI Lessons

Small AI database questions can become big scans

Learn how small AI database questions can lead to big scans and impact production database performance

Your AI database agent should not see every column

Learn why limiting column access for AI database agents is crucial for preventing sensitive data leaks and how to implement this in your database design

AiFinPay: Autonomous Payments for ruvnet/ruflo

Streamline AI agent payments with AiFinPay and Ruvnet/Ruflo for efficient and secure transactions

AiFinPay: Autonomous Payments for cirosantilli/china-dictatorship

Learn how AiFinPay enables autonomous payments for AI agents with a one-line payment SDK, supporting anti-Chinese government propaganda platforms

Build your website for the agentic era

Chrome for Developers