AI Engineering Advanced Pro

Case Study: Design a Coding Agent

A full AI-engineering interview answer for a Claude Code-shaped agent: the loop, the tool set, the permission model, context management, memory, cost control and evaluation

35 min read 10 views

Model interview answer for designing a terminal coding agent that reads, edits, runs and verifies code in a repository: requirements and threat model, the agentic loop, a minimal tool set with output caps, a permission model that separates read from write from execute, context management for a finite window (truncation, compaction, subagents, cached prefixes), layered memory, cost and step budgets, prompt-injection defence, evaluation on task suites, and observability.

Preview Subscribe to unlock

Practice questions (5)

Designing the Permission Model for a Coding Agent

Advanced · Free

View →
Fitting a 300k-Line Repository into a 200k-Token Window

Advanced

View →
Cost per Task and the Levers That Move It

Advanced

View →
Choosing and Shaping the Tool Set

Advanced

View →
Evaluating a Change to the Agent's System Prompt

Advanced

View →

Quizzes (1)

Case Study: Coding Agent Quiz

0 attempts · 10 min · Pass 70% · Advanced

Take quiz →