# Anthropic engineer's 14-minute guide to building Claude agents

> TikTok recap of an Anthropic engineer's agent-building advice: start with three primitives, don't agentify everything, and respect the tiny working context.

Published: 2026-05-03
URL: https://daniliants.com/insights/anthropic-engineer-14-min-video-on-building-claude-ai-agents/
Tags: claude, ai-agents, system-prompts, context-window, agent-design, human-in-the-loop

---

## Summary

A short TikTok recap of an Anthropic engineer's 14-minute video on building agents in Claude. Three takeaways: start every agent with just three primitives (environment, one connected tool, system prompt), don't agentify everything (use a decision tree to pick automated workflow vs. human-in-the-loop vs. autonomous agent), and respect the agent's tiny working context (~10k-20k tokens) by trimming system prompts ruthlessly.

## Key Insight

- **Three-piece minimum viable agent:** environment + one tool + system prompt. Anything more is premature scaling. Most agent failures come from stacking tools before the base loop works.
- **Not every task is an agent.** Decision tree: deterministic workflow with human approval > autonomous agent. Human-in-the-loop is the default; full autonomy is reserved for narrow, well-bounded tasks.
- **Context window is the real constraint.** Working budget for the agent's reasoning is roughly 10k-20k tokens per turn after tool definitions, examples and system prompt are loaded. Bloated system prompts crowd out the actual task.
- **Use Claude to design the agent itself.** Feed Claude the takeaways and let it map the tool list, system prompt skeleton, and likely failure modes before any code is written. Cheaper than discovering them at runtime.
- This is a TikTok summary, not the source video, so treat the numeric claims (token budget, "three things") as the engineer's heuristics, not Anthropic guidance.