cd /news/ai-agents/ask-hn-how-to-claude-like-anthropic · home topics ai-agents article
[ARTICLE · art-106745] src=news.ycombinator.com ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Ask HN: How to Claude Like Anthropic

Anthropic engineer Daisy described a multi-agent workflow for Claude Code in which two lead agents supervise 8-10 projects, each with 5-10 IC agents, totaling 30-50 prompts per day, with IC agents working autonomously for 2-3 days. The workflow relies on the SendMessage tool for agent communication, with 60% of interaction with leads, 35% with project leads, and 5% for troubleshooting. The post contrasts this with a more manual, review-centric approach and asks for similar experiences or guides.

read2 min views3 publishedAug 22, 2026

I just received an email from Anthropic. Besides the usual new feature ad, there is a piece that I find quite amusing:

How to Claude like Anthropic

"My daily driver currently looks like: two lead agents that keep each other accountable and restart the other if either fails. These delegate to tech lead or PM agents for the 8-10 projects I'm running at any one time, and each project has 5-10 IC agents, generalists or specialists depending on the problem. Across all of these I'm still only doing 30-50 prompts per day, and my IC agents typically work autonomously for 2-3 days. About 60% of my interaction is with the leads, 35% with a project lead, and 5% is when something has gone off the rails. All of these agents communicate directly with the SendMessage tool."

– Daisy, Engineer on Claude Code

This sounds very foreign to me because it couldn't be more different from how I use Claude Code. My current workflow is:

  • For a new feature, I create a session, and depending on the complexity, I will either use plan mode or something else like Superpowers to brainstorm, work out the requirements, and create a plan/spec. This process typically makes up most of my interactions with the agent.

  • Then, after it implements the feature, I open a new session, use my own skill to review the PR, and post the findings on the PR.

  • Once I have the PR comments, I give them back to the original session and use another matching skill to give a verdict on the findings and attempt to fix them. This process will typically happen back and forth for ~3 rounds.

  • Once the reviewer session is happy, I ask the original session to perform an E2E test plan that covers everything it has implemented.

I feel like my workflow is not automated enough, and my verification loops are still too manual. But I also feel more reassured this way because I read every report and have a general sense of the quality of the PR without having to read the code.

Does anyone here use a similar workflow to Claude, that utilizes specialized agents instead of just the general-purpose one? Can you share your experience? Do you have a guide/blog I can read to learn more about it?

Comments URL: [https://news.ycombinator.com/item?id=49396175](https://news.ycombinator.com/item?id=49396175)

Points: 1

── more in #ai-agents 4 stories · sorted by recency
── more on @anthropic 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ask-hn-how-to-claude…] indexed:0 read:2min 2026-08-22 ·