Skip navigation
ANTHROPIC LEAKED A 5-AGENT SETUP THAT TURNS ONE QUESTION INTO A SOURCED REPORT
0:00 / 0:49

ANTHROPIC LEAKED A 5-AGENT SETUP THAT TURNS ONE QUESTION INTO A SOURCED REPORT

Hanako

@hanakoxbt21K followers

Visit on X
429 likesDownloadOriginal post

59,073 views

ANTHROPIC LEAKED A 5-AGENT SETUP THAT TURNS ONE QUESTION INTO A SOURCED REPORT you write one line and never open a tab - the fleet reads 40 sources and only the answer comes back. question → scope → 5 searchers → dedupe → writer → fact-check → report the scope agent turns a vague question into 5 angles that do not overlap - skip this and five agents fetch the same three articles. 5 searchers run in parallel with separate contexts - none of them sees what the others found, which is exactly why they do not converge on the same source. dedupe is code, not an agent - flatten, drop repeats, normalize URLs, zero tokens, instant. the writer only sees structured findings, never raw pages - it cannot cite something that was never verified because it never had access to it. the fact-checker reads the draft against the sources, not against itself - every claim without a matching source goes back, and only that section is rewritten. nothing reaches you until a second agent, with clean context, has tried to kill it. 12 minutes, 40 sources, one report where every line traces back to something real. save this and read the full graph engineering course below ↓

11 Comments

Comments from the original post on X (Twitter)

  • Hussain Hashim | Building SundayBack's profile picture

    @itsthedonhashim

    @hanakoxbt that's wild! feel like i need this setup for all the random questions i end up googling daily. game changer for info junkies like me.

    1 like

  • cvxv666's profile picture

    @antpalkin

    saved it, real hidden alpha

  • AI Mastery Guide's profile picture

    @aiseomastery

    40 sources in 12 minutes

  • ∑: Meww ∑: (❖,❖)'s profile picture

    @NgocO88803

    Fascinating breakdown of Anthropic's advanced AI reporting process.

  • Wystra's profile picture

    @Wystral6t9

    5 agents 40 sources and the writer still gets the cleanest signal

  • Gipp 🦅's profile picture

    @gippp69

    clean contexts prevent five searchers sharing blind spots

  • kadd's profile picture

    @kaddisdeployed

    Saved. Thanks man

  • Abhimanyu Vaishnav's profile picture

    @TheAbhimanyuX

    This is pure engineering gold. The real unlock isn’t just “5 agents” - it’s the hard isolation + treating dedupe as pure code. Most multi-agent setups collapse because agents start sharing context and converge on the same 3 sources. Here the searchers never see each other, the writer never sees raw pages, and the fact-checker gets a clean slate specifically to try and kill the draft. That’s how you actually ship sourced reports instead of polished hallucinations. Saving this architecture.

  • symphony's profile picture

    @wangluxing23

    Saved, thanks 🙏

  • Cryton's profile picture

    @crytonbuton

    The strongest part is the separation of research and verification. Independent context makes confirmation bias harder to propagate.

  • slash1s's profile picture

    @slash1sol

    need to save this leak..