Claim ledger

Your Multi-Agent System Is an Org Chart

Cognition said don't build them. Anthropic said do. A year on, they converge on the one question that decides it.

Read the essay On Substack Published Tests Law I: Bottleneck Migration

Claims
9
Verified at the primary source
9
Removed before publication
0
Last checked

9 claims: 9 verified.

Download this ledger: CSV · JSON · Markdown · CC BY 4.0 · Query it from Claude or ChatGPT

The evidence, row by row

Each row is a claim the essay makes, then the evidence recorded for it and the source it was checked against. For verified rows that is usually the exact words, where they sit and the day they were read. The label says how far it was checked.

What the labels mean
Verified
Checked against the primary source itself by a checker who did not draft the piece, usually with the exact words, where they sit and the date read.
Executed
A run or observation done for the piece: code, a query, a count, or a check made live in an app. The claim is what it returned. Run records are not published.
Checked
Checked against its source by a separate checker in the older ledger format, which recorded no quote, locator or date.
Reported
Not verified word for word against a primary source: carried from a secondary source, from one that could not be opened in full, or supported only in part. The essay words it accordingly.
Struck
Drafted, checked and removed before publication. Kept here, crossed out, with the reason.
Excluded
Considered and deliberately left out of the piece. Kept here with the reason.
  1. MA1 Verified Read

    Cognition's June 2025 post, written from its own experience building coding agents and explicitly dated to 2025, said running multiple agents in collaboration produced fragile systems because decision-making ended up too dispersed and context could not be shared thoroughly enough between the agents.

    in 2025, running multiple agents in collaboration only results in fragile systems … decision-making … too dispersed and context isn’t able to be shared thoroughly enough

    Walden Yan, Cognition, Don't Build Multi-Agents, 12 June 2025 · section "Applying the Principles", sub-section "Multi-Agents", final paragraph · cognition.com

    Link
    Cite

    Walden Yan, Cognition, Don't Build Multi-Agents, 12 June 2025, section "Applying the Principles", sub-section "Multi-Agents", final paragraph, https://cognition.com/blog/dont-build-multi-agents. Checked in: Claim Ledger, "Your Multi-Agent System Is an Org Chart", The Durability Curve, row MA1, https://durabilitycurve.com/claims/your-multi-agent-system-is-an-org-chart/#c-MA1 (source read 2026-10-03).

    Report an error
  2. MA2 Verified Read

    On Anthropic's own internal research eval, not an external benchmark, its multi-agent research system (a Claude Opus 4 lead agent with Claude Sonnet 4 subagents) outperformed single-agent Claude Opus 4 by 90.2%.

    Claude Opus 4 as the lead agent and Claude Sonnet 4 subagents outperformed single-agent Claude Opus 4 by 90.2% on our internal research eval

    Anthropic Engineering, How we built our multi-agent research system, 13 June 2025 · section "Benefits of a multi-agent system", second paragraph · anthropic.com

    Link
    Cite

    Anthropic Engineering, How we built our multi-agent research system, 13 June 2025, section "Benefits of a multi-agent system", second paragraph, https://www.anthropic.com/engineering/multi-agent-research-system. Checked in: Claim Ledger, "Your Multi-Agent System Is an Org Chart", The Durability Curve, row MA2, https://durabilitycurve.com/claims/your-multi-agent-system-is-an-org-chart/#c-MA2 (source read 2026-10-03).

    Report an error
  3. MA3 Verified Read

    On the BrowseComp browsing evaluation specifically, Anthropic found that token usage by itself explained 80% of the performance variance; three factors together explained 95%.

    three factors explained 95% of the performance variance in the BrowseComp evaluation … token usage by itself explains 80% of the variance

    Anthropic Engineering, How we built our multi-agent research system, 13 June 2025 · section "Benefits of a multi-agent system", third paragraph · anthropic.com

    Link
    Cite

    Anthropic Engineering, How we built our multi-agent research system, 13 June 2025, section "Benefits of a multi-agent system", third paragraph, https://www.anthropic.com/engineering/multi-agent-research-system. Checked in: Claim Ledger, "Your Multi-Agent System Is an Org Chart", The Durability Curve, row MA3, https://durabilitycurve.com/claims/your-multi-agent-system-is-an-org-chart/#c-MA3 (source read 2026-10-03).

    Report an error
  4. MA4 Verified Read

    In Anthropic's own data, multi-agent systems used about 15× more tokens than chats, against about 4× for single agents.

    In our data, agents typically use about 4× more tokens than chat interactions, and multi-agent systems use about 15× more tokens than chats

    Anthropic Engineering, How we built our multi-agent research system, 13 June 2025 · section "Benefits of a multi-agent system", fourth paragraph · anthropic.com

    Link
    Cite

    Anthropic Engineering, How we built our multi-agent research system, 13 June 2025, section "Benefits of a multi-agent system", fourth paragraph, https://www.anthropic.com/engineering/multi-agent-research-system. Checked in: Claim Ledger, "Your Multi-Agent System Is an Org Chart", The Durability Curve, row MA4, https://durabilitycurve.com/claims/your-multi-agent-system-is-an-org-chart/#c-MA4 (source read 2026-10-03).

    Report an error
  5. MA5 Verified Read

    Anthropic wrote in June 2025 that domains requiring all agents to share the same context, or involving many dependencies between agents, are not a good fit for multi-agent systems today, and that most coding tasks involve fewer truly parallelisable tasks than research.

    share the same context or involve many dependencies between agents are not a good fit … most coding tasks involve fewer truly parallelizable tasks than research

    Anthropic Engineering, How we built our multi-agent research system, 13 June 2025 · section "Benefits of a multi-agent system", fourth paragraph · anthropic.com

    Link
    Cite

    Anthropic Engineering, How we built our multi-agent research system, 13 June 2025, section "Benefits of a multi-agent system", fourth paragraph, https://www.anthropic.com/engineering/multi-agent-research-system. Checked in: Claim Ledger, "Your Multi-Agent System Is an Org Chart", The Durability Curve, row MA5, https://durabilitycurve.com/claims/your-multi-agent-system-is-an-org-chart/#c-MA5 (source read 2026-10-03).

    Report an error
  6. MA6 Verified Read

    A preprint by Tran and Kiela found that, with reasoning-token budgets held equal, single-agent systems consistently match or outperform multi-agent systems on multi-hop reasoning tasks across three model families (Qwen3, DeepSeek-R1-Distill-Llama and Gemini 2.5). The finding covers multi-hop reasoning only.

    three model families (Qwen3, DeepSeek-R1-Distill-Llama, and Gemini 2.5) … SAS consistently match or outperform MAS on multi-hop reasoning tasks when reasoning tokens are held constant

    Dat Tran and Douwe Kiela, Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets, arXiv preprint 2604.02460v2 · Abstract (revised 11 April 2026) · arxiv.org

    Link
    Cite

    Dat Tran and Douwe Kiela, Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets, arXiv preprint 2604.02460v2, Abstract (revised 11 April 2026), https://arxiv.org/abs/2604.02460. Checked in: Claim Ledger, "Your Multi-Agent System Is an Org Chart", The Durability Curve, row MA6, https://durabilitycurve.com/claims/your-multi-agent-system-is-an-org-chart/#c-MA6 (source read 2026-10-03).

    Report an error
  7. MA7 Verified Read

    Claude Code's current sub-agents documentation lists its built-in Explore and Plan subagents with read-only tools, Write and Edit denied.

    Explore … Tools: read-only tools; Write and Edit are denied … Plan … Tools: read-only tools; Write and Edit are denied

    Claude Code Docs, Create custom subagents · section "Built-in subagents", Explore and Plan tabs, Tools line · code.claude.com

    Link
    Cite

    Claude Code Docs, Create custom subagents, section "Built-in subagents", Explore and Plan tabs, Tools line, https://code.claude.com/docs/en/sub-agents. Checked in: Claim Ledger, "Your Multi-Agent System Is an Org Chart", The Durability Curve, row MA7, https://durabilitycurve.com/claims/your-multi-agent-system-is-an-org-chart/#c-MA7 (source read 2026-10-03).

    Report an error
  8. MA8 Verified Read

    Cognition's April 2026 follow-up said its original observations still hold for parallel-writer swarms, and that the multi-agent setups that work in its practice are those where multiple agents contribute intelligence while writes stay single-threaded.

    Our original observations still hold today for parallel-writer swarms … setups where multiple agents contribute intelligence to a task while writes stay single-threaded

    Walden Yan, Cognition, Multi-Agents: What's Actually Working, 22 April 2026 · introduction, second paragraph · cognition.com

    Link
    Cite

    Walden Yan, Cognition, Multi-Agents: What's Actually Working, 22 April 2026, introduction, second paragraph, https://cognition.com/blog/multi-agents-working. Checked in: Claim Ledger, "Your Multi-Agent System Is an Org Chart", The Durability Curve, row MA8, https://durabilitycurve.com/claims/your-multi-agent-system-is-an-org-chart/#c-MA8 (source read 2026-10-03).

    Report an error
  9. MA9 Verified Read

    Cognition states, as its own company figure, that Devin usage in its largest-enterprises segment, which it describes as traditionally cautious toward new technologies, grew roughly 8× over the six months before its April 2026 post.

    Devin usage in our largest enterprises segment … traditionally been cautious toward adopting new technologies, we see an explosion over the last 6 months (~8x)

    Walden Yan, Cognition, Multi-Agents: What's Actually Working, 22 April 2026 · section "What Changed in the Last 10 Months", first paragraph · cognition.com

    Link
    Cite

    Walden Yan, Cognition, Multi-Agents: What's Actually Working, 22 April 2026, section "What Changed in the Last 10 Months", first paragraph, https://cognition.com/blog/multi-agents-working. Checked in: Claim Ledger, "Your Multi-Agent System Is an Org Chart", The Durability Curve, row MA9, https://durabilitycurve.com/claims/your-multi-agent-system-is-an-org-chart/#c-MA9 (source read 2026-10-03).

    Report an error

Cite and reuse

A single claim
Use the row's Cite button. It names the original source first, then this row, which carries its own link.
This ledger
Floyd, Harry (2026). Claim Ledger: Your Multi-Agent System Is an Org Chart. The Durability Curve. https://durabilitycurve.com/claims/your-multi-agent-system-is-an-org-chart/
The essay
Floyd, Harry (2026). Your Multi-Agent System Is an Org Chart. The Durability Curve. https://durabilitycurve.com/blog/your-multi-agent-system-is-an-org-chart/

The ledger data is licensed CC BY 4.0: reuse it, quote it or train on it, with credit to The Durability Curve and a link. Read the licence. Machine copies: JSON, CSV, Markdown.