[lilyshen0722]

GTM copy PR, as CTO asked.

• Question: keeps docs(landing): fix the FALSE clauses in landing FAQ 1-6 (#2884) #2886's wording ("Should one agent run as one loop instead of subagents?…"). GTM approves it. It drops the unsupported attribution, and FAQ 6 isn't one of the five fixed GEO questions.
• Answer: removes "For a single agent, we agree: each expert should be one strong loop." No file on main supports that premise, and the docs(audits): landing FAQ and firstRun claim table (TASK-009) #2884 audit scores it FALSE. It now opens "That's a choice inside each agent." "several of those experts" becomes "several agents", since its antecedent is gone. The rest is unchanged.

🤖 Generated with Claude Code

https://claude.ai/code/session_01MDs9DQ4A4V1Vdp54isbxo5

[coderabbitai]

No actionable comments were generated in the recent review.

Recent review info

Run configuration

• Source mode: Auto
• Repository: Team-Commonly/commonly
• Branch: gtm/faq6-premise
• File: .coderabbit.yaml
• Commit: 41a9902
• Layers: Repository YAML
• Review profile: QUIET
• Plan: Advanced
• Run ID: 6a9e3924-ab84-452d-b123-b30b3c719d87

Commits

Reviewing files that changed from the base of the PR and between a6c112a and 41a9902.

Files selected for processing: 1

• frontend/src/content/landing-faq.json

Included review availability: This review used your included allowance. Your plan provides up to 10 included reviews per hour; 9 remain after this review.

Walkthrough

The landing FAQ now describes loop design as a choice within each agent. Its explanation of team work, task claims, and connector grants remains.

Changes: Landing FAQ wording

Layer / File(s)	Summary
Update agent loop wording frontend/src/content/landing-faq.json	The answer describes loop design as a choice within each agent. It retains the descriptions of team work, task claims, and connector grants.

Priority: Low

Estimated code review effort: 1 (Trivial) | ~3 minutes

Change: Other

Possibly related PRs

• Team-Commonly/commonly#2886: Updates FAQ 6 wording about shared conversations and removes its subagent statement.
• Team-Commonly/commonly#2884: Audits the landing FAQ and identifies the FAQ 6 premise addressed here.

Merge Risk: Minimal · up to 41a99

The FAQ update is limited to clarifying loop design within an agent and is ready to merge.

Pre-merge checks: 4

Check name	Status	Explanation
Title check		The title clearly identifies the FAQ copy change and the removal of the unsupported one-loop premise.
Description check		The description directly explains the FAQ 6 wording changes and the reason for removing the unsupported premise.
Linked Issues check		Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check		Check skipped because no linked issues were found for this pull request.

Finishing Touches

🧪 Generate unit tests (beta)

• Commit to this branch
• Create a new PR

• Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

_{Comment @coderabbitai help to get the list of available commands.}

[lilyshen0722]

D138 copy gate at 41a9902. CI is green; every check completed as success or skipped. There are no review threads.

1. The opener answers the question and claims nothing. The question at landing-faq.json:23 asks "Should one agent run as one loop instead of subagents?". "That's a choice inside each agent." answers it by saying how each agent runs is that agent's own choice. It makes no claim about what Commonly does. That is accurate: the Claude Code adapter's subagent cue (claude.js:113-116) is a runtime choice, not something the platform imposes. The question's second half, "Isn't Commonly a multi-agent system?", is still answered by the unchanged "Across a team…" sentence.
2. No claim is lost. The removed text is "For a single agent, we agree: each expert should be one strong loop." That is the premise my #2884 audit scored FALSE: "we agree" agreed with an unsourced claim (Landing FAQ 6 (premise, in the question)). Changing "several of those experts" to "several agents" only drops the back-reference to that sentence. "Divides by expertise and ownership" and "each running under its own owner" are still there, so the TRUE row is unchanged. A word diff confirms the rest of the answer is byte-identical.
3. There is a single source. landingFaq.ts:1 imports landing-faq.json into LANDING_FAQ, and buildFaqPageJsonLd (:30-37) emits each answer verbatim. generate-seo-pages.mjs:589 reads the same JSON for the static landing page and its faqSchema (:491). No other copy of the old text exists in frontend/, so there is nothing else to edit.

Non-blocking: once this merges, the #2884 audit's "we agree" notes at :16 and :69 become historical. That's fine, because its verdicts are pinned to a6058f39d.

Written by Lumen, a Commonly agent — https://commonly.me/v2/pods/6a692a1be833c668acdb84cf

GATE: PASS