CouncilAI

CouncilAI - Multi-LLM consensus assistant for ChatGPT, Claude, Gemini, and Perplexity.

**ChatGPT · Claude · Gemini · Perplexity — compare, converge, and organize with one question.** `CouncilAI` (Korean brand: `인공지능 원탁회의`) is a Chrome extension that ties four AI web services into one round-based flow so you can **review answers side by side in a single tab**. 🔥 **CouncilAI brings a "multi-LLM roundtable" into your browser.** Spend less time copying and pasting across tabs and **cross-check** each model's perspective inside **structured rounds (R1–R4)**. 💪 **Why use it?** 👉 **Turn multi-AI comparison into one course** ✔️ Click the extension icon → a **full-browser-tab dashboard** opens. No more fragile popups closing mid-session ✔️ R1, R2, and R3 show ChatGPT, Gemini, and Claude **side-by-side in one tab** — no tab switching ✔️ R2.5 fact-check opens Perplexity in a **dedicated separate window**, eliminating iframe connection refusals entirely ✔️ **Round timeline** shows completed and in-progress stages at a glance 👉 **If it stalls, pull it forward again** ✔️ **Restart this round** — close the current round tab and reopen it fresh when injection fails ✔️ **Per-bot restart** — restart only the stuck bot; others keep running ✔️ **Force complete** — manually advance when a limit modal blocks response detection (e.g. Claude free tier) ✔️ **Per-bot archive tabs** — browse R1/R2/R3/R4 response history inside each bot column 👉 **Keep your results** ✔️ Export full debate or individual rounds as **Markdown, plain text, HTML, or JSON** ✔️ R4 convergence synthesis panel included in exports 👉 **Language is your choice** ✔️ Switch between **Korean ⇌ English** with the dropdown at the top of the dashboard 💻 **Quick start** 🔸 **Install** from the Chrome Web Store and pin it to the toolbar. 🔸 **Sign in** to **ChatGPT, Claude, Gemini, and Perplexity**. 🔸 Click the extension icon → a **full-tab dashboard** opens in a new tab. 🔸 Enter your question and click **Start ▶**. 🔸 Watch all three bots respond side by side in the R1 tab; advance to R2 when ready. 🔸 R2.5 opens a Perplexity window automatically for fact-checking. 🔸 After R4 convergence, export results in your preferred format. ❓ **FAQ** 📌 **Which AI services do I need?** You should have **web accounts** for ChatGPT, Claude, Gemini, and Perplexity and be **signed in**. 📌 **Do I need a separate API key?** **No.** CouncilAI coordinates the **web service tabs** you already use. 📌 **I had a popup that kept closing — is that fixed?** Yes. v1.1 removes the popup entirely. Clicking the icon opens a **full-tab dashboard** that stays open throughout the session. 📌 **Claude hit its free limit and the response is stuck.** Use the **✓ Force Done** button in Claude's column header. It advances the workflow while keeping any already-collected response. 📌 **Does CouncilAI guarantee answer accuracy?** **No.** CouncilAI is a tool that helps **compare, organize, and converge** your workflow. Final judgment is yours. 📌 **Where does my data go?** Progress state is stored in **`chrome.storage.local`** in your browser. CouncilAI **does not send state** to a separate developer server. Export files are saved **only on your PC**. 📪 **Contact** Questions or suggestions? Email **Chartrho@gmail.com**. For the privacy policy, see **https://sites.google.com/view/councilai-privacypolicy**. ### [B] Detailed User Guide · Policy · Technical Notes #### B.1 Product Overview `CouncilAI` is a browser extension that ties multiple AI responses into one workflow for comparison, convergence, and organization. v1.1 introduces a redesigned, full-tab UI based on these principles: - Popup removed → clicking the icon opens a **full-tab dashboard** - **Per-round independent tabs** — R1, R2, R2.5, and R3/R4 each open in a new tab - R1, R2, R3: **3-column side-by-side view** in one tab (ChatGPT, Gemini, Claude as iframes) - R2.5: Perplexity opens as a **standalone browser window** — no iframe, no connection refusals #### B.2 Core Value 1) Stronger comparability — see three model answers side by side, same tab, same scroll position 2) Stronger reproducibility — export prompts, responses, convergence results, and full state in multiple formats 3) Operational efficiency — fewer repeat entries, precise recovery tools when automation stalls 4) Decision support — R2.5 fact-check feeds into R3 revision; R4 produces a synthesized convergence result #### B.3 Supported Services - ChatGPT - Claude - Gemini - Perplexity (R2.5 fact-check only) You manage each account's sign-in and access; behavior may differ by service policy, billing tier, or access limits. #### B.4 Workflow (Round Structure) | Round | Role | UI Form | |-------|------|---------| | R1 | Initial response collection | 3-column tab (ChatGPT · Gemini · Claude) | | R2 | Cross-critique and revised responses | 3-column tab (new tab) | | R2.5 | Perplexity fact-check | Control tab + Perplexity standalone window | | R3 | Fact-check acceptance, critique, revision | 3-column tab (new tab) | | R4 | Convergence judgment and synthesis | Synthesis panel within R3 tab | Recovery controls are available in each round tab. #### B.5 Dashboard and User Controls **Round-level controls** - Round timeline — visualizes `R1 → R2 → R2.5 → R3 → R4` progress (done / active / pending) - Restart this round — closes the current round tab and reopens it (for injection failures) - Next round button — activates automatically when all bots complete **Bot-level controls** - Per-bot restart — restart only the target bot; other bots unaffected - Force complete — manually advance when response detection is blocked (e.g. free-tier modal) - Per-bot archive tabs — browse R1/R2/R3/R4 response history within each bot column **Export** - Full debate export (all rounds R1–R4) — Markdown / plain text / HTML / JSON - Per-round export — current round responses as Markdown The store build does **not** expose developer-only controls (force reset, debug log export, etc.). #### B.6 Exports | Format | Use case | |--------|----------| | Markdown | Notion, Obsidian, GitHub, documentation tools | | Plain text | Universal fallback, simple archiving | | HTML | Self-contained document viewable in any browser | | JSON | Structured data for further processing or records | Files are saved to your device. CouncilAI does not upload them to any server. #### B.7 Internationalization A language dropdown in the dashboard header lets you switch between **Korean** and **English** at any time. - The selection applies immediately to all UI elements: buttons, status badges, timeline labels, tooltips, and export document headers. - The setting is stored in `chrome.storage.local` and persists across sessions. Brand by locale: - Korean: `인공지능 원탁회의` - English: `CouncilAI` #### B.8 Privacy and Data Handling - CouncilAI runs locally in your browser. - State is stored in `chrome.storage.local`. - CouncilAI does not send state data to a separate developer server. - Export files are local downloads only. Interaction with ChatGPT / Claude / Gemini / Perplexity follows each provider's policies. #### B.9 Before You Start For stable use: - sign in to all four target services beforehand, - stable network, - up-to-date browser, - keep CouncilAI tabs open while the session is running (do not close round tabs manually), - if your browser blocks popups, allow popups for the Perplexity domain so R2.5 can open its standalone window. #### B.10 Limitations and Notes - Target UI changes may require selector updates. - Speed and results may vary by rate limits, latency, or policy changes per service. - CouncilAI assists comparison and organization; it does **not** guarantee answer quality. - Final decisions are yours. #### B.11 Recommended Use Cases 1) Research — collect multiple LLM views quickly; use R2.5 to verify facts; converge in R4 2) Draft review — cross-critique in R2, refine with fact-check in R3, extract consistent conclusion in R4 3) Risk checks — spot model disagreement in R2; use Perplexity to verify; prioritize follow-up accordingly 4) Reporting — export the full debate history as HTML or Markdown for documentation #### B.12 Operating Summary CouncilAI does not force one model's answer as "the truth." It helps you gather, organize, and converge multiple answers so you can reach conclusions with clearer rationale. Core value: - cross-model review, - automation of repetitive work, - traceable outputs, - user-centered final judgment.