What's New

Version 6.2.6

3 months ago

Auto Model Migration - when providers release newer versions, stale model selections are detected and migrated automatically across council members, chairman, direct chat, and comparison. A notification explains what changed. Session expiry notifications replace silent failures. Network timeouts prevent hangs. Bounded notification caches. Comfort settings - new Appearance controls let you adjust colour warmth and contrast to reduce eye strain. Background completion badges - conversations that finish processing while you’re elsewhere now show a notification badge. Non-chat model filtering - audio, search, and other non-chat model variants no longer appear in model pickers. HTML title decoding - conversation titles with special characters now display correctly. Dynamic model pricing - pricing data is fetched live from providers rather than using static values. Switching between conversations now reliably shows the right content. A bug where a recently completed conversation’s synthesis could appear inside a different conversation has been fixed. The chair retry button (“Generate Chair’s Report”) now surfaces clear error messages when the chairman model fails, instead of appearing unresponsive. Network requests fail faster when a provider is unreachable, so one slow model no longer stalls the full council for minutes. Bug fixes and stability improvements. Apple Intelligence is now the built-in on-device option on supported iPhones and iPads. It works out of the box with no setup and no cloud. Add cloud providers on top if you want a multi-model Council. Direct Chat: one-on-one conversations with any configured model, including Apple Intelligence. Compare View: send the same prompt to several models side by side and see how they differ. Prompt Library: save, tag, favourite, and reuse your best prompts. Document Workspace: attach a PDF, Markdown file, or plain-text document and chat about its contents. Web Search with eight providers and clickable source citations beneat

Description

About The AI Council

A flawed analysis. A missed edge case. A recommendation you defended in a meeting, only to discover the model hallucinated half of it. Every professional using AI has had that moment. The uncomfortable truth: when you rely on one AI, you’re gambling that its blind spots don’t overlap with what actually matters. AI Council eliminates the gamble. Your question goes to multiple AI models simultaneously. Each one responds independently. Then - before you see a single word - they anonymously review each other’s work,... A flawed analysis. A missed edge case. A recommendation you defended in a meeting, only to discover the model hallucinated half of it. Every professional using AI has had that moment. The uncomfortable truth: when you rely on one AI, you’re gambling that its blind spots don’t overlap with what actually matters. AI Council eliminates the gamble. Your question goes to multiple AI models simultaneously. Each one responds independently. Then - before you see a single word - they anonymously review each other’s work, catching errors, challenging assumptions, identifying what the others missed. You get one answer: a synthesis of the strongest thinking from every model, with a confidence score showing exactly how much they agreed. High consensus means act with confidence. Significant disagreement means you’ve just saved yourself from trusting the wrong answer. Ask better questions, get better answers Weak prompts get weak answers. The built-in Prompt Enhancer rewrites your question using a separate referee model - sharpening the framing, clarifying intent, and tuning it for depth before a single council member sees it. Better input. Better output. Every time. Five ways to run your council • Standard: Independent responses, synthesised into one. • Devil’s Advocate: One model’s job is to find holes in the others’ reasoning. • Expert Panel: Models adopt specialist roles and critique from those perspectives. • Debate: Models argue before synthesis - you see the strongest case for each view. • Consensus Seeker: Finds and articulates where all models genuinely agree. Built for serious work Project Workspaces keep your context - codebase, strategy docs, requirements - attached to every query. Council Chains automate multi-stage thinking: Research, Analyse, Recommend, Plan. Evidence Mode forces every claim to cite a specific source. Decision Log preserves your most important calls with full council context. Your keys. Your models. Connect your own API keys from 20+ providers - OpenAI, Anthropic, Google, xAI, Mistral, Groq, DeepSeek, Perplexity, and more. You pay providers directly at their standard rates. No markup. No middleman. When providers release new model versions, the app migrates your selections automatically. All data stays on your device. API keys in Keychain. Nothing sent to us. Ever. For researchers, analysts, developers, and anyone whose work is too important to trust to one AI’s opinion. Read full description

The AI Council

Previews

Version 6.2.6

About The AI Council

Information

Country chart visibility