Run Smarter Meetings
Claude Meetings
Invite Claude into Google Meet to build Docs, Sheets, and Whiteboards live while your team talks, with a full post-call hub.
Step-by-step illustrated editions for modern tools, creative studios, coding, and workflows. Read right in your browser on a phone, tablet, or laptop, or save any 12-page magazine PDF in one click.
Three approachable starting points designed to give you a useful result in under 15 minutes.
Claude Meetings
Invite Claude into Google Meet to build Docs, Sheets, and Whiteboards live while your team talks, with a full post-call hub.
Claude Design
Turn ideas, brand guidelines, or real screens into clickable prototypes, slide decks, and product one-pagers.
Obsidian + Desktop AI Agents
Pair your Obsidian vault with Claude Desktop and Antigravity so your own notes power daily briefings and research.
Filter by what you want to do, pick a topic, or type a word below to find the right guide. Browse all 8 topic hubs.
Cinematic AI filmmaking studio powered by Veo 3.1, Ingredients consistency, Frames-to-Video transitions, and Scenebuilder.
Agent-first desktop IDE, parallel subagents, skills/MCP customization, and asynchronous GitHub PR automation with Jules.
Image-first visual remixing studio blending Subject, Scene & Style cards, hidden Gemini captions, Seed locking, and Whisk Animate.
Workspace AI video presentation studio turning Docs & Slides into narrated storyboards with AI voiceovers, avatars, teleprompter, and Veo B-roll.
AI-native UI/UX design studio turning prompts, sketches, and screenshots into multi-screen flows, Figma Auto-Layout frames, and Tailwind code.
Visual no-code AI mini-app studio chaining Gemini, Imagen, Veo, Lyria, and Web Search nodes into shareable interactive apps.
Flagship Gemini developer & power-user workbench for 1M+ token video/PDF analysis, Stream Realtime screen share, Build vibe-coding, and SDKs.
Zero-hallucination research studio for 500+ sources, live interactive Join Audio Overviews, Video Overviews, and clickable Mind Maps.
Autonomous multi-hundred-site research dossiers, split-screen Canvas live apps with embedded AI, and custom Drive-synced Gems.
Autonomous browser-use agent & Gemini Agent Mode running up to 10 parallel cloud browsers, Teach & Repeat skills, and safety gates.
Tailor Google Antigravity 2.0, IDE, CLI (agy), and Python SDK with progressive SKILL.md modules, AGENTS.md rules, lifecycle hooks.json, namespaced plugins, and message-board agent swarms.
Build low-latency bidirectional voice/vision agents with Gemini 3.8 Live (Extended Thinking, NON_BLOCKING tools, Live Translate) and multi-shot 4K generative video workflows with Gemini Omni 1.2 Flash.
Ship full-stack mobile and web apps with firebase-tools MCP, Firebase AI Logic + App Check, Data Connect, Android CLI, live Device Hub mirroring, Compose Preview sidecars, and XML Journey tests.
Customizing Claude Code from the inside with in-process TypeScript/JavaScript mods—building live terminal HUDs, prompt/tool interceptors, custom slash commands, and sec-default guardrails.
Turning messy voice and text brainstorms into real-time multiplayer visual canvases—mastering region-box prompting, retro clustering, Doc/Slide handoffs, and Miro/Lucid exports.
Connecting warehouses and CRMs to natural-language analytics—building auditable SQL charts, Certified Queries, Scrollytellers, Visual Shorts, and credential-safe live team shares.
Packaging reusable domain expertise across Claude.ai, Claude Desktop, and Claude Code—mastering 3-tier progressive disclosure, SKILL.md anatomy, skill-creator, and executable scripts.
Automating multi-step knowledge work across Desktop, Web, and Mobile—mastering background macOS Computer Use, built-in browser tasks, recurring /schedule runs, and SaaS connectors.
Building live multi-tab spreadsheets with cross-sheet formulas, dropdowns, charts, multiplayer edits, and .xlsx round-tripping alongside interactive MCP-connected Artifacts.
Running unattended multi-turn /goal completion contracts, supervising parallel sessions in claude agents, CLI-to-Desktop /resume, and publishing live PR walkthrough Artifacts.
Connecting Remote HTTPS/SSE and local stdio MCP servers across Claude surfaces and self-hosting cma-server agent sandboxes with scoped OAuth and Bedrock/Vertex routing.
Turning live Google Meet calls into visible co-creation sessions—mastering calendar auto-join, external-guest guardrails, live Whiteboards, Docs & Sheets, Interactive Connectors, and the post-meeting claude.ai hub.
Operating Anthropic's proactive Opus 5.5 cloud chief of staff—delivering Morning Briefs, persistent Cloud VM and headless browser sweeps, topic Channels, and Human-in-the-Loop approval gates.
Turning real codebases and brand guidelines into on-brand interactive prototypes, wireframes, decks, and product one-pagers—with live Control Knobs, inline comments, and Figma MCP or Claude Code handoffs.
Orchestrating parallel cloud worker branches with Claude Fable 5.2, Opus 5.5, and Haiku 5.5 alongside the Session Rail HUD, /btw and /fork context hygiene, Background MCP tasks, and identity safeguards.
Deploying continuous, reasoning-driven application security with Claude Mythos 5.2—mastering Deep Baseline Scans, living Threat Models, automated fix verification, and Claude Code MCP remediation.
Connect live local terminal sessions to webhooks, CI/CD, Sentry, and chat bridges with Channels, steer active repos from mobile via Remote Control, and isolate cross-device Dispatch runs.
Bridge authenticated Chrome tabs to Claude Code and Claude Desktop for live console and DOM forensics while compounding knowledge via /memories CRUD, CLAUDE.md, and Auto-Dream consolidation.
Configure TOML sandboxes, AGENTS.md constitutions, on-demand SKILL.md modules, GPT-6.1 Sol tiers, and parallel Codex Cloud PR containers.
Architect production multi-agent systems with handoffs, Agents-as-Tools, parallel input/output guardrails, built-in tracing, and stateful MCP sessions.
Master surgical split-pane Canvas diffs, multiplayer Spaces and Pages, and gated Agent Mode browser and desktop workflows.
Build sub-second speech-to-speech and live vision agents across WebRTC, WebSockets, and SIP telephony with native VAD barge-in and async MCP.
Organize durable workspaces inside ChatGPT Projects, seal confidential work behind Project-Only Memory walls, steer autonomous Deep Research plans, and schedule proactive Tasks & Dots briefings.
Stream typed UI messages, ToolLoopAgent runs, and structured Output.object() calls through Vercel AI Gateway with OIDC auth, virtual models, budgets, and automatic provider failover.
Build crash-safe agents and long-running pipelines using eve, Workflow 5 (WorkflowAgent, use workflow & use step), Vercel Queues, and Vercel Schedules.
Adopt cacheComponents and partialPrefetching in Next.js 16.3+, grow instant static App Shells with use cache and Suspense, and lock regressions with @next/playwright instant().
Ship one TypeScript bot codebase across Slack, Teams, Discord, Telegram, GitHub, and Linear with @chat-adapter/*, Vercel Connect OAuth, Sandbox PR reviews, and Workflow approval cards.
Cross-vendor context architecture (AGENTS.md, CLAUDE.md, Cursor rules), progressive disclosure, and Spec-to-Plan-to-Tasks agent workflows.
Designing specialist subagents, context forks, least-privilege tool scoping, lifecycle hooks, and multi-agent coordinator-worker swarms.
Running parallel coding agents without file collisions—covering Git worktree fleets, isolated ports/databases, safety hooks, and teardown.
Building persistent semantic memory for AI agents with structure-aware chunking, Chroma, pgvector, Qdrant, local Ollama, and hybrid retrieval.
Turning LLM vibe-checks into deterministic CI deploy gates with golden datasets, code scorers, calibrated LLM-as-judge, and Promptfoo.
Defending tool-calling and browsing AI agents against indirect prompt injection, poisoned MCP servers, secret exfiltration, and unsafe output sinks.
Running private, zero-per-token LLMs and embeddings on your own hardware—mastering GGUF quantization, Apple Silicon memory math, Ollama, and llama.cpp.
Replacing fragile LLM JSON parsing with fast, calibrated System One decisions—mastering Choice, Score, and Noul primitives, parallel fan-out, and confidence-gated routing.
Architect, test, and ship high-reliability Model Context Protocol servers in TypeScript (SDK v2) and Python (FastMCP)—mastering stateless Streamable HTTP factories, Zod v4 & outputSchema, OAuth 2.1, MCP Inspector, and 10-question evals.
Pair live Chrome DevTools MCP diagnostics (accessibility uid snapshots, LCP subpart traces, HttpOnly cookie forensics, and heap leak diffs) with deterministic Playwright E2E regression gates.
Architecting ephemeral microVMs, Firecracker, E2B, Docker, and gVisor environments for safe autonomous code execution, snapshotting, and network egress control.
Orchestrate parallel AI coding agents across isolated Git worktrees, coordinator-worker task DAGs, inline diff annotations, embedded browser captures, and remote SSH or mobile runtimes.
Instrument multi-agent workflows with OpenTelemetry GenAI trace trees, maximize static-first KV cache hit rates, compact historical tool outputs, and route models for predictable token FinOps.
Eliminate fragile regex loops with CFG/FSM constrained decoding, Pydantic v2 and Zod v4 contracts, streaming partial objects, explicit transition tables, idempotency, and HITL approval gates.
Turn spoken architectural intent into code and notes with mlx-whisper and Superwhisper, codebase symbol glossaries, voice PR diff triage, and automated Obsidian _inbox/ capture pipelines.
Transform messy PDFs, Office suites, and JS-heavy websites into clean, chunked, citation-ready Markdown using Docling, Granite-Docling VLM, Crawl4AI fit_markdown, Firecrawl v2, and SHA-256 deduplication.
Operating your Obsidian vault side-by-side with Claude Desktop and Google Antigravity Desktop—mastering Cowork folders, Local REST API MCP, the native Obsidian CLI, vault AGENTS.md rules, and scheduled briefings.
Turning flat Markdown notes into live relational databases and spatial visual boards—having Claude Desktop and Antigravity generate native .base views, YAML schemas, and .canvas architecture maps.
Building a Karpathy-style self-maintaining knowledge base in Obsidian where Claude Desktop and Antigravity compile raw PDFs, transcripts, and web clips into interlinked evergreen concept notes.
Building persistent, queryable knowledge graphs from codebases and notes that you explore visually in Obsidian and expose to AI agents via MCP.
Protecting private journals, API secrets, and multi-device sync when AI agents touch your vault—mastering privacy zones, sandboxes, prompt-injection defenses, and conflict-free Obsidian Sync + Git.
Turn web articles, academic PDFs, voice memos, and whiteboard photos into structured vault notes—mastering Obsidian Web Clipper templates, Interpreter {{"..."}} prompts, Knap filters, PDF++ citations, and quarantine-safe _inbox/ routing.
Compose songs, brand beds, and looping SFX using Suno v6 meta-tags, Personas, and 12-stem WAV/MIDI exports alongside ElevenLabs Music, Google Lyria 3.5, and 2026 commercial clearance rules.
Produce studio voice clones, W3C PLS phoneme lexicons, multi-speaker Gemini TTS dialogues, 175-language HeyGen lip-sync dubbing, and real-time WebRTC LiveAvatars with C2PA provenance.
Generate navigable 3D sets in Google Project Genie, direct camera paths and Act-One facial performances in Runway Gen-4.5, lock characters with Kling Elements, and finish in 4K at 24fps.
Turn rough briefs into investor-grade stories using Gamma fluid cards, Studio Mode, Theme Builder brand locks, Spotlight viewer analytics, API/MCP automation, and PowerPoint or Google Slides round-trips.
Win inline citations across ChatGPT Search, Perplexity, Google AI Overviews, Claude, and Gemini using Answer-First prose capsules, entity corroboration, JSON-LD schema, SSR parity, and Share-of-Voice KPIs.
Audit sites 0-100 with is-agentic, publish /llms.txt maps and Accept: text/markdown content negotiation, expose browser-native WebMCP tools, and enforce human-in-the-loop safety gates.
Capture meetings silently without call bots in Granola—merging rough human bullets with local transcripts, custom templates, Ask Granola folder Q&A, Recipes, and Slack, Linear, MCP, and Obsidian _inbox/ sync.
Try switching back to all topics or searching with a simpler word like meetings, notes, or video.