# Features > Everything GreatArrow.ai does: memory, integrations, agents, scheduling, documents and cost control. Canonical page: https://www.greatarrow.ai/features Site map for agents: https://www.greatarrow.ai/llms.txt (full text: https://www.greatarrow.ai/llms-full.txt) 649 MCP tools · 45 connectable providers · 21 specialist agents · 21 AI clients with a first-class install path. ## Knows your business Give every AI you use a shared, cited memory of your work — searchable across clients. - **Cross-model shared memory** — One workspace memory store with semantic search, shared across the AI clients you connect. - **Grounded Ask-AI chat** — Ask-AI chat that answers from your workspace data and attaches citations to its sources. - **Document intelligence** — Upload docs and they're parsed, OCR'd when needed, and made searchable across your workspace. - **Conversation history across clients** — Ingest transcripts from clients like Claude Code, Claude Desktop, and OpenAI Codex into one history. - **Entity & knowledge graph** — People and organizations are linked into a typed graph you can explore to see how facts connect. ## Does the work Hand work to a team of agents and a board that tracks it end to end. - **21 specialist agents** — An orchestrator delegates work to specialist agents that pick up and act on assigned board tasks. - **Kanban task board** — Plan and track work on a board of cards with statuses and assignees, including assignment to agents. - **Goals with real finish dates** — Group cards under a goal and see when it will actually finish, worked out from how fast you have been closing them. - **A weekly operating rhythm** — Quarterly priorities, weekly numbers and one 90-minute meeting, built from what your workspace already shows. - **Agents that brief each other** — A private channel where your connected AIs hand off work and answer each other, so you stop relaying between them. - **Lead pipeline** — A pipeline with stages and deal values on the same records as your contacts, so a lead and a person are never two entries. - **Public booking pages** — Share a link and let people book you against your real availability, in their own timezone. - **AI meeting scheduling** — Schedule meetings with timezone-aware availability, calendar sync, and shareable booking links. - **Planning** — A guided wizard turns context into a sprint plan, sending items to your board or Jira. - **Contacts / lightweight CRM** — Track contacts across pipeline stages with deal values and pipeline metrics. - **Scheduled automations** — Set agents to run on a recurring schedule so routine work happens without you asking. ## Create Draft, design, and capture — by voice or just by asking. - **AI tools workbench** — Browse and run the workspace's AI tools from a single workbench page. - **Canva designs** — Start from a blank Canva design or brand template, let agents autofill it, then export. - **Voice interface** — Speak a command and the Web Speech transcript is matched against an intent catalog that routes the action. - **Scratchpad** — Capture quick notes with microphone dictation and opt in any note to workspace memory for RAG. - **A pitch page you can send investors** — Write your pitch once and share it on a private password-protected page; investors only ever see what you published. - **Save a view and come back to it** — Save any selection of your work — a dashboard, a client page, a rollup — and come back to it or hand it to someone. ## Control & insight See what everything costs, route to the right model, and stay in control. - **Cost intelligence & budgets** — See AI spend broken out by agent and MCP client, and track usage against budget ceilings. - **Smart model routing** — Route each task to the best-in-class or lowest-cost model automatically — or bring your own key. - **Proactive suggestions** — Great Arrow notices, from real usage, when connecting an app or flipping a setting would help — and nudges you. - **AI-composable business dashboard** — Build your business dashboard by asking AI to add the metrics and widgets you want. - **Accomplishments** — Track shipped work and generate progress reports or resumes from it. - **Doc Guardian documentation auditing** — An LLM grounds in your repo snapshot to flag documentation statements the code contradicts. - **Team workspaces & roles** — Organize work into shared workspaces with Owner, Admin, Member, and Viewer roles. - **Every expense next to what AI costs** — Log what the business spends alongside what your AI costs, so one view answers where the money went. - **Report a problem from the page it happened on** — Point at anything that looks wrong and file it without leaving the screen; the report carries the context with it. ## Connect anywhere Wire in your stack and let every AI you use act on it. - **45 providers** — Connect Google Workspace, Microsoft 365, Slack, Notion, GitHub, Jira, and more from one place. - **649 built-in actions your AIs can use** — Actions your connected AIs can take — from searching memory to booking meetings — grouped into five permission levels you control. - **Memory for the models on your own machine** — Run open models in LM Studio or Ollama and give them the same memory every other client reads. The model stays local; only the lookups leave. - **One-click install everywhere** — Install from a universal web flow or download an Apple-notarized macOS .pkg. - **Encrypted at rest** — Your content and connected-tool credentials are encrypted at rest. Bring your own key available on Enterprise. - **Share a workspace with a link or a QR code** — Hand someone one link to join or to see a page — and revoke it just as quickly when they should not have it any more.