Startups run on details — everything matters, and it all moves fast. Decisive puts AI on that problem: it reads your whole workspace, every turn, so speed doesn’t cost you the details.
A model without context is a brilliant stranger — it can reason, but it doesn’t know your work. In Decisive everything lives on one surface, so the AI reads all of it.
No DMs, no channels, no seventh tab. Everything the team knows lives on one open surface.
Every turn, the live workspace becomes one cached block Claude reads before it answers. No ranking, no guessing.
The AI writes into the same workspace it reads. Tomorrow’s context includes everything it did today.
Most tools search for context or fetch it a piece at a time. Decisive does the simple thing: it reads everything.
Everything, read before it answers.
Every turn, @AI gets a live snapshot of the whole
workspace. Then it doesn’t just talk — it acts.
chat · tasks · docs · decisions · members
assembles a live snapshot — cached per turn
reads it all in a 1M-token window
creates, triages, replies, decides, ships
@AI works through real workspace tools — triaging
tasks, drafting decisions, replying in chat, building pages. The loop runs in your
browser; the server is just a relay.
› @AI triage the new login reports
↳ read list_recent_chat_messages · read_discussion · list_tasks
↳ act create_task “Fix OAuth redirect loop” · P1
↳ act send_chat_message “Grouped 3 reports into T-142.”
✓ done — full workspace in context
build_page is generative UI — a live, interactive
page composed in your sidebar.
Runs on Anthropic’s side, capped at five lookups a turn.
Custom slash commands run the same loop — each with its own model tier and context level.
The same teammate, with the same complete context, wherever the work happens.
Mention @AI in chat or any thread. It answers in place — or just does the thing.
@AI · chat · comments · threads
Press ⌘O and talk. It listens, thinks and answers out loud — same context, same tools.
Deepgram → Claude → ElevenLabs
Call it into a live huddle. It hears the room and can act on what was said.
on-demand · in-call · acts live
Launch a coding agent from a task. It works in its own cloud branch and opens the PR.
Claude Code · 1 task = 1 branch · → PR
Your dev server, live in the cloud. Claude Code edits while you watch — then ships a PR.
live cloud preview · then a PR
Decisive is an MCP server. Connect Claude Code, Cursor or Codex — your context follows.
MCP · OAuth 2.1 · 13 tools
Everything the AI does — tasks it opens, replies it sends, pages it builds — lands in the open and becomes part of the next turn’s context. A teammate that remembers gets more useful every week.
read→decide→act→land in the open↺
Claude holds a million tokens at once — a lean team’s whole workspace fits many times over. No summarizing, no sampling; as the windows grow, Decisive just reads more.
A lean team's entire workspace is a fraction of the window — so it all fits, with room to spare. Retrieval systems pass a sliver and hope it's the right one. Decisive loads the whole thing, then leaves 5× headroom for the day your workspace is bigger and the windows are larger still.
Decisive is in alpha. Bring your GitHub repo and a Claude key — the AI shows up already knowing everything.