Design partner pulse
The current signal from Atlas pilotand Partner onboarding.
Use the short setup guide in tomorrow’s partner email.
Jackdaw resolves what your team has actually decided, then preserves it—with its owners, evidence, changes, and limits—in one source of truth people can maintain. Agents receive the relevant parts when they run.
The current signal from Atlas pilotand Partner onboarding.
Use the short setup guide in tomorrow’s partner email.
Slack3 setup questions
LinearGuide ready for review
CalendarCall moved to 11:30Decisions change while old versions remain visible. People compensate with status meetings and repeated briefings. AI acts on whichever version it retrieves.
A product brief, an architecture note, and a coding agent point in different directions. Jackdaw gets the conflict in front of the engineering lead, preserves the release boundary, and gives every coding agent the resolved decision.
Working page for Guest checkout and Release 1.14.
Ship guest checkout without emptying saved carts for returning users.
Keep the fallback until saved carts are migrated and the rollback window closes.
Notes, plans, decisions, owners, evidence, and history live on connected pages. People shape them together; agents work from them and bring new learning back.
Keep the welcome flow accurate without making the team hunt through chat. This page connects the work forNorthwind rollout and Customer onboarding.
The welcome email should point to Thursday office hours.
@GraceOffice hours · Wednesday at 3:00
@PriyaFriday welcome email
Today, 10:00 AM · Prepared from the Q3 launch, Checkout v2, and Northwind feedback. [14 sources]
Guest checkout: out of scope.
Ship Aug 1. Maya owns the invite-only rollout.
Drafted the recap with the Aug 1 date, the invite-only rollout, and the decisions from the room.
Updated the build plan for guest checkout and kept every change behind the approved flag.
Prepared the Northwind brief from what changed, why it changed, and the source behind each claim.
One page · current everywhere · proposed changes come back for approval
Jackdaw brings in information from your inbox, calendar, chat, documents, code, and other tools—then understands how it relates and reconciles it with what the team has settled.
Give an agent a lasting mission, recurring responsibilities, tools, and explicit boundaries. Every run starts from the team's current state; every useful discovery improves the next one.
Catches who is blocked on whom, and keeps Claude Code moving when it stalls.
Builds the update you owe from what actually happened, and keeps the decision trail.
Keeps an eye on your inbox, calendar, and the loose ends you keep meaning to get to.

Fewer status meetings and repeated briefings. Decisions survive the room. Agents keep routine work moving without drifting from what the team actually meant.

One shared source of truth for the people and agents doing the work.
For teams that want their people, tools, and agents working from the same context.
For solo work across the AI tools you connect.
Up to 5 members. One shared memory for the household.
Eligible new accounts get one 14-day trial; card required. Workspace subscriptions renew monthly until canceled. Ordinary assistant and connector processing includes daily safety limits. Agent runtime is metered separately at each AI provider’s published API rate, with no markup.
ChatGPT and Claude help an AI remember conversations. Jackdaw maintains the shared operating context across the team: what was decided, what changed, who owns it, what remains uncertain, and what each agent may act on. People can inspect and correct it, and connected agents use the same resolved state.
Yes. Jackdaw exposes your model via standard context protocols (MCP and provider-native APIs). If your tool can take a system prompt or call an MCP server, it can use Jackdaw.
Corrections stay in the current conversation first. Approve one for your long-term wiki and every connected provider can inherit the corrected fact instead of the value it replaced.
Never. Your model is yours alone. We do not use your personal data to train any foundation model, improve our product for other users, or sell to third parties.
Yes, completely. One request purges your structured memory, vector index, and message history — not a soft delete, a full cascade across every store. You can also disconnect individual sources at any time.
All connections are encrypted in transit via TLS. Disks are encrypted at rest. The architecture enforces hard per-user data isolation at every database layer — there is no code path that can return one user's data to another.
Jackdaw is in closed beta. Request access and we’ll reach out personally when a spot opens.