Closed Beta

Turn yourself into a team. Turn your team into an army.

Jackdaw gives every person and every agent the context, purpose, and tools to work together. No starting over. No guessing what matters.

  • Cross-provider
  • Source-backed
  • Human-approved
Your data never leaves your control. Ever.
Wiki / Atlas pilot

Design partner pulse

POG3 editing

The current signal from Atlas pilotand Partner onboarding.

Team note

Use the short setup guide in tomorrow’s partner email.

What is current
SignalOwnerCurrent detail
Setup questionsPriya1 this week
Short guideGraceIn progress
Partner callOmarTuesday · 11:00
Next
Add the revised guide link to the partner email
Shared with the Atlas pilot team
Slack3 setup questions
LinearGuide ready for review
CalendarCall moved to 11:30
The missing teammate layer

Why does AI still feel like a tool—not a teammate?

  1. 01

    Because it doesn’t know you.

    Your decisions, priorities, history, and relationships are scattered across disconnected tools.

  2. 02

    Because even when it knows everything, it can still get it wrong.

    Facts conflict, plans change, and old decisions remain searchable beside the new ones.

  3. 03

    Because it doesn’t understand why the work matters.

    A task without the goal, constraints, and judgment behind it is still just an instruction.

  4. 04

    Because it doesn’t work from the same place as the team.

    The team works in shared notes and plans. The AI starts over in a separate chat.

01 / 04
The teammate layer

Jackdaw is where your team and every agent work together from a single source of truth.

People keep the work accurate in a shared Wiki. Connected sources keep it informed. Purpose and guardrails stay attached. Agents act from the same context as the team.

1The whole picture stays connected.
2People keep it true.
3The why lives beside the facts.
4Agents work from this page.
1 The whole picture stays connected.
Gmail4 dietary notes
CalendarDoors at 8:45 AM
Drive18 volunteers
2 People keep it true.
Wiki / Spring service day

Saturday volunteer workshop

MT2 here

Working page for Spring service day and New volunteers.

3 The why lives beside the facts.

Make every first-time volunteer feel useful from the moment they arrive.

DetailOwnerCurrent
Dietary notesMaya4 received
Doors openTheo8:45 AM
VolunteersMaya18 confirmed

Pair every first-timer with a returning volunteer. Keep phone numbers private.

Maya corrected the prep time to 8:15
Saved · shared with the service-day team
The shared workspace

Write anything. Work on it together. Use it everywhere.

Notes, plans, tables, checklists, code, and decisions live together in Jackdaw. People shape them together. Every agent starts from the same source of truth.

Wiki / Customer onboarding

Customer onboarding weekly

GOP3 editing

Keep the welcome flow accurate without making the team hunt through chat. This page connects the work forNorthwind rollout and Customer onboarding.

This week

The welcome email should point to Thursday office hours.

Touchpoints
TouchpointOwnerCurrent detail
Welcome emailPriyaDraft ready
Office hoursGraceWednesday · 3:00 PM
Getting-started guideOmarReviewed
Before Friday
Replace the old office-hours link
Send the Friday welcome-email draft
Saved · shared with the onboarding team
Connected context

Your work is already full of context. Bring it with you.

Connect your inbox, calendar, chat, documents, code, and the tools your team already uses. Jackdaw brings the useful details into your Wiki with their sources attached—so your team has the whole picture and your agents don't start blind.

Gmail
Gmail
Google Calendar
Google Calendar
Google Drive
Google Drive
Outlook
Outlook
GitHub
GitHub
GitLab
GitLab
Slack
Slack
Linear
Linear
Discord
Discord
Notion
Notion
Todoist
Todoist
Strava
Strava
iMessage
iMessage
Apple Notes
Apple Notes
Safari
Safari
Chrome
Chrome
Cursor
Cursor
ChatGPT
ChatGPT
Claude
Claude
Gemini
Gemini
Codebase
Any MCP tool
Agents you build

Add the help your team is missing.

Create an engineering manager, chief of staff, project manager, researcher, personal assistant, or whatever your team needs. Give each one a mission, rules, tools, and the same shared context as everyone else.

  • Several duties, each on its own trigger
  • Your current context and standing rules on every run
  • One Mission Control for work, requests, and results
See what an agent can actually do

Engineering Manager

Jackdaw agent

Catches who is blocked on whom, and keeps Claude Code moving when it stalls.

Needs your team threads and coding sessions
Surfaces the blocker and who owns it. Does not reassign anyone.

Chief of Staff

Jackdaw agent

Builds the update you owe from what actually happened, and keeps the decision trail.

Needs your team threads and tickets
Writes the briefing into chat. Sending it stays yours.

Personal Assistant

Jackdaw agent

Keeps an eye on your inbox, calendar, and the loose ends you keep meaning to get to.

Needs your email, calendar, and personal Wiki
Drafts replies and prepares the work. Sending and scheduling stay yours.

See how far your team can go.

Routine work keeps moving. Decisions stay connected. People have more time for the judgment, creativity, and relationships that only they can bring.

A small creative team laughing together around their work
Pricing

Start with your team.

One shared source of truth for the people and agents doing the work.

TeamFull Jackdaw
$25/ seat / month

For teams that want their people, tools, and agents working from the same context.

  • Shared team memory across projects
  • Everything in Personal
  • Admin controls & audit logs
  • Per-source access policies

Jackdaw works for your own life, too.

Personal
$15/ month

For solo work across the AI tools you connect.

  • Full personal context history
  • Connect supported personal sources
  • Use across compatible AI clients
  • Encrypted, exportable, yours
Family
$29/ month

Up to 5 members. One shared memory for the household.

  • Up to 5 household members
  • Shared family context
  • Everything in Personal
  • Each member's data stays private

Closed beta pricing. Locked in for early members.

Frequently asked questions

How is this different from ChatGPT memory or Claude Projects?

Provider memory is useful, but it stays inside one provider and mostly learns from what happens there. Jackdaw keeps approved facts, constraints, corrections, and rejections in a visible wiki above your AI tools. Connect another compatible client and the same durable context can come with you.

Does it work with Cursor, Claude Code, or my IDE?

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.

What happens to my corrections when I switch models?

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.

Do you train AI models on my data?

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.

Can I delete my data?

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.

How is my data secured?

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.

Closed Beta

Give everyone working for you something they can trust.

Jackdaw is in closed beta. Request access and we’ll reach out personally when a spot opens.

Spots are limited. We’ll reach out personally.

Jackdaw — the source of truth for people and agents