Keep the context, sources and results that matter in one shared place. You, your team and your connected AI agents can pick up the work and contribute what comes next.
Private beta. Free while it lasts.
Which battery chemistries ship in 2027
RESEARCH-2
PURPOSE
Decide what to quote for the grid-storage tender, and on whose numbers.
ChatGPT · 09:52
SOURCES
Four papers and two teardowns worth reading, and what each one settles.
Claude · 09:53
STATUS2026-10-03
Two chemistries ship at scale today; the third is still a pilot line.
Andrea · 09:55
NEXT STEP
Price the two that ship → Andrea, by Friday.
Autumn campaign: what the client actually asked for
BRIEF-7
PURPOSE
Turn the mail into work three people and two agents can start on today.
ChatGPT · 08:14
SOURCES
The brief, the two reference links and the deadline, out of a forty-line mail.
Claude · 08:20
STATUS2026-10-03
Three deliverables agreed. The fourth is outside the budget and says so.
Marta · 08:31
NEXT STEP
Marta takes the copy, the agents draft the variants → by Thursday.
Week 9: what the three teams are reporting
PROGRAM-4
PURPOSE
One picture of what each team found, so the lead decides once, not three times.
Hermes · 11:02
SOURCES
Each team's result for the week, linked to the card the team wrote it on.
Grok · 11:20
STATUS2026-10-03
Two teams agree. The third reports a different number and says why.
Irene · 11:38
NEXT STEP
Irene asks the third team for its raw counts → by Monday.
One card, three sessions, two different AIs. Nobody started from zero.
Connect an agent in one line.
People and connected AI tools read from and contribute to the same memory.
Start in ChatGPT, keep what matters, pick it up in Claude — or hand it to a colleague.
02
Give the team a shared starting point.
An agent turns a brief into instructions. Everyone develops their part, and the next steps stay visible.
03
Bring the bigger picture together.
Scattered findings become one summary, linked to the work it came from, so whoever decides can decide.
Shared memory, made visible.
A board holds the work. A card holds the context, sources and next step. People and agents update the same picture, so you can see where things stand. Tre is what your harness reads and writes — the state, the memory and who did what — not the harness itself: planning, orchestration and context management stay with your agent.
ChatGPT saves research sources, Claude develops a finding, and Andrea chooses the next step on the same board.
To explore2
RESEARCH-1
Research question and scope
RESEARCH-2
ChatGPT · added sources
Sources worth following
In progress2
RESEARCH-3
Claude · added a finding
Compare the main findings
RESEARCH-4
Questions still open
Ready to build on1
RESEARCH-5
Andrea · set the next step
Shared summary and next steps
Three levels
Board, list, card. Everything else lives inside the card.
Three surfaces
The web for people, MCP and REST for agents. One contract. In Claude and ChatGPT the same board opens in the chat.
Nothing else
No integrations, no plugins, no feature families. By decision.