Them AI for Productivity

Stop rebuilding context before the work begins

The work slows when every question needs a new explanation. Bring decisions, recurring questions, and reviewed ways of working into shared rooms, so teammates and their agents can begin with context the company already understands.

Mac-only for now. Free during the beta (invite-only).

Project roomShared room
You with your team

Why did we narrow the scope?

Them AI with company context

The team kept the core requirement and deferred optional work because of a delivery constraint. Before adding scope back, check whether that constraint has changed with the decision owner.

↗ Example scope decision
Review with Project lead
After human approvalProject scope rationale

A useful record for the next person.

Illustrative workflow. Not a live conversation.

The work gets better when the context stays.

Good judgment belongs
with the whole team.

01

Keep the reason

Preserve decisions beyond the meeting that made them.

02

Ask with context

Give repeated questions a checkable starting point.

03

Share useful methods

Reuse reviewed practice across people and agents.

In the day-to-day

Work your team can bring to Them AI.

Start with the question. Keep the source. Make a person responsible for what comes next.

Productivity room Example 01

Where does this working rule come from?

The working guide connects this rule to the handoff problem it was meant to solve. Keep that purpose in view, and bring changed circumstances or exceptions to the process owner.

↗ Example working guide

Repeated questions

Choose the questions that keep interrupting the same teammate. Bring approved guidance into shared memory, name an owner, and let the team inspect the source instead of relying on secondhand explanations.

See how the workflow fits
Bring
Working guidance
Review
Process owner
Keep
Shared answer
Productivity room Example 02

What did we agree, and why?

The decision note confirms the core scope and leaves the optional work unresolved. The team chose that boundary because of a delivery constraint; the owner can clarify when to revisit it.

↗ Example decision note

Decision context

Keep the outcome of a discussion with the reason behind it. Add an organization-safe summary for review, then preserve the decision context that a teammate arriving later will need to understand.

See how the workflow fits
Bring
Reviewed decision notes
Review
Decision owner
Keep
Decision record
Productivity room Example 03

What should someone know before taking over?

Start with the goal, confirmed decisions, and unresolved dependencies. The handoff checklist keeps suggestions separate from commitments, so the receiving teammate knows what is settled and what still needs discussion.

↗ Example handoff checklist

Project handoffs

Help the next teammate understand what matters before picking up the work. Review the goal, constraints, and unresolved questions together, then keep the shared context useful without turning assumptions into commitments.

See how the workflow fits
Bring
Handoff guidance
Review
Receiving teammate
Keep
Context outline
Productivity room Example 04

How should we frame this new piece of work?

Begin with the intended outcome, known constraints, and unresolved assumptions. The planning skill then asks who needs to review each assumption before the team agrees the scope of the work.

↗ Example planning approach

Reusable planning

Turn a useful planning approach into guidance the team can repeat. Review the questions and checks as a skill, then let people or external agents retrieve it for their own work.

See how the workflow fits
Bring
Planning approach
Review
Practice owner
Keep
Planning skill

These are example workflows to evaluate, not customer results. Connected agents use their own tools; Them AI is the shared context and review workspace.

From useful work to reusable knowledge

The conversation is
only the beginning.

Memory keeps the facts and decisions. Skills keep a way of working. People decide what deserves to become a shared reference.

Meet Rooms and the Collective
  1. 01

    Bring the context

    Example scope decision

  2. 02

    Make the human call

    Project lead reviews the sources and proposed record.

  3. 03

    Keep the method

    Planning review

Make it real

Start where context keeps going missing

Bring one shared process, its best explanation, and the teammate people usually ask.

Discuss a design partnership
Them AI product demonstration of people and agents working in a room
Product demonstration with illustrative people and data.

Before you begin

A few things
worth knowing.

Does Them AI do the work automatically?
These examples provide shared context. External agents own execution; people review decisions and the knowledge they plan to reuse.
Can a project room be private?
Not currently. Human room and memory access is organization-wide. Share only material appropriate for everyone in your workspace.
How can a team begin?
Mac-only for now. Free during the beta (invite-only). Start with one recurring question and its responsible owner.
What does the current beta include?
Shared rooms, memory with sources and review status, reusable skills, and MCP access for connected agents. Mac-only for now. Free during the beta (invite-only). Human room and memory access is organization-wide. Client-scoped MCP feeds restrict agent retrieval to that client's approved records plus approved firm-wide material. Do not treat a room as a private boundary for individual members. Read the access boundaries.

Bring one real workflow

Make the next project
better informed than the last.

Start with a question your team keeps answering. Bring the sources, the people who know, and the decisions worth keeping.

Mac-only for now. Free during the beta (invite-only).