Them AI for Customer support

Make the next answer better than the last

Support knowledge often lives with the person who solved the awkward case. Bring reviewed troubleshooting guidance, escalation criteria, and useful explanations into shared rooms, so the next teammate can find the reasoning behind an answer.

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

Support roomShared room
You with your team

What should we check before escalating?

Them AI with company context

Include the observed behavior, reproduction steps, and checks already attempted. The troubleshooting guide routes unexplained issues to the escalation owner with that context, rather than a guessed cause.

↗ Example troubleshooting guide
Review with Support lead
After human approvalEscalation criteria

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

Answer with context

Keep the explanation attached to its source.

02

Escalate clearly

Pass along what was checked and why.

03

Keep useful lessons

Review repeatable guidance after a difficult case.

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.

Customer support room Example 01

Which troubleshooting steps apply here?

Confirm the supported setup, then try the documented reproduction steps. If the behavior persists, record where the result differs from the guide and bring that question to the specialist.

↗ Example setup guide

Reviewed troubleshooting

Ask a question against approved support guidance instead of reconstructing a fix from memory. Check prerequisites and limitations with the cited source before a teammate shares instructions with the customer.

See how the workflow fits
Bring
Support guidance
Review
Support specialist
Keep
Checked steps
Customer support room Example 02

What belongs in the escalation?

Lead with the unresolved question. Follow it with reproduction steps, observed behavior, and checks already attempted. The escalation checklist keeps evidence separate from a possible explanation.

↗ Example escalation checklist

Better escalation

Separate observations from guesses before asking another team for help. Use a reusable escalation skill to organize the question, prior checks, and missing evidence, then review the summary for accuracy.

See how the workflow fits
Bring
Sanitized observations
Review
Escalation owner
Keep
Issue summary
Customer support room Example 03

Can we promise a resolution time?

The incident note confirms the issue but gives no resolution commitment. Share the confirmed impact and current response, then ask the incident owner whether there is an approved timing update.

↗ Example incident note

Incident wording

Give teammates one reviewed explanation of a known issue. Ask what is confirmed, what remains uncertain, and who owns the update before drafting a response that could become a promise.

See how the workflow fits
Bring
Approved incident note
Review
Incident lead
Keep
Response draft
Customer support room Example 04

What can the next teammate reuse?

Keep the diagnostic pattern, the verified fix, and the conditions where it applies. The review checklist also asks what would make the guidance unsuitable for a future case.

↗ Example review checklist

Reusable resolutions

After a case closes, decide which lesson belongs in shared knowledge. Keep the general pattern, supporting evidence, and exceptions, then ask an owner to review it before the team reuses it.

See how the workflow fits
Bring
Sanitized case lesson
Review
Knowledge owner
Keep
Resolution 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 troubleshooting guide

  2. 02

    Make the human call

    Support lead reviews the sources and proposed record.

  3. 03

    Keep the method

    Resolution outline

Make it real

Choose one recurring issue

Bring its approved troubleshooting guide and the teammate who knows its exceptions.

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 send customer replies?
These examples support a human review workflow. Them AI does not promise native helpdesk actions or automatic replies.
Can we add customer tickets?
Human access is organization-wide today. Start with sanitized guidance, not sensitive tickets or customer records.
What is available during the beta?
Mac-only for now. Free during the beta (invite-only). Pilot cited guidance with a support owner before broader use.
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).