Keep promises clear
Separate a customer request, a product intention, and an approved commitment.
Them AI for B2B SaaS
Keep the product story consistent across the team.
Product, engineering, and customer teams need more than the latest document. Them AI brings recurring questions into shared rooms, with reviewed knowledge that preserves what was decided, why it matters, and who can clarify it.
Mac-only for now. Free during the beta (invite-only).
Release readinessShared room
You with your team
Why are we introducing this feature in stages?
Them AI with company contextThe staged rollout depended on completing rollback tests before wider access. Confirm the current test results, dependency readiness, and engineering owner's sign-off before carrying that plan into the next release.
↗ Illustrative release reviewReview with Engineering lead
After human approvalRelease decision and its conditions
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.
Carry the rationale
Give the next teammate the constraint behind an architectural or product choice.
Reuse support judgment
Turn reviewed explanations into methods without promoting every workaround to policy.
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.
B2B SaaS room Example 01
Does the earlier rollout plan still apply?
Only if the same dependencies and rollback conditions hold. Compare the latest test evidence with the release decision, then ask the engineering owner to confirm what changed.
↗ Illustrative rollout decisionExplain a release decision
Bring the release note and decision owner into one discussion. Ask what changed, which assumptions still hold, and what evidence a teammate needs before repeating the recommendation.
See how the workflow fits
- Bring
- Authorized release notes and decisions
- Review
- Engineering owner checks current constraints
- Keep
- Approved release rationale
B2B SaaS room Example 02
Did we promise this capability?
The agreement covers standard reporting; custom exports appear in discovery notes. Ask the account owner to check for a later amendment before communicating a delivery date.
↗ Illustrative account handoffClarify a customer commitment
Review a handoff with the account and product owners. Keep confirmed commitments distinct from requests, estimates, and ideas that never became a promise to the customer.
See how the workflow fits
- Bring
- Authorized agreement and handoff notes
- Review
- Account owner resolves conflicting statements
- Keep
- Reviewed commitment brief
B2B SaaS room Example 03
When should this workaround not be used?
Stop when the customer's configuration falls outside the supported setup. Record the configuration and error details for the support lead instead of repeating a workaround with unmet prerequisites.
↗ Illustrative support reviewKeep a support lesson
Use a resolved, appropriately redacted support example to explain a recurring issue. Record the conditions behind the answer and where a specialist must take over.
See how the workflow fits
- Bring
- Reviewed support explanation
- Review
- Support lead checks exceptions
- Keep
- Diagnostic skill with stop conditions
B2B SaaS room Example 04
Why did we reject the simpler approach?
We separated background jobs to keep long-running work out of customer requests. Revisit that choice if the workload changes; the decision depends on those response-time constraints.
↗ Illustrative product decisionExplain how the product evolved
Give a new teammate a small set of reviewed product decisions. Use their questions to find missing context, then ask an owner to approve useful clarifications.
See how the workflow fits
- Bring
- Current product decisions
- Review
- Product owner checks interpretation
- Keep
- Sourced onboarding answers
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- 01
Bring the context
Illustrative release review
- 02
Make the human call
Engineering lead reviews the sources and proposed record.
- 03
Keep the method
Release readiness review
Make it real
Start with one release handoff
Choose an authorized decision set and one reviewer. Compare the resulting brief with your usual handoff, including correction effort. Mac-only for now. Free during the beta (invite-only).
Discuss a design partnership
Before you begin
A few things
worth knowing.
Does Them AI replace our product tools?
No. Use it for reviewed context and discussion. Connected agents execute in their own tools, under your existing review process.
Can a room restrict customer information?
Human access is organization-wide. Client-scoped MCP feeds serve that client's approved knowledge plus approved firm-wide material, not a private human room.
What should we measure first?
Whether another teammate can explain a decision, verify its sources, and recognize when its assumptions no longer apply.
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).