Retrospective Tools
ScatterSpoke logo
Retrospectives· USA· Founded 2019

ScatterSpoke

AI copilot for team feedback

Overall score
5.7

Overview

ScatterSpoke was rebuilt from scratch as v3 in August 2026: retro boards, static and agent-run surveys, a Signals engine that detects morale, burnout and psychological-safety patterns in feedback text, and an Ask layer that answers questions with cited evidence. An official OAuth MCP server is included on every tier, including Free.

Best for: Engineering orgs that want AI to synthesise feedback across many teams and surveys — and agent builders who need a survey backend over MCP.

How ScatterSpoke describes itself

Two sites, two products. The marketing homepage still sells "the AI copilot for team feedback" to agile coaches and engineering leaders, badges Jira/Slack/Teams, and leans on DORA and SPACE posts written in 2024. The documentation — rebuilt across July and August 2026 — sells something else, and says so plainly:

"ScatterSpoke v3 is a new platform, not an upgrade to the old one. […] v2.5 collected feedback into boards you read, while v3 collects feedback into evidence you can question."

That framing is accurate. Surveys, agent-run adaptive interviews, detected Signals and a natural-language Ask layer are the product now. The retro board is one input into it rather than the thing being sold.

Our take

The v3 rebuild shipped in August 2026 with the most precise vendor documentation in this category — a per-tier entitlement table, named gates, and candid notes about what each feature costs you. The AI is the real asset. Fifteen built-in signal rules run a detect-then-critique pass before a detection is recorded, automations fire on morale, burnout risk or psychological safety, cross-retro theme trends ship on paid plans, and Ask cites the survey or board every answer came from.

The retro itself got thinner. The manual Group phase is gone, columns are fixed at creation, and action items are no longer part of the retro flow — the Review phase tells you to type outcomes into a card comment thread. Export is one CSV. Integrations are Slack, Teams and email; Jira appears on the marketing site but nowhere in the v3 docs. The DORA angle is 2024 blog content, not a shipped surface.

Best fit: engineering orgs buying AI synthesis across many teams — not teams who need the retro to end in owned, tracked actions.

Score breakdown

Ease of Use8.0
Retro Toolkit6.5
Value3.0
Fun Factor3.0
AI & Insights9.0
Integrations4.0
Open Platform6.0
Enterprise-grade6.0

Pros

  • + Official MCP server on every tier including Free — OAuth, no API keys to mint; reading results is where the paid line sits
  • + Signals engine with fifteen built-in rules and a detect-then-critique pass before anything is recorded
  • + Ask names the survey or retro behind every answer, and cross-retro theme trends ship on paid plans
  • + Unusually precise public docs — a per-tier entitlement table that names exactly what each plan gates
  • + Guest join by verified email or open link, and guests never consume a seat

Cons

  • $814/mo for 3 teams of 8 on Business (5 seats included, then $35/seat); Free is a single seat
  • Action items are no longer part of the v3 retro flow — the Review phase records outcomes as card comments
  • Manual grouping was removed; clustering is AI-only and board columns are fixed at creation
  • The v3 integration entitlement covers only Slack, Teams and email — no Jira, GitHub or Azure DevOps setup is documented
  • One CSV export from a closed retro; audit logs, data retention and org-wide AI are Enterprise-only

Features

Retrospectives

TemplatesCustom templates· Workspace-scoped custom templates on Business and up; retro board columns are fixed by the format and cannot be renamed after creationAnonymous inputRecurring retros· Recurring series applies to Surveys; a closed retro offers 'Run it again' with the same format, not a schedulePrivate/public retros· Three access modes — members only, guests with a verified email, or anyone with the link (forced anonymous)Custom process flow· Two run styles — Guided (Feedback, Vote, Review) or Live with no phases; the phases themselves are fixedSchedule future retros· Cadence scheduling exists for Survey series; retro boards are created on demand

Health checks

Health checks· Recurring Survey Series (weekly pulse, monthly team health check) plus a per-retro 1–5 temperature check; no dedicated multi-dimension health modelMood / sentiment checkPsychological safety· Detected as a built-in signal from feedback text (65% minimum confidence); not a dedicated psych-safety survey instrument1:1 meetings· Automation rules can fire a 'Schedule 1:1' action; no 1:1 meeting surface in the product

Facilitation

Meeting timerAction items· Workspace action-item object with manage/close permissions and an automation action; the v3 retro's Review phase records outcomes as card comments, not action itemsPresentation mode· Review-phase spotlight — the facilitator puts one card on a lit stage for everyone, sorted by dot votes@mentions· @-mentions in Ask threads; not on retro cards or commentsDrag-and-drop grouping· Drag cards between and within columns; the manual Group phase was removed in v3 — clustering is AI-onlyAsync mode

Voting

Independent dot votingCustom vote countVote at any time· Any time on a Live board; Vote-phase only on a guided board

Engagement

Mobile friendlyPolling· Survey builder with nine question types plus an NPS preset; not an in-retro pollCheck-in / check-out· Anonymous 1–5 temperature check runs beside the board; no check-out roundGIFs· Pasted Giphy/Tenor and image URLs render inline; no GIF picker or search

AI

AI grouping / clustering· Paid plans only (RETRO_AI entitlement) — realtime themes, cluster chips and a prompt when the Vote phase opensAI template suggestions· AI drafts Agent Surveys and automation rules from a plain-English goal; no AI suggestion of retro formatsAI action items· An automation rule can create an action item when a signal fires; retro cards do not generate themAI summaryAI sentiment / heatmapsAI retro / health-check insightsAI discussion prompts· 'Probe deeper' on a theme drafts a pre-briefed Agent Survey; Agent Surveys generate adaptive follow-up questionsIn-meeting AI assistant

Reporting

Cross-team reporting· Org-wide signals and a cross-team friction rule (Teams and Groups on Business and up); boards themselves belong to one teamOrg health dashboard· Signal Intelligence rolls up detections org-wide; workspace-wide AI analytics is Enterprise onlyExport formats· CSV, PDF

Enterprise

SSO / SAML· SAML 2.0 (Okta, Entra ID, ADFS) — paid add-on on Business, included on Enterprise; self-serve metadata upload and SSO enforcementSCIM provisioning· Enterprise tier only per the pricing page; the v3 docs cover SAML just-in-time provisioning, not SCIMSOC 2 Type 2· Vendor states SOC 2 Type II from the start with annual penetration testing; no public trust portal or report pageGDPR compliantAudit logs· Enterprise tier only — Free, Pro and Business see a blurred sample behind an upgrade promptFacilitator-only roleGuest / observer rolesMeeting historyEmail domain restrictions· Verified-email guest access mode and SSO domain verification; no workspace-wide email-domain allowlistUptime SLA / dedicated support· Priority support on Business, dedicated CSM on Enterprise; no uptime figure publishedPublic API· Business and Enterprise only; scoped bearer keys, but no public endpoint-level reference published yetMCP server

Integrations

Jira· Marketing still badges Jira; the v3 docs' INTEGRATIONS entitlement names only Slack, Microsoft Teams and email, and no Jira setup is documentedSlackMicrosoft Teams

Compare ScatterSpoke against