Plain
Plain built an autonomous support agent, and has now built the controls to trust it.
A side-by-side editorial comparison of Formbricks and Xurrent — release velocity, themes, recent moves, and the top alternatives to consider.
The 5.3 line reached stable and immediately dropped into single-fix patch-RC mode.
Formbricks runs three release branches at once — 5.1, 5.2 and 5.3 — publishing release candidates almost daily, most carrying a single backported fix. The 5.3 line has moved past its feature RCs: 5.3.0-rc.1 through rc.3 delivered MCP scope corrections, Helm volume extension points and an accessibility pass, and the branch is now on 5.3.4-rc.1, a one-line fix stopping no-overlay surveys from blocking the host page they sit on. Workspace and organization scoping remains the recurring thread, with the contact detail page the latest surface re-tied to its authorizing workspace.
Sera AI crosses from assistant to autonomous agent while the ITSM core keeps its monthly grind.
Xurrent ships on a disciplined monthly cadence, and the last quarter splits cleanly in two. One half is steady ITSM plumbing — shared tags across Requests, Problems, Workflows and Projects, CMDB reconciliation that a human can actually read, iPaaS connectors, self-service reservations. The other half is Sera AI, which moved from a chat widget to a configurable studio and then, on 10 July, to two agents that act without a person in the loop.
Formbricks runs three release branches at once — 5.1, 5.2 and 5.3 — publishing release candidates almost daily, most carrying a single backported fix. The 5.3 line has moved past its feature RCs: 5.3.0-rc.1 through rc.3 delivered MCP scope corrections, Helm volume extension points and an accessibility pass, and the branch is now on 5.3.4-rc.1, a one-line fix stopping no-overlay surveys from blocking the host page they sit on. Workspace and organization scoping remains the recurring thread, with the contact detail page the latest surface re-tied to its authorizing workspace.
The multi-tenancy audit is still running and still backported everywhere rather than only forward — API keys, surveys, quotas, integrations, response imports and now the contact detail page have each been re-scoped in turn. Alongside it, the agent-facing surface built out in 5.2.0 is being refined rather than extended: the 5.3 MCP work is scope correction, not new capability. With 5.3 now issuing patch RCs a day or two apart, that branch has crossed from feature development into maintenance.
Expect 5.3 to keep issuing single-fix patch release candidates while the next feature drop opens a 5.4 line, and 5.1 and 5.2 to continue receiving only security and billing backports.
Xurrent ships on a disciplined monthly cadence, and the last quarter splits cleanly in two. One half is steady ITSM plumbing — shared tags across Requests, Problems, Workflows and Projects, CMDB reconciliation that a human can actually read, iPaaS connectors, self-service reservations. The other half is Sera AI, which moved from a chat widget to a configurable studio and then, on 10 July, to two agents that act without a person in the loop.
The two tracks are converging rather than running in parallel. Knowledge article readiness, CI location hints and reconciliation legibility are not standalone features — they are the data-quality preconditions an agent needs before it can be trusted to close a request. Xurrent is building the substrate first and letting Sera consume it, which is why the agent work has landed without the usual rollback noise. Agent Designer success metrics suggest the next constraint is proving the agents work, not shipping more of them.
Expect the agent count to grow slowly and the governance surface around it to grow faster — more Golden Set tooling, more per-agent success reporting, and tighter scoping of which request types an agent may close unaided.
Other Support products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either Formbricks or Xurrent.
Plain built an autonomous support agent, and has now built the controls to trust it.
Sleekplan rebuilt itself around AI triage, then put the feedback board inside ChatGPT.
Comm100 publishes steadily about AI support — none of it is Comm100 shipping anything.
respond.io is layering an agent-authoring copilot and consumption billing on top of its omnichannel inbox.
Hatz sells through MSPs, and its roadmap has started to serve the partner more than the end user
A teaser-only content feed making one argument: AI in the contact center fails on knowledge, not models.
See all Formbricks alternatives → · See all Xurrent alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
Both compete on the same themes — mcp — within Support. Xurrent is currently shipping more aggressively (velocity 6.3 vs 5.0), with 0 editorial sparks in the last 30 days against 0. See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. Xurrent is currently shipping more aggressively (velocity 6.3 vs 5.0), with 0 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other Support products to evaluate alongside.
Top Formbricks alternatives in Support are ranked by recent ship velocity. Browse the "Formbricks alternatives" section above for the current picks, or visit /alternatives/formbricks for the full list with editorial commentary on each.
Top Xurrent alternatives in Support are ranked by recent ship velocity. Browse the "Xurrent alternatives" section above for the current picks, or visit /alternatives/xurrent for the full list with editorial commentary on each.