Peppermint
Peppermint v0.5.3 adds a Documents feature to the open-source help desk
A side-by-side editorial comparison of ChurnZero and Plain — release velocity, themes, recent moves, and the top alternatives to consider.
ChurnZero is building an agentic layer across CS work — every play, profile, and pipeline now has an AI author.
ChurnZero has spent the past year systematically replacing manual CS work with AI-driven agents. The platform now ships over a dozen named agents covering email drafting, risk detection, presentation analysis, and handoff coordination. Monthly releases have maintained a consistent cadence across Salesforce, HubSpot, Intercom, Notion, and SharePoint integrations, with growing AI credit management and Play step automation. The June 2026 Agentic Essentials tier introduced an MCP server that routes live ChurnZero customer data into Claude and ChatGPT.
Plain built an autonomous support agent, and has now built the controls to trust it.
Plain's changelog is dated entries with no titles, and nearly all of it concerns two AI surfaces: Ari, the customer-facing responder, and Sidekick, the internal agent. Sidekick spent July gaining reach — its own full-page home, reusable workspace skills, and connection to arbitrary MCP servers. The newest release turns to Ari and adds what was missing around it: a way to test it before customers see it, provenance behind each answer, configurable tone, and explicit escalation rules.
ChurnZero has spent the past year systematically replacing manual CS work with AI-driven agents. The platform now ships over a dozen named agents covering email drafting, risk detection, presentation analysis, and handoff coordination. Monthly releases have maintained a consistent cadence across Salesforce, HubSpot, Intercom, Notion, and SharePoint integrations, with growing AI credit management and Play step automation. The June 2026 Agentic Essentials tier introduced an MCP server that routes live ChurnZero customer data into Claude and ChatGPT.
ChurnZero is converging on a model where human CSMs set objectives while the agent layer handles research, writing, and routing. The MCP Connect move signals that the company sees ChurnZero as a data substrate for the broader AI ecosystem — not just a self-contained tool. As the agent library grows, the line between features and agents is dissolving; every new capability arrives as a named agent with a defined role. Triggered automation is deepening: agents that respond to real-time events rather than scheduled runs.
ChurnZero's next move is likely a programmatic multi-agent chain builder — a way to wire agents together (Harbinger detects risk → Pilot drafts email → Baton queues a handoff brief) rather than running each in isolation. The Signals tab and Command Center already hint at this orchestration layer; a workflow builder for agent sequences would be the natural next step.
Plain's changelog is dated entries with no titles, and nearly all of it concerns two AI surfaces: Ari, the customer-facing responder, and Sidekick, the internal agent. Sidekick spent July gaining reach — its own full-page home, reusable workspace skills, and connection to arbitrary MCP servers. The newest release turns to Ari and adds what was missing around it: a way to test it before customers see it, provenance behind each answer, configurable tone, and explicit escalation rules.
The sequence reads as capability first, then governance. Plain rebuilt Ari into an agentic first responder, opened Sidekick to any MCP server, and let teams write skills the whole workspace shares — all of which widen what the agents can do and reach. The current release closes the loop the other way, making that autonomy inspectable and bounded before it is switched on. That is the order support-AI vendors have to complete in: teams will not put an agent in front of customers on capability claims alone.
With testing and provenance in place, the next step is likely measurement — resolution and escalation rates per skill, or per-answer quality review feeding back into the skills teams write. The entries are short summaries linking off-site, so per-release depth is limited.
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 ChurnZero or Plain.
Peppermint v0.5.3 adds a Documents feature to the open-source help desk
UVdesk v1.0.18 adds PHP 8 support and ticket transfer with only one entry visible
DoneDone ships custom fields and workflow automations, closing the gap on mid-market ticketing platforms
Twilio expands Salesforce integration to WhatsApp and SMS while adding transcription failover
Service Fusion publishes field service industry content while its one product move is an AI outbound calls integration
Live Helper Chat opens its permission and routing layer to external AI agents via an MCP endpoint.
See all ChurnZero alternatives → · See all Plain alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
Both compete on the same themes — ai-agents — within Support. Plain is currently shipping more aggressively (velocity 8.8 vs 2.5), 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. Plain is currently shipping more aggressively (velocity 8.8 vs 2.5), 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 ChurnZero alternatives in Support are ranked by recent ship velocity. Browse the "ChurnZero alternatives" section above for the current picks, or visit /alternatives/churnzero for the full list with editorial commentary on each.
Top Plain alternatives in Support are ranked by recent ship velocity. Browse the "Plain alternatives" section above for the current picks, or visit /alternatives/plain for the full list with editorial commentary on each.