The support stack, rebuilt around the agent.
One queue for every channel. Agents that resolve the routine work end-to-end, and stop for a human when your policy says to.
and APIs for the long tail
Support tools weren't built to take action.
Most teams are stuck between legacy ticketing and bolt-on assistants that never close the loop. Subport closes it.
More headcount, same backlog
Hiring doesn't move the queue if the queue grows linearly with headcount. Subport puts automation where it deflects, resolves, and hands off cleanly.
AI that stops at a draft
Copilots suggest text. Customers still wait. Subport takes the action end-to-end, with gates when risk is high.
Weeks to wire channels and playbooks
You shouldn't need a migration project to get value. Connect channels, attach knowledge, and route work in hours—not quarters.
Six surfaces. No new tabs.
Inbox, macros, channels, palette, insights, runs—same view, same shortcuts.
Built for the people running support — and the people building it.
Ship macros and routing without filing an IT ticket. Extend with code when the workflow gets sharp.
Operators ship in an hour.
Connect a channel, attach a knowledge base, define gates for risky actions. The repetitive tier handles itself.
Engineers don't hit a wall.
APIs, webhooks, custom tools, and workflows that match how your org actually resolves work—not a toy canvas.
Seats for people. AI that scales with the plan.
Pick a tier sized to your team and automation volume. No per-message charges to budget around—current numbers on the pricing page.
Four things we hold automation to.
Speed where it's safe. Grounding everywhere. Gates where it isn't safe. Numbers reflect well-instrumented workspaces — yours will vary.
“We needed one queue, grounded answers, and approvals that didn't feel like IT tickets.”
What changes when policy lives in code, not in scripts.
The win wasn't “faster drafts.” It was fewer round-trips: the agent pulls order state, applies the policy we wrote, and only pings us when the amount crosses the threshold. Our queue stopped growing linearly with headcount.
After rollout, teams report fewer tools to switch between, faster medians once tier-1 is automated, more consistent resolutions, and a useful routing + knowledge-base baseline in days rather than quarters.
Talk to us about your rollout →What shipped.
Plans by human seat, with AI work bundled in.
Each plan includes a quota of AI auto-resolves (one per ticket the AI closes without a human). Channels, knowledge bases, and workflows come standard. Enterprise adds SSO, residency, and procurement support.
- Shared inbox + AI agent
- Bundled auto-resolves / month
- Knowledge base
- Unlimited AI agents (fair use)
- Workflow automation + routing
- Priority support options
- SSO / SCIM patterns
- Custom terms + migration help
- Solutions support
Too many “AI help desks” stop at text generation. The hard part is safe action: tools, approvals, audit trails, and a queue model that doesn't fall apart when you add WhatsApp, email, and chat.
That's what we're building—one place for support to run, with automation that earns trust.
If you have a sharp edge case, bring it. We'd rather lose a deal than sell a story we can't ship.
Notes from the build.
Boring on purpose.
Encryption, audit trails, tenant isolation. The questions procurement asks—answered without a sales call.
Before you roll it out.
Yes—start a 14-day trial on Starter or Team from the dashboard, or book a demo if you want a guided walkthrough.