The crew that runs this platform after launch.
Agents we build and run for you — not a slogan. Each one has a name, a job, and a rule for when it stops and asks a human. The four below run this platform live today; catalog agents show their own production status on each card.
Dispatch
Lead scoring & routing
- Contact form + chat-handoff submissions
- Lead score changes
- Score a new lead and write it to the CRM instantly
- Enroll a lead in the welcome or quote-followup email sequence
- Send a hot-lead SMS alert to the founder at score ≥ 40
A lead scoring ≥ 40, or any reply, exits automation and waits for a human reply — never auto-closes a deal.
Scribe
Content & lifecycle ops
- Due sequence steps and scheduled broadcasts (15-minute cron)
- Resource-magnet gate submissions
- Every route needing an OG image
- Send the right email sequence step, in the subscriber’s own locale
- Deliver a gated lead magnet the moment a submission comes in
- Generate a fresh, on-brand OG image for any page on demand
A send failure surfaces on the dashboard’s needs-attention queue; the compliance footer (unsubscribe + address) is appended by the engine itself and can’t be edited away, even by a human.
Sentinel
Integration health & uptime
- D1, Resend, Turnstile, Twilio/SMS.ir — live status
- Login rate-limits and session integrity
- The 15-minute cron heartbeat itself
- Run a real, authenticated probe against every integration on demand
- Rate-limit repeated failed logins per IP
- Report exactly which integration is down — never guess "all good" without checking
A failed integration check surfaces in /admin/settings as "not configured" or "failing" — never auto-retried silently, and never auto-fixed. A human decides the next step.
Analyst
Event tracking & KPI computation
- The full 15-event first-party taxonomy (page views, CTA clicks, conversions)
- Email open/click tracking
- Funnel and per-market KPI splits
- Insert every tracked event to the database, fire-and-forget
- Compute traffic, funnel, and campaign stats on request for /admin/analytics
- Split every KPI by market (EN/FA) so neither market’s numbers hide inside the other’s
Read-only by design — Analyst never changes a lead, a send, or a subscriber. It only surfaces numbers a human then acts on.
Browse by tier
A task agent owns a single signal: a cart goes idle, a review lands, a quote goes unanswered. It does one thing on a schedule or a trigger, reports weekly, and hands anything unusual to you.
A department agent owns a function, not a trigger — the shared inbox, accounts receivable, the editorial calendar. Multi-step, multi-system, and stateful: it remembers where things stand and reports against a named KPI every week.
An autonomous operator supervises a roster of task and department agents underneath it, holds the operating plan, and is sold against one named metric — pipeline coverage, DSO, blended CAC. You review the plan monthly; the operator runs the execution.
Fleet migrations off manual/RPA/Zapier stacks, private and on-premise deployment, computer-use automation for legacy software with no API, and industry-specific operators — engagements that don't fit a priced band because the scope is set by your infrastructure, not a template.
Agents you can deploy on your own site.
The crew above runs Orbital itself. These are the same kind of named, escalation-bound agents, sold individually, running on any site — yours included, whether or not Orbital built it.
60 agents
Live feed
Real, sanitized events from this platform’s own event log — no fake data.
- 4m ago
Analyst · Recorded a page view
- 10m ago
Analyst · Recorded a page view
- 5h ago
Analyst · Recorded a page view
- 5h ago
Analyst · Recorded a page view
- 5h ago
Analyst · Recorded a page view
- 6h ago
Analyst · Recorded a page view
- 6h ago
Analyst · Recorded a page view
- 6h ago
Analyst · Recorded a page view
- 6h ago
Analyst · Recorded a page view
- 6h ago
Analyst · Recorded a page view
- 1d ago
Analyst · Recorded a page view
- 1d ago
Analyst · Recorded a page view
- 1d ago
Analyst · Recorded a page view
- 1d ago
Analyst · Recorded a page view
How escalation works
Honesty builds trust: every agent has a threshold where it stops and a human decides, not the other way around.
- Dispatch
A lead scoring ≥ 40, or any reply, exits automation and waits for a human reply — never auto-closes a deal.
A human — founder or team - Scribe
A send failure surfaces on the dashboard’s needs-attention queue; the compliance footer (unsubscribe + address) is appended by the engine itself and can’t be edited away, even by a human.
A human — founder or team - Sentinel
A failed integration check surfaces in /admin/settings as "not configured" or "failing" — never auto-retried silently, and never auto-fixed. A human decides the next step.
A human — founder or team - Analyst
Read-only by design — Analyst never changes a lead, a send, or a subscriber. It only surfaces numbers a human then acts on.
A human — founder or team
Frequently asked
Three bands: task agents run $190–490/mo, department agents $790–1,900/mo, and autonomous operators $2,500–7,500/mo — each with a one-time setup fee. Enterprise and bespoke work is quoted per engagement.
Tier is what the agent owns — a trigger, a function, or an outcome. Category (revenue, support, marketing, operations, finance, data, compliance) is what part of the business it works in. Every agent has both.
Yes — that's the intended path. Every task agent page links to the department agent it feeds into, and no autonomous operator is sold without its supervised agents already proven for 60 days.
No — task and department agent pages are self-serve. For a custom fit, use the agent spec builder to scope a brief, or send us a message if you'd rather talk it through.
Get a crew like this on your platform.
The Ops retainer puts a named agent behind every recurring task on your site, with the same escalation rules shown above.