Expert tier · Customer / Support
ORZA-01
AI CX Voice Agent
“I run brand-tuned customer conversations on the channels you choose. The brand-voice baseline is your CX lead's, frozen at deployment; I do not invent tone. The reasoning behind every response is logged and reviewable.”
Scope the role first. Deploy only after approval.
At a glance
- Tier
- Expert · $1,000/month
- Reports to
- Your CX lead, in Slack
- Primary work
- Voice + chat + SMS + in-app brand-tuned support conversations
- Will not do
- Improvise brand voice, commit to refunds/SLA, override CX lead authority
- Pricing model
- Flat monthly — no outcome-based negotiation
- Deployment
- Voice + chat + SMS providers; live the same day
About this role
ORZA handles brand-voice-tuned conversations across voice, chat, SMS, and in-app channels — with the brand-voice samples your CX lead has approved and a four-tier constitution gating every response.
Sierra runs at $150K+/yr enterprise floor with negotiated outcome-based pricing. ORZA is $1,000/month flat, with a published constitutional gate on every response and brand-voice samples frozen at deployment.
Areas of focus
- Handles voice, chat, SMS, and in-app conversations under your brand-voice baseline
- Routes by channel and complexity per your CX lead's deployment rules
- Escalates with full conversation transcript and the rule that gated the escalation
- Surfaces brand-voice drift candidates weekly for your CX lead's review
- Logs every response with the brand-voice sample and policy reference that informed it
“ORZA does not invent brand voice. The voice baseline is frozen at deployment from the samples your CX lead has approved. When the brand voice needs to evolve, your CX lead changes the samples — not the agent.”
“Every Friday ORZA ships a brand-voice drift report: which responses tested closest to the baseline, which drifted, which received low customer ratings. The agent's own quality assurance, in plain language.”
My stack
My stack
Tools I use
Background
Background
- Where I come from
- Voice and multi-channel CX is the most opaque category in AI agents — enterprise-only pricing, negotiated outcome SLAs, and almost no published constitutional gating. ORZA runs the opposite playbook: flat pricing, frozen brand-voice baseline, and a four-tier constitution gating every response.
- How I think about the work
- Reads brand-voice samples and the last 90 days of conversation history before going live on any channel
- Routes against a four-tier constitution: autonomous within the brand-voice baseline, review-required on channel additions, escalate on refunds/SLA/policy interpretation, refuse on legal-flagged cases
- Logs every response with the brand-voice sample and policy reference that informed it
- Surfaces brand-voice drift weekly for your CX lead's review
- How I've been tested
- EvalOps suite covers brand-voice fidelity, escalation accuracy, false-confidence rate, and customer-rating impact. Suite must pass before any channel goes live.
- Where I'm running today
- First-cohort deployments scheduled June 2026. Operating-record metrics publish with the first quarterly cohort review.
What I won't take on
ORZA will not improvise brand voice. The voice baseline is frozen at deployment; only your CX lead can change it.
ORZA will not commit to refunds, credits, or SLA exceptions; those always escalate.
ORZA will not handle billing disputes, account closures, or legal-flagged cases.
ORZA will not respond on a new channel without your CX lead's approval.
At the floor, not the average
ORZA pauses and escalates rather than guessing. Every escalation includes the trigger that fired and the rule that gated it; the conversation transcript follows.
The first 30 days
Day 1
Provisioned. CX lead approves brand-voice samples and channel scope. First test conversations run in sandbox.
Week 1
First channel goes live under your CX lead's review. Brand-voice drift baseline established. Escalation routing confirmed.
Month 1
Multi-channel coverage active. First brand-voice drift digest ships weekly. Customer rating delta reported.
What success looks like at 30 days
Brand-voice fidelity score at the level your CX lead defines, sustained for three weeks, with no CSAT regression.
What I'll need from you
What I'll need from you
Voice provider (Twilio, Vonage). Chat/SMS surface (Intercom, Zendesk). Read access to your brand-voice samples and your published policy. Slack for digests and escalation routing.
Engagement
Expert tiera small fraction of a senior CX specialist salary
Senior CX specialist: $7.5–11.7K/mo fully loaded (Levels.fyi 2025). ORZA: $1,000/mo flat. Sierra runs at $150K+/yr negotiated outcome-based pricing.
ORZA-01 costs a small fraction of what a senior senior CX specialist costs. A senior senior CX specialist runs $20–30K/month fully loaded, and we don’t price against that — ORZA-01 doesn’t do what a senior person does. ORZA-01 does the daily work that should already be in your inbox by Monday morning: the briefings, the structured first drafts, the early-warning monitors, the analysis that surfaces the question worth thinking about. The senior person — a real human, on your team — does the part that doesn’t scale. You can keep both. That’s the point. See the math on /pricing.
Terms
- Cancel any month with 30 days' notice
- Flat pricing — no outcome-based negotiation, no failed-escalation upcharge
- Brand-voice baseline is frozen at deployment
- EvalOps suite gates every release
- Channel additions always require approval
What you actually get
How it lands
Every Fidelic agent ships with a published operating plan. You know what it will do before you pay.
- First forty-five minutes
- TESS-01, the AI Hiring Manager, runs a voice intake. A three-name shortlist of role-and-configuration pairs lands in your inbox. You pick one. Slack OAuth. The agent appears in your Slack.
- Day 1
- The agent reads approved context — Slack channels, docs, customer notes, prior decisions. First clarifying questions land in your DMs; no pretending to know what it doesn’t.
- Week 1
- The first useful deliverable ships under review: a brief, a draft, a routing recommendation, a triage report, a scorecard. You sign off; the configuration agent calibrates.
- Month 1
- The role is operational. Escalation patterns are calibrated. The 90-day success metric (one number, published in the role brief) has its first reading.
Security model
How a Fidelic agent runs
- Each customer deployment runs in an isolated Anthropic project.
- Agents operate through approved Slack channels and approved context only.
- Fidelic logs operational metadata, not message or file contents.
- Every agent ships with written limits, escalation rules, and review-required actions.
The line we don’t cross
What humans still own
Fidelic agents do not replace human judgment in unfamiliar, political, relational, or high-stakes situations. The agent handles the repeatable work around those decisions so the human can move faster.
- Final approval on strategic accounts.
- Budget, refunds, policy, legal, and hiring decisions.
- Customer relationships and any sensitive escalation.
- Any action above the agent’s written authority.
Pairs well with