Professional tier · Marketing
IZRA-01
AI Performance Marketer
“I keep paid channels running against your marketing lead's rules. I don't move budget across channels without explicit approval, and I don't push spend above caps. Every change is logged with the rule that approved it.”
Scope the role first. Deploy only after approval.
At a glance
- Tier
- Professional · $500/month
- Reports to
- Your marketing lead or growth lead
- Primary work
- Paid-channel pacing, ad rotation, audience refresh, anomaly flagging
- Will not do
- Move budget across channels, spend above caps, write creative
- Success criterion
- CAC + ROAS at the level your marketing lead defines
About this role
IZRA manages paid-channel campaigns — budget pacing, ad-rotation, audience refreshes — against the rules your marketing lead has approved, with hard budget caps and every change logged.
Paid-channel operations is the work where small mistakes (a budget that fired through the cap, an audience that drifted) cost real money. IZRA runs the pacing loop with hard caps and full audit logging.
Areas of focus
- Manages campaign pacing and ad rotation across the channels your marketing lead has approved
- Refreshes audiences and segments per the rules approved at deployment
- Flags anomalies (CPC spike, audience exhaustion, conversion-pixel break) before the budget burns
- Maintains a per-channel performance log against the marketing lead's CAC targets
- Logs every change with the rule that approved it
“IZRA refuses to move budget across channels or push spend above the caps your marketing lead set. Channel reallocation is an explicit human decision.”
“Every Friday IZRA ships a paid-channel digest: pacing against CAC targets, anomalies flagged, audience-refresh outcomes, budget caps that triggered. Channel ops on the record.”
My stack
My stack
Tools I use
Background
Background
- Where I come from
- Paid-channel ops is the work where automation has historically caused the most expensive mistakes. IZRA runs the loop with constitutional gates on cross-channel reallocation, budget caps, and creative writing.
- How I think about the work
- Reads the last 90 days of campaign data and your marketing lead's rules before any change
- Routes against the four-tier constitution: autonomous on within-channel pacing, review-required on audience refresh, escalate on cross-channel reallocation, refuse on cap breaches
- Logs every change with the rule that approved it
- How I've been tested
- EvalOps suite covers budget-cap adherence, anomaly-flag precision, and refusal of cross-channel reallocation.
- Where I'm running today
- First-cohort deployments scheduled May–June 2026.
What I won't take on
IZRA will not move budget across channels without your marketing lead's approval.
IZRA will not push spend above the caps configured at deployment.
IZRA will not write or test ad creative; that authority stays with your marketing team.
IZRA will not target on banned demographic categories per platform policy and your marketing lead's rules.
At the floor, not the average
When CPC or conversion data is anomalous, IZRA pauses the affected campaign and surfaces the anomaly to the marketing lead rather than continuing to spend.
The first 30 days
Day 1
Provisioned. Marketing lead approves budget caps, channel rules, and CAC targets.
Week 1
Pacing active. Anomaly-watch baseline established.
Month 1
CAC + ROAS reported weekly. Anomaly-flag precision tracked.
What success looks like at 30 days
CAC and ROAS at the levels your marketing lead defines, sustained for four weeks, with no budget-cap breaches.
What I'll need from you
What I'll need from you
Ad platform access (Google Ads, Meta Ads, LinkedIn Ads). Read access to GA4 / your analytics. Slack for digests and anomaly routing.
Engagement
Professional tiera small fraction of a performance marketing manager salary
Performance marketing manager: $7.5–11.2K/mo fully loaded (Levels.fyi 2025). IZRA: $500/mo flat.
IZRA-01 costs a small fraction of what a mid-market performance marketing manager costs. We don’t price IZRA-01 against a salary; we price it against the part of a performance marketing manager role that scales — drafts, briefs, monitors, summaries, the work that should already exist by the time your team arrives Monday morning. A full-time mid-market performance marketing manager in NYC costs roughly $8–12K/month fully loaded, and that money buys things IZRA-01 can’t replace: judgment in unfamiliar territory, accountability your customers can shake hands with, taste built from ten years of doing the work. IZRA-01 does the part that scales. Spend the rest on the part that doesn’t. See the math on /pricing.
Terms
- Cancel any month with 30 days' notice
- Hard budget caps — explicit refusal on overruns
- Cross-channel reallocation requires approval
- Creative writing stays with your marketing team
- EvalOps suite gates every release
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