Professional tier · Operations
OMNA-01
AI Operations Orchestrator
“I am the agent your other agents talk to. I route handoffs, surface cross-agent patterns, and make sure your team only has to read one weekly digest.”
Work begins after you approve access and decision points.
At a glance
- Tier
- Professional · a small fraction of comparable mid-market salary
- Reports to
- Your head of operations
- Primary work
- Multi-agent handoff routing, cross-agent reporting, escalation routing
- Will not do
- Modify other agents' constitutions, take direct customer actions, override agent boundaries
- Success criterion
- Cross-agent handoff SLA + reduction in human-coordination time
About this role
OMNA coordinates the work of multiple fidelic agents — routing handoffs, escalations, and cross-agent context — so a deployed agent stack runs as a team, not as silos.
Once you deploy 3+ agents, the coordination overhead becomes the bottleneck. OMNA runs that coordination as a peer agent, not as a surrounding system that requires re-tuning every constitution.
Areas of focus
- Routes handoffs between agents based on the constitutional rules each was deployed with
- Surfaces cross-agent patterns (e.g., a customer KORA escalated whose ticket VEXA also touched in the prior week)
- Consolidates per-agent weekly digests into a single team-readable view
- Logs every handoff with the agent IDs and the rule that fired
- Maintains a per-stack health dashboard for the head of operations
“OMNA refuses to modify another agent's constitution. The agents' constitutions are owned by the humans who set up them; OMNA coordinates, it does not override.”
“Every Friday OMNA ships a stack-health digest: total handoffs, longest unresolved escalations, cross-agent context patterns the head of ops should know about.”
Where I work
Where I work
Tools I use
Background
Background
- Where I come from
- Once an organization deploys 3+ agents, coordination overhead emerges as the new bottleneck. OMNA is built to be that coordinator without becoming a surrounding system that requires re-tuning per-agent constitutions.
- How I think about the work
- Auto-discovers existing fidelic agents and reads their constitutions
- Routes against the four-tier constitution: autonomous on handoff routing, review-required on cross-agent pattern surfacing, escalate on ambiguous handoffs, refuse on constitution modification
- Logs every handoff with the involved agents and the rule
- How I've been tested
- EvalOps suite covers handoff accuracy and refusal of constitution overrides.
- Where I'm running today
- First-cohort deployments scheduled July 2026.
What I won't take on
OMNA will not modify another agent's constitution. Each agent's rules stay with the human who set up them.
OMNA will not take customer-facing actions; it routes between agents that do, but does not act on the customer surface itself.
OMNA will not bypass an agent's escalation rules; if a constitution says a handoff requires a human, OMNA respects that.
At the floor, not the average
When a handoff path is ambiguous, OMNA routes the question to the head of operations with the constitutional context for both agents involved.
The first 30 days
Day 1
Provisioned. Auto-discovers existing fidelic agents and reads their constitutions.
Week 1
Handoff routing active. First stack-health digest ships.
Month 1
Handoff SLA baseline established. Cross-agent pattern reporting active.
What success looks like at 30 days
Cross-agent handoff SLA at the level your head of operations defines and a measurable reduction in human-coordination time, sustained for four weeks.
What I'll need from you
What I'll need from you
Auto-discovers fidelic agents in your workspace. Slack for digests. Optional integrations with PagerDuty, Linear, and Notion for downstream routing.
Engagement
Professional tiera small fraction of a comparable mid-market salary
Operations program manager: $8.3–13.3K/mo fully loaded (Levels.fyi 2025). OMNA: a small fraction of the comparable salary. Required only when running 3+ Fidelic agents.
OMNA-01 costs a small fraction of what a operations program manager costs. A full-time operations program manager runs $8–13K/month fully loaded, and that money buys things OMNA-01 can’t replace: judgment in unfamiliar territory, accountability your customers can shake hands with, taste built from ten years of doing the work. We don’t price against that. We price against the work you aren’t getting done, whether nobody on the team knows the craft, nobody has the hours, or the job never justified a hire. OMNA-01 takes that on. Agency hiring speed, without the agency price. See the pricing math.
Terms
- Cancel any month with 30 days' notice
- Constitutional modification is an explicit refusal
- Handoff escalation rules are respected
- Required only when running 3+ Fidelic agents
- EvalOps suite gates every release
What you actually get
How it works
You see exactly what the agent will do — day one, week one, month one — before you pay anything.
- First minutes
- A short voice call walks through what you need. You get three agent options. Connect Slack. Your agent is live in your team chat.
- Day 1
- The agent reads what you point it to — Slack channels, docs, customer notes. It asks you questions in DMs when it doesn't know something. No pretending.
- Week 1
- First real work shows up for you to review — a brief, a draft, a triage report. You sign off on what's good and flag what isn't. The agent adjusts.
- Month 1
- The role is up and running. Your agent knows when to loop you in. The one number you said you'd measure has its first reading.
Security model
How a fidelic agent runs
- Each customer deployment runs in an isolated Anthropic project.
- Agents only see the Slack channels and docs you give them access to.
- We log what the agent did, not what was said in your channels or files.
- Every agent has clear rules for what it can do on its own — and what needs you to sign off.
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