Skip to content
Prometa.ai
AI workspace
Governed AI operating workspaceCapability catalog, execution surfaces, and governed evaluation
OverviewAgentsWorkflowsRunTestingAlertsIntegrationsGovernanceInvestment

Registry module

Agent registry

Track agent inventory, versions, connected tools, environments, ownership, and Prometa reference usage from one registry.

Agents04
Prod02
Templates03
VersionedSearchableProduction aware
Primary outcomes
  • Lifecycle visibility
  • Ownership clarity
  • Reuse and clone readiness
Open workflowsRun tests
Workspace model

The same product can run as Prometa’s external capability workspace or as a customer’s internal AI operating system.

Agent registry

Register, version, and operate every enterprise agent from one governed registry.

Prometa AI Operating System tracks ownership, status, environments, connected tools, related capabilities, workflow usage, and Prometa reference templates in one operational layer.

4Total agents
2Production agents
3Prometa-tested agents
3Max clicks to action
workflow_agentproductionproduction

Revenue Orchestrator

Coordinates recommendation, pricing, and campaign tools across retail growth workflows.

Owner usr-004 · latest version v2.3

CRMCDPCampaign API

Last execution 2026-03-16T12:05:00Z · 14.8k orchestrations / month

Production-tested by Prometa

document_agentpilotpilot

Claims Intake Agent

Classifies intake packets, invokes extraction tools, and routes claims into reviewer queues.

Owner usr-003 · latest version v1.6

Document StoreCase APIHuman Review Queue

Last execution 2026-03-16T10:18:00Z · 2.4k packets / month

Pilot-ready

analytics_agentapprovedtest

Demand Planning Analyst

Runs scenario-led forecasting checks and escalates anomalies to planners.

Owner usr-001 · latest version v1.2

ERPForecast APIPlanner Review UI

Last execution 2026-03-16T09:44:00Z · 640 scenario runs / month

monitoring_agentproductionproduction

Control Plane Monitor

Observes integration health, policy breaches, and release readiness across tenant environments.

Owner usr-004 · latest version v3.1

Observability BusAlertingAudit Export

Last execution 2026-03-16T12:11:00Z · 96 control checks / hour

Actively used by Prometa

Runtime engine

Every agent execution exposes observability, governance, and control by design.

input handler

Normalizes input payloads and request context before execution.

payload validation + request shape

tool router

Selects allowed tools and routes calls by policy, env, and confidence state.

tool route + dependency health

memory layer

Injects session, long-term, and vector context according to retention policy.

context source + retrieval latency

response synthesizer

Builds final output, action bundle, and escalation path.

output quality + latency

guardrail checker

Runs pre and post execution safety, data, and policy checks.

policy hits + blocked actions

Configuration graph

Instructions, tools, memory, safety, routing, and fallback logic stay versionable.

agt-001session + vector

signal -> retrieval -> decision -> review -> release

Optimize revenue outcomes while respecting policy and promotion constraints.

Overrides: per request policy override · per environment channel restriction

CRMCDPCampaign APIPolicy Engine
agt-002session + document

intake -> extraction -> routing -> review -> action

Route intake packets into review-safe claims paths with document context.

Overrides: pilot-only reviewer requirement · per request masking policy

Document StoreCase APIHuman Review Queue

Multi-environment runtime

Execution context, secrets, and logs stay isolated by environment.

deveu-central-1

Free execution environment

Promotion path dev → test → pilot → prod · 0 execution contexts

testeu-central-1

Protected environment

Promotion path dev → test → pilot → prod · 1 execution contexts

piloteu-west-1

Protected environment

Promotion path dev → test → pilot → prod · 1 execution contexts

prodeu-west-1

Protected environment

Promotion path dev → test → pilot → prod · 1 execution contexts

Version operations

Compare prompts, tools, thresholds, and routing snapshots before publish or rollback.

agt-001v2.3

Added campaign throttling threshold and reviewer checkpoint for margin-sensitive segments.

prompts, routing logic, policy gates, fallback tool order

Created by Prometa Admin on 2026-03-15

agt-002v1.6

Expanded extraction policy and confidence escalation path for missing document bundles.

tool permissions, confidence thresholds, human review routing

Created by Aylin Demir on 2026-03-12

agt-003v1.2

Enabled regression suite against golden demand scenarios before planner release.

forecast inputs, benchmark set, reviewer scoring

Created by Elif Kara on 2026-03-10

Execution trace

Live trace viewer for agent runtime and routing behavior.

Trace `/trace-001` exposes orchestration steps, tool calls, decision points, latency, token cost, and suggested remediation without opening backend internals.

Scenario ingestsuccess

Scenario pack normalized

Tool calls

Forecast API

Decisions

Peak cluster anomaly detected

Token / cost

1240 in · 318 out · $2.10

Latency breakdown

model 420 ms · tool 980 ms · orchestration 210 ms

Planner review routingwaiting_review

Escalated to planner queue

Tool calls

Planner Review UI

Decisions

Confidence below threshold

Token / cost

220 in · 91 out · $0.60

Latency breakdown

model 180 ms · tool 220 ms · orchestration 140 ms

Explain this execution

Decision path stayed inside registered tools, applied runtime guardrails, and routed to review whenever confidence or policy state required intervention.

Fix suggestion engine

Planner scenario payload missing one required pricing field. Suggested fix: Add schema validation in input handler and inject default pricing floor before review.