Agent Runtime

Brightwire Agent Runtime

Department-scoped execution: standing role agents, skills, connectors, and a durable surface — always under Agent Governance.

OptionalUnder Governance

Brightwire Agent Runtime is a department-scoped execution environment: a standing team of role agents (lead + specialists) with shared skills and tools, verification so work finishes or escalates, and connectors on your real operations systems — always under Brightwire Agent Governance.

It is not another chatbot seat, not a generic services “AI shop,” and not unsupervised trading or plant control by default.

How we name an instance: {Department} Agent Runtime — e.g. Market Ops Agent Runtime · Energy Management Agent Runtime.

Why this exists

SymptomWhat breaks
Laptop / personal stackWorkflow dies when the champion is offline; no shared ownership
Seat sprawlMany tools; little inventory of who runs what, on which data, at what cost
No department groundingGeneric desktop tools don’t live on ETRM, PI/historian, settlements, ISO feeds, or CMMS as first-class systems
No durable multi-agent collaborationOne chat window is not lead + specialists with handoffs, review, and escalation
Weak production surfaceNo department web application for the dashboards the desk actually runs on
Governance afterthoughtAccess, cost, audit, and human gates bolted on late — or never

Runtime addresses the department side. Governance addresses company control. You can adopt Governance while staying on existing seats. Runtime is optional; when you add it, it always carries Governance posture.

Design principles

  1. Department boundary — one Runtime per named department or workstream; scale by adding Runtimes under one Governance posture.
  2. Standing role agents — lead + specialists with clear jobs, tools, memory scope, handoffs, and escalation.
  3. Blueprint, then tailor — start from a proven pack; fit the department’s systems and workflows.
  4. Governance travels with Runtime — access, cost, audit, and policy are included.
  5. Dedicated department web application — dashboards and review for that desk, not chat-only.
  6. Your cloud — production Runtime is an isolated environment in your cloud tenant; Brightwire operates the stack inside it.
  7. Progressive autonomy — Ask → See → Advise → Act. Trading and plant control stay human-led unless separately scoped.
  8. Managed operate — Brightwire designs and operates the Runtime with your team.

How Runtime relates to Governance

Existing seatsAgent GovernanceDept Runtime + web appMore dept Runtimes
LayerProductJob
ControlAgent GovernanceAccess, cost, audit, policy on supported paths
ExecutionAgent RuntimeDepartment role agents + skills/tools + connectors + verification
SurfaceDepartment web app (per Runtime)Dashboards, analytics, and review for that desk
Offer shapeWhat you getWhen it fits
Governance aloneAgent GovernanceSprawl, spend, audit pain; custom multi-agent can wait
Governance + RuntimeGovernance + one or more department RuntimesA department needs multi-agent work on market, plant, or ops systems
ExpandMore Runtimes or deeper actionsTrust and proof are in place

What lives in a Runtime environment

ComponentPurpose
Role agentsStanding personas with scoped instructions, tools, and memory
Multi-agent collaborationHandoffs, review, escalation — work finishes or surfaces to a human
Skills and toolsReusable capabilities under policy
ConnectorsIntegration to department systems of record (scoped)
Department web applicationDurable UI for dashboards, analytics, and review
Team messagingHuman + agent collaboration, including Teams where scoped
Knowledge retrievalAnswers grounded in approved documents and sources
Identity (SSO)Enterprise SSO and role-based access
Secrets & configurationWorkspace-scoped credentials; values not shown in the UI
ObservabilityHealth, events, and usage for operate and cost control

Trust ladder inside Runtime

AskSeeAdviseAct

Default starting point is not Act. Runtime can host work at any rung; Act only inside pre-approved workflows.

Runtime vs desktop agent tools

DimensionDesktop / personal toolsBrightwire Agent Runtime
Unit of designOne user + one sessionDepartment team of standing role agents
CollaborationManual tab and chat jugglingDesigned handoffs, review, escalation
Systems groundingPaste context / ad-hoc toolsConnectors and skills on ops systems (scoped)
Production homeLaptop sessionYour cloud tenant + durable app surface
GovernancePersonal or vendor-seat settingsAgent Governance posture
Best whenIndividual productivityDepartment production workflows with company control

We do not ask power users to abandon Claude or Copilot. Governance is additive. Runtime is what you add when seats cannot carry department multi-agent work on real systems with production continuity and audit.

Out of scope unless written separately
  • Unsupervised plant or OT control
  • Unsupervised trading execution
  • One Runtime for the entire enterprise
  • Replacing your Microsoft 365 admin or vendor governance stack

Related: Why Governance · How a project runs · Next steps