Industry Solutions

How are AI agents used in utilities?

Utilities use AI agents for outage communications, field-crew knowledge lookup, asset maintenance history and regulatory research. The architecture pairs an OpenAI-compatible agents API with retrieval over procedures and asset records, tool calls into work-management and asset systems, and human authority over grid or customer-impacting actions. Plugsky supports 30+ models with on-prem and air-gapped deployment for critical infrastructure.

Key facts

API compatibilityOpenAI-compatible /v1/chat/completions (change the base URL)
Models30+ models from free to frontier tiers behind one API
Agent primitivesFunction calling, JSON mode and streaming are live
RetrievalEmbeddings and RAG over your own corpus
DeploymentPlugsky cloud, VPC, on-prem or air-gapped
PricingFlat monthly self-serve plans with fair-use usage; see the live pricing page
Critical infrastructureOn-prem and air-gapped deployment with no control-path access
Operations controlSwitching and dispatch authority stays with operators

TL;DR

  • Keep your OpenAI SDK — change the base URL and model name.
  • 30+ models behind one API, from free chat models to frontier reasoning.
  • Deployment options from hosted cloud to VPC, on-prem and air-gapped.
  • Keep agents out of control paths entirely.
  • Version safety procedures before any field use.

How it works, step by step

  1. Define the job, the permitted data sources and where a human must approve.
  2. Pilot field-procedure lookup and outage drafting.
  3. Create a Plugsky account and generate an API key (free plan, no card required).
  4. Point your OpenAI SDK at the Plugsky base URL and map your model names.
  5. Index the approved corpus with embeddings and keep retrieval role-scoped.
  6. Version controlled procedures before field use.
  7. Measure quality on your own samples, then scale with usage monitoring.
1Define the job, thepermitted datasources and where a2Pilotfield-procedurelookup and outage3Create a Plugskyaccount andgenerate an API key4Point your OpenAISDK at the Plugskybase URL and map5Index the approvedcorpus withembeddings and keep6Version controlledprocedures beforefield use.

Try it yourself

Open the sovereign AI readiness score →

Where AI agents pay off in utilities

Utilities teams do not lack ideas for agents; they lack a safe path from demo to production. The pattern below targets repetitive, document-heavy work where a human can check the output, which is where agents earn their place first. Treat the agent as a new team member with a narrow brief, explicit permissions and a probation period, and rollout becomes an operations exercise rather than a leap of faith.

  • Outage communications — draft accurate updates from incident information you supply
  • Field knowledge — retrieve procedures and safety guidance for crews
  • Asset history — answer maintenance and failure questions for a given asset
  • Regulatory research — summarise filings and internal policy with citations

A reference architecture for utilities agents

A communications agent drafts outage updates from approved inputs, while a field agent retrieves the right procedure and asset history through tools. Grid control and switching decisions remain fully with operations.

  1. Site and role scoped collections
  2. Read-first tools into work management and asset systems
  3. Approval gates for customer communications
  4. Offline-capable deployment where required

Data governance and human oversight

Critical-infrastructure answers must be dependable and traceable. Version the procedures that feed retrieval, keep operational data in the boundary, and never let an agent sit in a control path.

  • Controlled-document versioning
  • Role-scoped access
  • Audit logs for queries and drafts
  • Operations retain switching and dispatch authority

From pilot to production

Pilot field-procedure lookup and outage drafting, then asset history. Keep control-room and switching workflows out of scope.

Keep the rollout reversible: run the agent in shadow mode alongside the current process, compare outputs on your own samples, and move it into the workflow only when the evidence holds. Document what you measured so expanding to the next team is a decision, not a hope.

Honest comparison

CapabilityPlugskyTypical cloud AI APIBuilding in-house
API compatibilityDrop-in base URL changeUsually compatibleFull rewrite
Model access30+ models behind one APIVendor's own catalogueYou host each model
PricingFlat monthly self-serve plans; see live pricingOften per-tokenGPU + ops cost
DeploymentCloud, VPC, on-prem or air-gappedUsually vendor cloud regionsYou own the stack
Operational controlExcluded; operators retain authorityVariesYou enforce it
Offline operationOn-prem and air-gapped optionsOften cloud-onlyYou own the stack

Frequently asked questions

Do we have to rewrite our application?

No. The chat completions API is OpenAI-compatible, so you change the base URL and model name and keep your existing SDK.

Is there a free plan?

Yes — the free plan includes two free AI models, plugsky-micro and plugsky-lite, with no credit card required.

How is pricing structured?

Self-serve plans are flat monthly with fair-use usage and no per-token charges; see the live pricing page for current plans.

Which endpoints are live today?

Chat, streaming, JSON mode, function calling, embeddings, RAG and agents are live. Audio, images, moderation, files, batch, fine-tuning, assistants and responses endpoints are coming soon — check the docs before planning around them.

Can agents control grid equipment?

No. They retrieve, summarise and draft; operational control stays with your systems and qualified operators.

Can it run without internet access?

Yes — on-prem and air-gapped deployment supports sites that cannot depend on a public endpoint.

How do we keep safety procedures current?

Treat retrieval as a controlled-document pipeline: publish revisions on your change schedule and retire superseded versions.