Key facts
| API compatibility | OpenAI-compatible /v1/chat/completions (change the base URL) |
| Models | 30+ models from free to frontier tiers behind one API |
| Agent primitives | Function calling, JSON mode and streaming are live |
| Retrieval | Embeddings and RAG over your own corpus |
| Deployment | Plugsky cloud, VPC, on-prem or air-gapped |
| Pricing | Flat monthly self-serve plans with fair-use usage; see the live pricing page |
| Property scoping | Per-property keys and retrieval collections |
| Work-order tools | Function calling into property management systems |
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.
- Pilot tenant Q&A at a single property first.
- Approvals and lease interpretation stay with managers.
How it works, step by step
- Define the job, the permitted data sources and where a human must approve.
- Start with tenant Q&A at one property.
- Create a Plugsky account and generate an API key (free plan, no card required).
- Point your OpenAI SDK at the Plugsky base URL and map your model names.
- Index the approved corpus with embeddings and keep retrieval role-scoped.
- Set approval limits before automating maintenance work orders.
- Measure quality on your own samples, then scale with usage monitoring.
Try it yourself
Where AI agents pay off in property management
Property Management 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.
- Tenant Q&A — answer building, amenity and policy questions from approved content
- Maintenance triage — classify requests, check the responsibility split and open work orders
- Lease questions — retrieve relevant clauses with citations for staff review
- Vendor coordination — draft work orders and follow-ups for manager approval
A reference architecture for property management agents
A tenant agent answers from building content and opens maintenance tickets through tools, while a lease agent retrieves clauses and cites them for the property manager. Repair approvals and legal positions stay with people.
- Property-scoped retrieval collections
- Tools into property management, accounting and vendor systems
- Lease clause source links
- Escalation rules and approval gates
Data governance and human oversight
Tenant data and lease terms are sensitive. Keep per-property scoping, log interactions, and avoid agent statements that could be read as legal or rental determinations without manager review.
- Per-property keys and collections
- Audit logs for tenant interactions
- No autonomous approvals of repairs or lease changes
- Retention aligned with your policy
From pilot to production
Pilot tenant Q&A at one property, then maintenance triage. Add lease Q&A only with manager review and clear escalation rules.
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
| Capability | Plugsky | Typical cloud AI API | Building in-house |
|---|---|---|---|
| API compatibility | Drop-in base URL change | Usually compatible | Full rewrite |
| Model access | 30+ models behind one API | Vendor's own catalogue | You host each model |
| Pricing | Flat monthly self-serve plans; see live pricing | Often per-token | GPU + ops cost |
| Deployment | Cloud, VPC, on-prem or air-gapped | Usually vendor cloud regions | You own the stack |
| Property systems | Agents call your PM software via tools | Varies | You integrate |
| Approvals | Manager-owned spend rules | Varies | You enforce it |
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 approve maintenance work?
They can classify and open requests; approval limits should stay with managers according to your spend rules.
Can it answer legal questions about a lease?
It can retrieve and quote clauses; interpretation should come from the property manager or counsel, not the agent.
Does it work across a portfolio?
Yes — scope each agent to its property or portfolio so content and access stay correct.