Industry Solutions

How are AI agents used in research teams?

Research teams use AI agents to retrieve literature, synthesise findings with citations, assist analysis code and keep project knowledge searchable. The architecture pairs an OpenAI-compatible agents API with retrieval over curated corpora, tool calls into reference managers and data stores, and researcher review of every claim. Plugsky supports 30+ models and long-context options with on-prem or air-gapped deployment.

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
Long contextLong-context models available for large excerpts
Sensitive dataOn-prem and air-gapped deployment options

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.
  • Ground synthesis in retrieval and verify every citation.
  • Match the deployment tier to data sensitivity per project.

How it works, step by step

  1. Define the job, the permitted data sources and where a human must approve.
  2. Curate a clean corpus and pilot a literature review.
  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. Verify citation accuracy before trusting synthesis.
  7. Measure quality on your own samples, then scale with usage monitoring.
1Define the job, thepermitted datasources and where a2Curate a cleancorpus and pilot aliterature review.3Create a Plugskyaccount andgenerate an API key4Point your OpenAISDK at the Plugskybase URL and map5Index the approvedcorpus withembeddings and keep6Verify citationaccuracy beforetrusting synthesis.

Try it yourself

Open the RAG sandbox →

Where AI agents pay off in research teams

Research 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.

  • Literature retrieval — find and summarise relevant work with citations
  • Synthesis — draft structured reviews that link to source passages
  • Analysis support — generate and explain code for data preparation
  • Project memory — answer questions across notes, protocols and prior results

A reference architecture for research teams agents

A retrieval agent returns sourced passages, a synthesis agent organises them into an outline with references, and a coding agent drafts analysis scripts for a researcher to test. Publication and data interpretation remain with the research team.

  1. Corpus-scoped collections with citation metadata
  2. Tools into reference managers and storage
  3. Long-context models for whole-paper reading
  4. Versioned prompts and reproducible runs

Data governance and human oversight

Research data ranges from public to highly sensitive. Choose the deployment tier per project, keep unpublished results inside the boundary, and record provenance so findings can be reproduced.

  • Project-scoped keys and collections
  • On-prem or air-gapped options for sensitive data
  • Audit logs and reproducible prompt versions
  • Researcher review of every cited claim

From pilot to production

Pilot on a literature review with a well-defined corpus. Check citation accuracy before trusting synthesis, then extend to project memory.

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
CitationsRetrieval-grounded with source linksVariesYou build it
Sensitive dataOn-prem/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 fabricate references?

Any generative model can produce incorrect citations; that is why retrieval-grounded answers with source links and human checking are the working pattern. Verify every reference.

Can I use it with sensitive datasets?

Yes — pick a deployment tier that keeps data inside your approved boundary, including on-prem or air-gapped options.

Does it support long papers?

Long-context models can process large excerpts; for large corpora, retrieval plus chunking is usually more reliable.