Use cases
Patterns we have shipped
15 production-tested patterns spanning agents, RAG, governance, and embedded chat on Console. Each one shows the architecture, the package mix, and a starting point you can copy.
- Patterns 15
- Shape Architecture, then code
- Language TypeScript
Every page opens with the architecture — which package owns which responsibility — and then walks the implementation step by step. The code is the real shape you would ship, not pseudocode.
Quota-Aware LLM Gateway
Run application traffic through Console with project-scoped quotas, model routing, and request-level visibility for cost control.
Vector RAG Operations Control Plane
Operate RAG pipelines through Console by combining file ingestion, vector index management, embeddings, and chat retrieval in one control surface.
PromptOps And MCP Tool Gateway
Use Console as the control plane for prompt versioning, secure config storage, and converting OpenAPI specs into MCP and tool endpoints.
SRE Incident Response Agent
Build an SRE agent that reads Confluence runbooks, ingests them into Console RAG, searches vector knowledge during incidents, and posts Jira updates through tools.
Agent Development With Tracing
Develop custom agents with Agent SDK and feed execution traces into Console so teams can compare runs, inspect tool behavior, and debug workflows faster.
Autonomous AI Agents
Build agents that plan, execute tools, and deliver structured outputs with full deterministic control and observability.
RAG & Semantic Search
Ingest documents, generate embeddings, and query vector stores through a unified gateway for retrieval-augmented generation.
Customer Support Bot
Deploy conversational AI with streaming responses, human-in-the-loop escalation, guardrails, and tool transparency.
AI-Powered Applications
Integrate AI capabilities into existing applications with OpenAI-compatible APIs, provider routing, and type-safe SDKs.
Multi-Agent Orchestration
Compose multiple specialised agents that hand off tasks, share context, and collaborate on complex workflows.
Enterprise AI Governance
Enforce guardrails, track usage, manage projects, and observe all AI operations from a single control plane.
Dynamic LLM Routing By Request And Caller
Give applications one stable model key and let Console pick the concrete model per request, by prompt content, size, channel, or who is asking.
Let Users Choose The Agent's Model
Offer a main model plus additional models on one agent and let the caller, or a chat UI model picker, choose which one answers.
Embedded Portal With Page Tools
Embed a Console portal as a chat bubble in your product, sign visitors in with your own identity token, and let the agent act on the page.
Agent Approvals Through Webhooks
Pause an agent before it runs a risky tool, get a signed webhook, and approve or deny from your own backend with the client API.
Browse by theme
The same 15 patterns, grouped by the problem they solve.
Agents and orchestration
- SRE Incident Response Agent — Build an SRE agent that reads Confluence runbooks, ingests them into Console RAG, searches vector knowledge during incidents, and posts Jira updates through tools.
- Agent Development With Tracing — Develop custom agents with Agent SDK and feed execution traces into Console so teams can compare runs, inspect tool behavior, and debug workflows faster.
- Autonomous AI Agents — Build agents that plan, execute tools, and deliver structured outputs with full deterministic control and observability.
- Multi-Agent Orchestration — Compose multiple specialised agents that hand off tasks, share context, and collaborate on complex workflows.
- Let Users Choose The Agent's Model — Offer a main model plus additional models on one agent and let the caller, or a chat UI model picker, choose which one answers.
- Agent Approvals Through Webhooks — Pause an agent before it runs a risky tool, get a signed webhook, and approve or deny from your own backend with the client API.
RAG and retrieval
- Vector RAG Operations Control Plane — Operate RAG pipelines through Console by combining file ingestion, vector index management, embeddings, and chat retrieval in one control surface.
- RAG & Semantic Search — Ingest documents, generate embeddings, and query vector stores through a unified gateway for retrieval-augmented generation.
Chat and embedded widgets
- Customer Support Bot — Deploy conversational AI with streaming responses, human-in-the-loop escalation, guardrails, and tool transparency.
- Embedded Portal With Page Tools — Embed a Console portal as a chat bubble in your product, sign visitors in with your own identity token, and let the agent act on the page.
Platform and governance
- Quota-Aware LLM Gateway — Run application traffic through Console with project-scoped quotas, model routing, and request-level visibility for cost control.
- Vector RAG Operations Control Plane — Operate RAG pipelines through Console by combining file ingestion, vector index management, embeddings, and chat retrieval in one control surface.
- PromptOps And MCP Tool Gateway — Use Console as the control plane for prompt versioning, secure config storage, and converting OpenAPI specs into MCP and tool endpoints.
- Agent Development With Tracing — Develop custom agents with Agent SDK and feed execution traces into Console so teams can compare runs, inspect tool behavior, and debug workflows faster.
- AI-Powered Applications — Integrate AI capabilities into existing applications with OpenAI-compatible APIs, provider routing, and type-safe SDKs.
- Enterprise AI Governance — Enforce guardrails, track usage, manage projects, and observe all AI operations from a single control plane.
- Dynamic LLM Routing By Request And Caller — Give applications one stable model key and let Console pick the concrete model per request, by prompt content, size, channel, or who is asking.
Products behind these patterns
Agent SDK
Deterministic TypeScript agent runtime — planning, tools, guardrails, sub-agents, and human-in-the-loop.
Agent Server
Serve agents as versioned REST APIs with streaming, auth, storage, and OpenAPI docs.
Console
Self-hosted AI control plane — routing, embeddings, vectors, files, guardrails, and tracing.
Console SDK
Typed TypeScript client for every Console endpoint, with streaming support.
Chat UI
React components for a production chat surface — streaming, tool cards, uploads, and theming.
Looking for peers, hookId widgets, or the Client SDK? Those are Cognipeer Studio patterns, listed under Studio use cases.
Weighing one of these against an alternative? The product comparisons page puts each Cognipeer product next to the tools teams usually evaluate alongside it.