Skip to main content

Generative AI

Zeta Alpha agents combine retrieval-augmented generation with tool use, memory, and multi-agent orchestration. There are two ways to work with them, depending on what you need.

What the Harness Provides

CapabilityWhat you getDocs
Composable capabilitiesEverything below is a pluggable source, enabled per agent with include/exclude filters: behavior is configured, not codedConcepts
Retrieval and citationsSearch, browse, and read any Zeta Alpha index, with resolved citations linking back to sourcesTools
Knowledge captureNotes, tags, and private document ingestion through conversationNote Tools
Data analysisCSV/Excel and SQL exploration, aggregation, and inline chartsDataFrame Tools
Web accessFetch and read public pages and PDFs, hardened against hostile contentWeb Tools
SkillsMarkdown-defined behaviors the agent discovers and applies on demandAgent Skills
MemoryFacts persisted across sessions and loaded into the promptMemory
Multi-agentAnonymous sub-agents and named specialist delegationDelegation
MCPExternal tool servers, including per-user OAuth authorizationMCP Tools
Model providersOpenAI, Anthropic, Azure, Bedrock, Ollama, and any OpenAI-compatible endpoint (vLLM), with tool-calling accommodations for small modelsLLM Configuration
Context managementKeeps as much history as fits by virtualizing old and large tool responses before older answers, so smaller and larger models swap in without code changesContext Window Management
Resilient conversationsServer-owned turns that survive restarts: reattach from any replica, resume a crashed turn from its checkpointConversations · Persistence
StreamingSSE streaming with reconnection, turn discovery, and cancellationStreaming
Tool streamingTemplated progress text while tools run, and per-tool shaping that keeps large results out of model context while the UI gets the full resultTool Events
Testing and evaluationBehavior specs, and RAGElo judging through the same provider layer, so the judge can be any OpenAI-compatible backendTesting
DeploymentRun on the Zeta Alpha platform or self-host the REST APISelf-Hosted

Configure Agents

Define agent behavior through JSON configuration: search tools, instructions, skills, memory, and sub-agents. No application code required for most use cases.

Start here if you want to:

  • Create or customize agents for your domain
  • Configure what tools, memory, and instructions an agent uses
  • Deploy agents to the Zeta Alpha platform
  • Test and debug agent behavior locally

Getting Started

Chat API

Call deployed agents from your application through REST or streaming endpoints. Send messages, pass context, and handle responses.

Start here if you want to:

  • Integrate agent conversations into your product
  • Use the streaming or REST Chat API
  • Pass custom context or handle function call requests

Getting Started with the Chat API