Skip to content
04Industries05Work06Resources07About
Start a conversation
Platform
The agent runtime

UAP Platform

The Unified Agentic Platform — a governed runtime and SDK that lets teams build, deploy, and operate autonomous agents safely, in hours instead of months.

Governance · lifecycleAgent frameworkModel gatewayData · RAG · guardrailsrequestinactplatform_core SDK
Overview

UAP is the foundation our products are built on. It packages everything an autonomous agent needs — a base agent framework, model routing, retrieval, session and memory, messaging, and a full lifecycle and governance layer — into one pip-installable SDK (platform_core). Product teams subclass a base agent and register their own tools and policies, shipping domain agents without re-implementing the plumbing, while platform-level guardrails, tracing, and approvals keep every action safe and auditable. It runs on your own infrastructure — no data leaves your cloud.

What it does

01

Base agent framework

A reusable LangGraph agent — Scanner/Input → Retriever → Reasoner → PolicyGate → Executor → ResponseAssembler — that products extend in a few lines.

02

Model gateway & routing

A LiteLLM gateway routes to Claude Sonnet (primary), Haiku (fast), and GPT-4o (fallback), with retries and failover, and traces every call to LangSmith.

03

Deterministic guardrails

Six non-LLM evaluators — PolicyCeiling, AuthRequired, ConflictCheck, PIIFence, EscalationTrigger, TenantPermission — return pass / warn / block before any action.

04

RAG & data layer

Postgres + pgvector hybrid retrieval, a Redis session store, and a run/trace schema that makes every agent run observable.

05

Governance & multi-tenancy

Catalog, versioning, promotion, and certification, with row-level tenant isolation so many agents can serve many tenants safely.

06

Fine-tune flywheel

LangSmith export → Together.ai fine-tune → vLLM shadow mode, so agents improve from their own traces before anything is promoted.

The request path
  1. 1

    Plan

    The agent decomposes the task into a traceable plan.

  2. 2

    Retrieve

    Hybrid pgvector + full-text retrieval grounds it in your data.

  3. 3

    Reason

    The gateway routes to the right model with retries and fallback.

  4. 4

    Guard

    Deterministic evaluators gate every proposed action.

  5. 5

    Act / approve

    Low-risk actions execute; high-risk pause for a human.

By the numbers
Hours
to scaffold a production agent
6
deterministic guardrail evaluators
Every action
traced & governed

Built and merged; control plane in rollout.

Built with
LangGraphLiteLLM gatewayClaude Sonnet / HaikuPostgres + pgvectorRedisAmazon MSK (SASL/IAM)EKS + IRSALangSmithTogether.ai / vLLM
Where it is

Feature-complete foundation: the gateway, data layer, agent framework, guardrails, tenancy, lifecycle governance, and the fine-tune flywheel are built and merged. The self-serve control plane — the lifecycle and tenant-onboarding API and console — is deployed and in rollout. Next: OIDC/RBAC via IAM Identity Center and broader multi-cloud data and messaging.

FAQ

Good questions.

Is UAP a framework or a managed platform?

Both. platform_core is a pip-installable SDK your teams build on, running on your own infrastructure (EKS/IRSA), with a control plane for lifecycle and tenants. No data leaves your cloud.

How is it different from using an agent library directly?

A library gives you an agent loop. UAP adds the parts that make agents safe in production — deterministic guardrails, human approvals, tracing, versioning, and multi-tenant governance.

Which models does it use?

Claude Sonnet as primary and Haiku for fast routing, with a GPT-4o fallback — all behind a gateway, so models are swappable and every call is traced.

Built on these capabilities

See UAP Platform on your systems.

Start a conversation
Next product
Resolve