+ P

Integration · Evaluate

Evaluate for LlamaIndex agents

Capture every LlamaIndex Workflow step the same way LlamaIndex itself defines one — event in, work done, event out — so a trace reads as the same step graph you wrote.

Book a demo → Request access

TL;DR

Prefactor evaluates your LlamaIndex agents — score outcome quality against the captured spans, track drift by comparing custom spans across versions and environments, and classify every run's risk on two axes: data sensitivity and action consequence.

Evaluate

pillar

TS + Py

official SDKs

Spans

LLM · tools · agents

Tokens

usage captured

How to add evaluate to LlamaIndex

Install the SDK

Add prefactor-core to your environment.

Register & create spans

Spans flow to Prefactor

Structured trace data lands in Prefactor as your agent runs.

# pip install prefactor-core
import os
from prefactor_core import PrefactorCoreClient, PrefactorCoreConfig
from prefactor_http import HttpClientConfig

config = PrefactorCoreConfig(
    http_config=HttpClientConfig(
        api_url="https://app.prefactorai.com",
        api_token=os.environ["PREFACTOR_API_TOKEN"],
    )
)

client = PrefactorCoreClient(config)
await client.initialize()

# then instrument your LlamaIndex run with spans — see docs.prefactor.ai

Shown with the Prefactor SDK — a first-class, working integration today.

How the LlamaIndex integration actually works

A LlamaIndex Workflow is event-driven: a @step method receives a typed Event, does its work, and returns another Event that triggers the next step — Prefactor spans one step at a time, the same StartEvent-to-StopEvent path the workflow itself runs.
Retrieval steps built on index.as_query_engine() are captured with the same span shape as any other step, so a RAG-style retrieve-then-synthesize workflow traces as one connected run, not a retrieval log plus a separate LLM log.
Beyond auto-captured spans, use withSpan to record any custom step you define — an API call, a quality check, a business action.

What Prefactor captures for LlamaIndex agents

Outcome quality

Score agent outputs against your own criteria, task by task, using the continuous run history as the record to measure against.

Drift detection

Compare custom spans for the same operation across versions and environments — a model update or prompt change shows up as a difference between spans, before it shows up as a quality drop.

Risk classification

Every run scored on data sensitivity and action consequence, weighted into a Low / Medium / High / Critical classification.

Data tagging

Tag PII and other sensitive fields once in the schema; every run carrying that tag becomes searchable — the record enforcement acts on.

Trace anything — not just LLM calls

The SDK captures LLM, tool, and agent spans automatically. With withSpan you wrap any operation in your own span type — an API call, a database query, a quality check, a business action — each with its own payload and schema. It all flows into the same Observe, Evaluate, and cost views.

research_competitorquality_checkpricing_lookuprefund_decisiondoc_retrieval …anything you define

import { withSpan } from "@prefactor/core";

// Wrap ANY operation in a span you define — an API call, a quality
// check, a business action — with its own spanType, inputs and schema
await withSpan(
  {
    name: "research competitor",
    spanType: "research_competitor",
    inputs: { competitor },
  },
  async () => {
    const results = await search(competitor); // your tool / API calls
    return summarize(results);                // captured as one span
  },
);

Nest spans to capture business-level actions, and start with permissive schemas you tighten over time. Instrumentation strategy →

An example run, span by span

Illustrative — a single LlamaIndex run as nested spans.

Trace · LlamaIndex run

1.84s6 spans1,210 tokensok

invoke_agent 1840

llm: plan 440

tool: search_kb 330

retriever: vector_search 210

llm: synthesize 700

tool: send_reply 320

agentllm calltool callretriever

Illustrative example.

Manual logging vs DIY vs Prefactor

Capability	Manual	DIY OpenTelemetry	Prefactor
LLM / tool / agent spans	Hand-rolled	✓ build it	✓ via the SDK
Token usage captured per call	—	Build it	✓
Configurable capture & sampling	—	Partial	✓
Hosted Admin UI (agents, instances)	—	—	✓
Risk profiles & audit trail	—	—	✓

LlamaIndex evaluate — FAQ

Does evaluation reuse the same LlamaIndex integration?+

Yes — evaluation runs on the spans the SDK already records for LlamaIndex, so there is one integration, not a separate one for evaluation.

What is quality drift and how is it detected for LlamaIndex agents?+

Drift is a change in behaviour over time — after a model update, a prompt change, or a data shift. Because a custom span records the same LlamaIndex operation every time it runs, this week's spans can be compared directly against last week's, or against a different version or environment.

How is risk scored for LlamaIndex runs?+

On two axes — data sensitivity (what kind of data the run touched) and action consequence (what the agent did with it) — combined via configurable weights into a Low/Medium/High/Critical classification per run.

Can I tag and find PII across LlamaIndex runs?+

Yes — tag the fields that matter once in your agent's data schema, and every run carrying that tag becomes searchable across your whole LlamaIndex deployment, not just the run it was tagged in.

Do I need a dedicated package for LlamaIndex?+

You can instrument LlamaIndex today with the framework-agnostic prefactor-core SDK; a dedicated package can be added on request.

What does Prefactor capture from LlamaIndex?+

Prefactor records query-engine steps, retrievals, agent tool calls and LLM calls as structured, timestamped spans — so every LlamaIndex run is captured as trace data you can reconstruct, search and export end to end.

Does Prefactor add latency or change how LlamaIndex runs?+

No. Observability capture is designed to stay off your agent's critical path, so it doesn't alter your LlamaIndex logic or your users' responses. The only part that acts inline is the optional runtime guardrails you enable per agent — by design, so a high-risk or low-confidence action can be held for human approval before it executes.

Can I evaluate agents built with LlamaIndex and catch regressions?+

Yes. Once runs are captured, eval suites score quality and groundedness on real traffic, drift detection flags behaviour changes after deployment, and versioned eval history catches regressions before they ship — the observe → evaluate → improve loop applied to your LlamaIndex agents.

Keep going

See it on your LlamaIndex agents

Book a 15-minute setup and our team gets you evaluate in production.

Book a demo → Talk to integrations