+ P Evaluate for Haystack agents
Capture every Haystack Pipeline as the directed graph it actually is — each Component's run as its own span, connected the same way Haystack connects component outputs to inputs.
Prefactor evaluates your Haystack 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.
How to add evaluate to Haystack
Install the SDK
Add prefactor-core to your environment.
Register & create spans
Register the agent instance and record spans around your Haystack run.
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 Haystack run with spans — see docs.prefactor.aiShown with the Prefactor SDK — a first-class, working integration today.
How the Haystack integration actually works
- A Haystack Pipeline is a directed multigraph of Components, each connected by which output feeds which input — Prefactor's spans follow that same graph, so a trace reads as the pipeline's real execution order, not a flat list of calls.
- Haystack's own tracing captures component input/output for debugging, disabled by default to avoid sending sensitive data to a backend; Prefactor's span capture is controlled separately via PREFACTOR_CAPTURE_INPUTS/_OUTPUTS, so the two don't need to be configured in lockstep.
- 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 Haystack 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.
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 Haystack run as nested spans.
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 | — | — | ✓ |
Haystack evaluate — FAQ
Does evaluation reuse the same Haystack integration?+
Yes — evaluation runs on the spans the SDK already records for Haystack, so there is one integration, not a separate one for evaluation.
What is quality drift and how is it detected for Haystack 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 Haystack 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 Haystack 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 Haystack 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 Haystack deployment, not just the run it was tagged in.
Do I need a dedicated package for Haystack?+
You can instrument Haystack today with the framework-agnostic prefactor-core SDK; a dedicated package can be added on request.
What does Prefactor capture from Haystack?+
Prefactor records pipeline component runs, retrievals, agent tool calls and LLM calls as structured, timestamped spans — so every Haystack run is captured as trace data you can reconstruct, search and export end to end.
Does Prefactor add latency or change how Haystack runs?+
No. Observability capture is designed to stay off your agent's critical path, so it doesn't alter your Haystack 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 Haystack 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 Haystack agents.
Keep going
Evaluate for other frameworks
LangChain →CrewAI →LangGraph →OpenAI Agents SDK →Claude Agent SDK →Microsoft AutoGen →See it on your Haystack agents
Book a 15-minute setup and our team gets you evaluate in production.