Future AGI × Vertex AI

Vertex AI on Future AGI

Cloud Platforms

Google Cloud's hosted Gemini, Anthropic, and Llama endpoints.

python typescript java · trace evaluate optimize

Start free Open in docs View example on GitHub

What you get

Everything traced, scored, and improvable

One install instruments Vertex AI on OpenTelemetry. Future AGI then layers evaluators, optimisers, and simulations on top of the same trace tree — no second SDK, no double instrumentation.

Trace

Auto-instrumented spans

Every Vertex AI call becomes a span — inputs, outputs, latency, tokens, cost, model name, tool args, retrieval results, and chain steps captured automatically.

Evaluate

70+ evaluators on every span

Attach Groundedness, Context Relevance, Prompt Injection, Toxicity, and 70+ more — purpose-built scorers powered by the Turing eval models, not generic LLM-as-judge.

Optimize

Closed-loop improvement

Pipe failed traces into agent-opt: GEPA, PromptWizard, ProTeGi, and Bayesian search rewrite your prompts with proof of measured gains.

Simulate

Adversarial scenarios at scale

Generate hundreds of personas and run them through your Vertex AI agent before launch — text and voice, scripted or persona-driven.

Quickstart · <3 min

Instrument Vertex AI in three steps

Step 1

Install the traceAI package

One package per language, ships from PyPI, npm, and Maven Central.
Step 2

Register the trace provider

Set FI_API_KEY and FI_SECRET_KEY, then call VertexAIInstrumentor().instrument().
Step 3

Run your existing Vertex AI app

No code changes. Traces appear in the Future AGI dashboard within seconds.

Install

pip install traceAI-vertexai

npm install @traceai/vertexai

<dependency>
  <groupId>ai.futureagi</groupId>
  <artifactId>traceai-java-vertexai</artifactId>
  <version>LATEST</version>
</dependency>

Instrument

from fi_instrumentation import register
from fi_instrumentation.fi_types import ProjectType
from traceai_vertexai import VertexAIInstrumentor

trace_provider = register(
    project_type=ProjectType.OBSERVE,
    project_name="VERTEXAI_APP",
)

VertexAIInstrumentor().instrument(tracer_provider=trace_provider)

# Your existing Vertex AI code runs unchanged from here.
# Every call is now an OpenTelemetry span in Future AGI.

import { register } from '@traceai/fi-core';
import { VertexAIInstrumentation } from '@traceai/vertexai';

const tracerProvider = register({
  projectName: 'vertexai_app',
  projectType: 'observe',
});

new VertexAIInstrumentation().instrument({ tracerProvider });

// Your existing Vertex AI code runs unchanged.
// Every call is now an OpenTelemetry span in Future AGI.

import ai.futureagi.fi.instrumentation.TraceProvider;
import ai.futureagi.traceai.vertexai.VertexAIInstrumentor;

TraceProvider provider = TraceProvider.builder()
    .projectName("vertexai_app")
    .projectType("observe")
    .build();

new VertexAIInstrumentor().instrument(provider);

// Your existing Vertex AI code runs unchanged.
// Every call is now an OpenTelemetry span in Future AGI.

Pick a recipe