INTRODUCING JSOC AI — FABRIC GOVERNS EVERY AI ACTION. PROOFSTATE PROVES EVERY RELEASE.

EXPLORE JSOC AI

CHAPTER 04.2 — JSOC AI · PROOFSTATE

PROOFSTATE

CONFIDENCE IN EVERY AI RELEASE.

TRACE · support-agent · productionILLUSTRATIVE
A ProofState trace: the agent run broken into spans, including a Fabric policy check, followed by evaluation scores and a ready-to-promote stamp.SPANTIMELINEDURATIONagent.run2.41s├ retrieve.kb0.31s├ llm.plan0.51s├ tool.orders0.27s├ fabric.policy ALLOW0.07s├ llm.reply0.87s└ judge.eval0.31sEVALUATIONSFAITHFULNESS0.94POLICY ADHERENCE1.00TONE0.91PII LEAKS0 ✓READY TO PROMOTEEVIDENCE ATTACHED ✓
01WHAT IT IS
One workspace to trace, evaluate and improve AI applications — from the first trace to the next release.
02WHO IT IS FOR
Teams shipping AI to real users: engineers, product owners and the reviewers who sign off.
03WHAT YOU GET
A record of every step, a score behind every change, and evidence behind every release.

/ THE REAL PRODUCT

SEE THE
EVIDENCE.

Real screens · demo data · open any of them

/ THE IMPROVEMENT LOOP

OBSERVE. EVALUATE.
IMPROVE. PROTECT.

Four moves, on repeat. Pick one, or let it play.

/ 01 — OBSERVE

FIND THE SIGNAL.

See every step your AI took — the prompt, the tools it called, how long it took and what it cost.

  • Traces of every request, span by span
  • Sessions, users and an agent graph
  • Latency and cost per step
TRACE · support-agent · productionILLUSTRATIVE
A ProofState trace: the agent run broken into spans, including a Fabric policy check, followed by evaluation scores and a ready-to-promote stamp.SPANTIMELINEDURATIONagent.run2.41s├ retrieve.kb0.31s├ llm.plan0.51s├ tool.orders0.27s├ fabric.policy ALLOW0.07s├ llm.reply0.87s└ judge.eval0.31sEVALUATIONSFAITHFULNESS0.94POLICY ADHERENCE1.00TONE0.91PII LEAKS0 ✓READY TO PROMOTEEVIDENCE ATTACHED ✓

/ EVERYTHING IN THE WORKSPACE

TWELVE TOOLS.
ONE PLACE.

  • TRACE EXPLORER

    Follow any request from first token to final answer.

  • AGENT GRAPH

    See how multi-step agents actually move through tools.

  • SESSIONS & USERS

    Group traces by conversation and by user.

  • ANALYTICS

    Quality, latency and cost over time.

  • ALERT RULES

    Hear about drift before your customers do.

  • PROMPT LIBRARY & STUDIO

    Versioned, labelled prompts and a safe place to iterate.

  • SCORES & HUMAN REVIEW

    Reviewers and judges on the same scorecard.

  • DATASETS & EXPERIMENTS

    Real cases, repeatable tests, side-by-side results.

  • RED TEAMING

    Adversarial probes, kept as release evidence.

  • VERA, THE ASSISTANT

    Ask about your traces in plain language.

  • AI GATEWAY

    One door to your model providers.

  • AUTOMATIONS & INTEGRATIONS

    Wire ProofState into the rest of your stack.

/ INTEGRATIONS

KEEP YOUR STACK.
ADD THE EVIDENCE.

ProofState plugs into the providers and frameworks you already use. OpenTelemetry native.

MODEL PROVIDERS

AGENT FRAMEWORKS & SDKS

  • + DSPY · HAYSTACK · AGNO · LITELLM · PORTKEY · GUARDRAILS

STANDARDS & PROTOCOLS

From ProofState's integration catalog. Brand names belong to their owners.

/ GET STARTED

FOUR STEPS
TO YOUR FIRST TRACE.

  1. 01
    CREATE A PROJECT

    Sign in at proofstate.ai and create a project for your application.

  2. 02
    ADD AN LLM CONNECTION

    Under Project Settings, connect a model provider for the Playground and experiments.

  3. 03
    CREATE AN API KEY

    Save the secret when it is shown — it is displayed only once.

  4. 04
    SET THREE VARIABLES

    Point the SDK at your project, run your app, and watch the traces arrive.

.env
PROOFSTATE_PUBLIC_KEY="pk-ps-..."
PROOFSTATE_SECRET_KEY="sk-ps-..."
PROOFSTATE_BASE_URL="https://proofstate.ai"

SDKs for JavaScript, Python and Java · public API · project MCP server

/ FREQUENTLY ASKED QUESTIONS

QUESTIONS
ABOUT PROOFSTATE.

HOW DO WE SEND DATA TO PROOFSTATE?

With the SDKs for JavaScript, Python or Java, the public API, or OpenTelemetry. Create a project, add a project API key, and set three environment variables in your application.

DOES IT WORK WITH OUR FRAMEWORK?

Most likely. ProofState integrates with the major model providers and frameworks — OpenAI, Anthropic, Google, Amazon Bedrock, Mistral, LangChain, LlamaIndex, CrewAI, Mastra and more — and anything that speaks OpenTelemetry.

CAN OUR TEAM USE IT FROM THEIR AI TOOLS?

Yes. Each project has an MCP server, so assistants and agents your team already uses can query traces, prompts and scores directly.

HOW DOES IT RELATE TO FABRIC?

Fabric sends every governed run to ProofState as evidence, and can use prompts kept in ProofState — always the version labelled production. Each product also works on its own.

YOUR NEXT STEP

SEE YOUR OWN TRACES IN PROOFSTATE.

Bring one AI feature. We'll help you instrument it, build a first test set, and show you what the evidence looks like.