HB-Eval

Your agent finished the task.
Did it behave?

Benchmarks measure whether an agent completed its work. Almost nothing measures how it behaved while things were going wrong — and that is where production incidents come from. HB-Eval measures it, watches it live, and can stop a run before the damage lands.

The demo needs no account. 500 evaluations a month on the free plan.

The reliability gap

An agent can retry the same failing call three times, lose its reasoning trail, recover by accident, and still deliver the right answer. Pass/fail scores it a success. The next time the same weakness appears, it will not be so lucky.

What benchmarks measure

Task completed

Nominal performance, under conditions where nothing broke.

What nobody measures

Behaviour under fault

Whether recovery was reasoned, whether the plan held, whether anyone can reconstruct what happened.

Five metrics

Each answers a question a completion score cannot.

PEI

Planning Efficiency

Is the plan holding, or is the agent redoing it?

Repeated re-planning means the agent is thrashing, not thinking.

FRR

Failure Resilience

Of the steps where a fault was present, how many still completed?

Undefined until a fault actually happens — resilience cannot be scored against nothing.

IRS

Intentional Recovery

Was the recovery reasoned, or a blind retry?

The difference between an agent that adapts and one that repeats itself faster.

TI

Traceability

Can each decision be followed afterwards?

An agent nobody can audit is an agent nobody should deploy.

CSI

Consistency Stability

Does the same task produce the same behaviour across runs?

Needs repeated runs, so it stays undefined inside a single session.

Undefined is never reported as zero

A metric that was never measured shows as a dash, all the way to the wire. Reporting it as 0.00 would claim a measured failure on a dimension nothing examined — and a chart, a gate or an auditor reading that zero would draw a confident, wrong conclusion.

Measure your own agent

Wrap your existing loop. Nothing about the agent changes, and the instrumentation costs about 0.002 ms per step.

Python
pip install hb-eval-sdk==2.9.0

from hb_eval_sdk import HBEvalClient

client = HBEvalClient(api_key=..., aes_key=..., signing_secret=...)

with client.monitor(
    agent_id="support-agent",
    halt_policy={"metric": "frr", "below": 0.5, "for_steps": 3},
) as session:
    for step in my_agent.run(task):
        session.record_step(
            action=step.name,
            success=step.ok,
            had_fault=step.faulted,
        )
        if session.should_halt:
            break            # cooperative: your loop decides how to stop

What is included

Every item links somewhere you can use it now.

Zero-setup instrumentation

One import derives reliability signals from OpenTelemetry spans you already emit. No new instrumentation code.

How derivation works

Live monitoring

Metrics computed per step, streamed while the agent runs. Timeline, replay, and comparison between runs.

Open monitoring

Safe Halt

Stop a run when resilience collapses. Cooperative, sustained rather than instant, and off unless you configure it.

How halting works

Policy engine

Retry, escalate or halt on a metric breach — with three independent limits so a policy cannot loop forever.

Policy reference

Fault Injection Studio

Six fault types across six domains. Preview the exact text your agent would receive before running anything.

Open the studio

CI reliability gate

Gate a pull request on reliability, comparing against your own baseline rather than an absolute floor.

Set up the gate

Alerting

Slack, PagerDuty or a plain webhook. Twenty breaches raise one alert, not twenty.

Configure alerts

Observatory

Aggregate reliability across contributed runs. Anonymous at write time, withheld until five independent accounts.

View the data

Verified evaluation

HB-Eval calls your agent itself, so the result cannot be shaped by the agent. Five runs a month on the free plan — enough to compare against a self-reported one.

How verification differs

Workspaces and audit export

Roles for a team, and a one-call export of every automated decision your agents made — including the alerts that failed to deliver.

Audit export

How it fits together

Where your data goes, what leaves your machine, and what we can see — drawn from the implementation, not an intended design.

See the architecture

Status and retention

Health checked rather than asserted, with the last automatic data cleanup published so the policy is verifiable.

Service status

Works with what you already use

One adapter call. Your agent keeps its own control flow — HB-Eval measures it rather than replacing it.

LangChain

adapt_langchain_agent(agent_executor)

LangGraph

adapt_langgraph_agent(compiled_graph)

CrewAI

adapt_crewai_agent(crew_agent)

Not using a framework? The SDK works around any loop, and an OpenTelemetry-instrumented agent needs one import and no calls at all.

A memory governed by reliability — and explanations grounded in it

Most systems remember everything and explain with confident guesses. HB-Eval does the opposite: it remembers only what proved reliable, and explains only what it can ground in a qualified record.

Quality-governed memory

Every run is judged before it is remembered. A trajectory enters qualified memory only when it clears PEI ≥ 0.80 and TI ≥ 4.0.

A memory that stores everything eventually recalls its own worst behaviour as precedent. The gate is what stops an agent learning from the runs it should forget.

Performance-grounded explanations

Explanations cite stored episodes above a similarity threshold and quote figures from the record, not from a model. Where no precedent exists, the system says so and defers to a human.

Saying “I have no comparable case” is a useful answer. A fluent explanation with no evidence behind it is not, and is harder to catch.

Both layers are live in production and implement published work — EDM and HCI-EDM. Papers, definitions and open problems

HB-EVAL AGENT PASSPORT

A record of behaviour anyone can verify

Every halt decision with the policy that caused it, every alert and whether it was delivered, the five metrics over 30, 60 and 90 days — signed with Ed25519 and published at a link.

The signature is checked in the reader’s own browser against a public key we publish. An auditor, a customer or a regulator verifies it without asking us and without our permission — which is the only thing that makes such a record worth more than a claim.

No overall grade — the weakest dimension is namedExpires after 90 days, because behaviour changesNot a certification

Plans

The free plan is not a trial. It runs the full battery, all five metrics, live monitoring and signed passports, with no time limit.

Free

$0

  • 500 evaluations a month, 3 agents
  • All five metrics, full fault battery
  • Live monitoring, Safe Halt, CI gate
  • Signed Agent Passports
  • 5 verified evaluations a month

Pro

Coming soon

  • 5,000 evaluations a month, 10 agents
  • Unlimited verified evaluations
  • Unlimited memory retrieval
  • Priority support

Why five verified runs are free. On every other path the behavioural evidence comes from your own agent’s runner. On the verified path HB-Eval calls your agent itself, so the result cannot be shaped by the agent. That difference is the strongest thing the paid tier offers and the hardest to convey in a sentence — five runs is enough to see it for yourself.

Full comparison

Built on published work

The framework, the metric definitions and the fault methodology are described in a manuscript under review, with three companion preprints on adaptive planning, evaluation-driven memory, and performance-grounded explanation.

See it before you sign up

Two minutes, no account, no keys. The same agent with and without a reliability policy.