Developer questions

HumanLayer is a human decision orchestration API.

It allows a system (AI agent, backend, workflow engine) to:

• submit a decision case
• wait for qualified human validation
• receive a structured response
• with a complete audit trail

👉 For a developer, HumanLayer is an external service you can call, like Stripe, Twilio, or Auth0 — but for human decisions.

When your system reaches a point where:

• a decision carries human accountability
• a rule is no longer sufficient
• a signature or validation is required
• or when you want formal proof of validation

Simple rule:

If you hesitate to automate → call HumanLayer.

Yes, natively.

HumanLayer is designed to:

• be called as a tool
• work in agentic loops
• be used by LLMs under control

Mental model:

if confidence < threshold or risk == "high":
    decision = humanlayer.request(...)

Both.

Async (recommended)
You create a decision request, continue your workflow, and listen to webhooks.

Sync (blocking)
Possible for fast decisions with a short SLA.

In all cases, delays are explicitly declared and contractual.

A decision is a structured object, with:

• a type (compliance_check, expert_judgment, authorized_decision)
• a level (1, 2, or 3)
• context provided by AI
• a status (pending, approved, rejected, escalated, timeout)
• a human justification
• audit metadata

👉 This is not free text. It's an artifact a system can use.

Only:

• the strictly necessary context
• the AI-prepared elements
• the required fields to decide

No global system access, no unnecessary data.

👉 Minimization by design.

Yes.

HumanLayer can work with:

• internal Sentinels
• external Sentinels
• or a mix of both

In all cases, HumanLayer remains:

• the orchestration layer
• the source of truth
• the audit proof

HumanLayer handles:

• timeouts
• automatic escalations
• default rejections
• configurable fallbacks

Behavior is deterministic and configurable.

Your code never stays blocked indefinitely.

Yes.

You can define:

• binary decisions
• conditional decisions
• decisions with required fields
• decisions with thresholds

HumanLayer does not allow ambiguous decisions.

Yes.

Natively:

• escalade automatique
• second Sentinel
• multi-signature validation
• quorum (enterprise configuration)

No. Never.

HumanLayer :

• does not generate decisions
• does not modify the human response
• does not "correct" the Sentinel

It orchestrates, structures, and logs.

• API key / OAuth authentication
• Scopes per decision type
• Organization isolation
• Access logs
• Encryption in transit and at rest

Sentinels can only access the cases assigned to them.

You can extract:

• the full decision history
• the justifications
• the timestamps
• the Sentinel identities

👉 No need to reconstruct from application logs.

A classic workflow:

• does not verify qualifications
• does not assign accountability
• does not provide enforceable proof
• is not designed for AI

HumanLayer treats a decision as a binding act, not a click.

Yes — where it's intentional.

HumanLayer is called:

• only at critical points
• when slowing down is preferable to taking a risk

Everywhere else, your system remains fully automated.

Because you would need to build:

• an assignment system
• human governance
• audit-grade traceability
• decision SLAs
• agent-native integration

👉 HumanLayer saves you months, even years.