Hyphen

Infrastructure for governed autonomous AI.

Hyphen is the execution layer for AI agents that make real decisions in real businesses. Define workflows in JSON or plain language, execute them deterministically, and let bounded AI agents handle the reasoning — with full audit trails, structural permissioning, and human-in-the-loop at every critical juncture.

Start Building

  • Quickstart Guide — Register an action, create a workflow, execute it. 15 minutes.
  • Core Concepts — The six building blocks you need to understand.
  • API Reference — Full endpoint spec with request/response examples.
  • Templates — Production-ready workflow patterns across industries.

Governed Autonomy

AI agents that reason and act on their own — within boundaries you define.

flowchart TD A["Operational Event<br/>(alert, document, request, exception)"] --> B["Deterministic Rules<br/>Matcher + Conditions"] B -->|"~80% auto-handled"| C["✅ Resolved"] B -->|"Exceptions"| D["ReAct Agent<br/>Bounded AI — thinks, acts, observes"] D -->|"~15% AI-resolved"| C D -->|"Low confidence"| E["Human Review<br/>PbotApproval"] E -->|"~5% human-resolved"| C C --> F["Audit Trail<br/>Every step, every decision, every reasoning trace"] style B fill:#e8f5e9,stroke:#2e7d32 style D fill:#e3f2fd,stroke:#1565c0 style E fill:#fff3e0,stroke:#e65100 style F fill:#f3e5f5,stroke:#6a1b9a

80 / 15 / 5 — The exact ratio varies by use case, but the architecture is always the same: rules first, AI second, humans last. This graduated approach gives you automation speed with human-grade accuracy.

## How It Works

Hyphen operates on a three-phase execution model:

Phase 1 — AI as Compiler. Describe what you want in plain language. Hyphen's AI compiles your intent into a precise JSON workflow specification — the conditions, data references, branching logic, and escalation paths. Humans describe the what. AI produces the how.

Phase 2 — Deterministic Runtime. The execution engine runs the compiled spec exactly as written. No improvisation. If the spec says "wait for approval," it waits. If a condition fails, it follows the defined fallback. Enterprises audit specs, not vibes.

Phase 3 — Bounded Agentic Runtime. For tasks requiring judgment — investigating exceptions, interpreting documents, making recommendations — ReAct agents reason within cages defined by the spec. Only declared tools are available. Every thought and action is captured. Iteration caps and stuck detection prevent runaway execution.

What You Build With It

The same primitives — matching, agents, approvals, storage — compose into workflows across any operational domain.

Domain Use Case Pattern
Finance Invoice reconciliation, payment matching, exception investigation Matcher → Agent → Approval
IT & Security Alert triage, incident response, access reviews Agent enriches → containment → escalation
Legal Contract review, clause extraction, playbook deviation flagging LLM extraction → Matcher → Agent
People Ops Employee onboarding/offboarding, leave processing Agent-as-orchestrator
Healthcare Claims adjudication, denial management, prior authorization Dual matcher → Agent → Clinical review
Supply Chain Supplier risk, PO exception handling, RFP processing Scheduled agent → threshold escalation
Customer Ops Escalation investigation, SLA monitoring, renewals Agent pulls context → drafts resolution → approval

See all templates →

The Primitives

Four building blocks compose into any operational workflow:

Primitive Purpose Example
Matcher Multi-criteria data matching Compare invoices to payments, alerts to known indicators, contract terms to playbook
Loop Batch processing (foreach) or AI reasoning (react) Process 10K records, investigate an exception, orchestrate across systems
PbotApproval Human-in-the-loop Manager sign-off, legal review, SOC analyst escalation
Custom Table Multi-tenant storage Audit log, contract registry, incident database

Three Deployment Patterns

The ReAct agent operates in three patterns depending on where autonomy lives:

flowchart LR subgraph A["Pattern A: Agent as Step"] direction TB A1["Workflow Step 1"] --> A2["🤖 Agent Step"] A2 --> A3["Workflow Step 3"] end subgraph B["Pattern B: Agent as Trigger"] direction TB B1["Inbound Event"] --> B2["🤖 Agent classifies"] B2 --> B3["→ Workflow A or B or C"] end subgraph C["Pattern C: Agent as Orchestrator"] direction TB C1["🤖 Agent coordinates"] --> C2["→ Workflow 1"] C1 --> C3["→ Workflow 2"] C1 --> C4["→ Workflow 3"] end
Pattern When to Use Example
Agent as Step Most of the process is deterministic, one step requires judgment Invoice matching → agent investigates exceptions
Agent as Trigger You don't know upfront which workflow to run Agent classifies incoming document → routes to correct pipeline
Agent as Orchestrator Dynamic coordination across sub-processes Agent coordinates onboarding across IT, HR, training, equipment

For AI Agents

If you're an AI agent or coding assistant, fetch /llms.txt for the complete documentation in a single structured text file optimized for LLM consumption.

Built by the Hyphen team. API Reference · GitHub