Your Java LLM agent works in the demo. Friday night in production is another story.

Описание и применение

В продакшене агент LLM, отвечающий за возвраты, столкнулся с 503‑ами, неверным JSON‑ом и несанкционированным крупным возвратом. Внедрение ARA добавило контракт проверки вывода, отказоустойчивость и ручное одобрение критических действий, устранив проблемы.

Задача

An LLM‑driven refund agent failed in production: provider 503s, malformed JSON, and unapproved large refunds.

Результат

The agent now validates outputs deterministically, retries malformed responses, requires human approval for critical actions, and handles provider failures and cost caps, preventing the production incidents described.

Рабочий процесс

• 1. Configure AgentContract with input sanitizers, content truncator, output schema, Markdown fence stripper, and repair attempts.
• 2. Create AraRuntime with llmClient and approvalGate.
• 3. Define AraAgent with humanApprovalRequired=true and enabledTools=["refund"].
• 4. When agent calls refund, runtime parks the call and creates an approval request.
• 5. Operator reviews request and submits Approved, Rejected, or Modified decision via gate.submit().
• 6. Agent proceeds based on decision or retries if rejected.

Доказательства

ARA is an open source (Apache 2.0) Java 21 runtime for LLM agents, built on LangChain4j.

Источник

The model wraps its JSON in a Markdown fence, or forgets a required field.

Источник

An agent can have access to the right tool, understand the request and even write a convincing justification.

Источник