---
title: "Before You Ship Nova, Set Four Gates"
description: "A practical checklist for putting Amazon Nova into an application: choose nova-lite or nova-pro by workload, expose tools, and verify context, modality, region, and cost constraints."
---

# Before You Ship Nova, Set Four Gates

**Type:** [How to](https://yomu.fyi/visual-explainers/category/how-to.md)

![A four-step light-mode diagram for deploying Amazon Nova: define the workload, choose nova-lite or nova-pro, connect a chat or agents endpoint with tools, then validate context, modality, region, latency, and cost.](https://yomufyi.s3.us-east-1.amazonaws.com/visual-explainers/97ecb476-3932-4b24-82a2-4f1f200d7404/image-475762e3-db40-4688-a270-4c752402876a.webp)

> A practical checklist for putting Amazon Nova into an application: choose nova-lite or nova-pro by workload, expose tools, and verify context, modality, region, and cost constraints.

## Explanation

Amazon Nova is presented here as an application decision rather than a single model choice. Start by defining whether the workload prioritizes low latency and volume or accuracy and deeper reasoning, then select nova-lite or nova-pro accordingly. The supplied Heroku integration provides managed inference, an OpenAI-compatible chat endpoint, an agents endpoint, and tool support including custom MCP tools. Before launch, check the 300,000-token context window, current text-to-text scope, US or EU provisioning, and expected token costs.

**Tags:** [AI](https://yomu.fyi/topic/ai.md), [AI Agents](https://yomu.fyi/topic/ai-agents.md), [Amazon Nova](https://yomu.fyi/topic/amazon-nova.md), [Architecture](https://yomu.fyi/topic/architecture.md), [LLMs](https://yomu.fyi/topic/llm.md)

## Related reading

### [From zero-shot forecast to purchase order with Amazon Bedrock AgentCore](https://yomu.fyi/post/from-zero-shot-forecast-to-purchase-order-with-amazon-bedrock-agentcor.md)
- Company: [AWS](https://yomu.fyi/company/aws.md)
- Author: Hyunsoo Kim, Ph.D.
- Published: Sep 11, 2026
- Type: Problem & solution

This post presents an inventory automation architecture that moves from zero-shot demand forecasts to validated purchase orders while applying safety stock, minimum order quantities, budgets, and promotional adjustments. It combines Amazon Chronos2, hosted on SageMaker Serverless Inference, with four Claude-powered agents built using the Strands Agents SDK and deployed on Amazon Bedrock AgentCore; deterministic Python tools perform computation and agents handle judgment. Product data and future covariates arrive through CSV files in S3, while business rules remain in JSON, enabling what-if forecasts and onboarding without per-SKU training. In internal testing across 50 SKUs over a four-week horizon, the system reached 12.3% median WAPE, reduced onboarding from 2–3 weeks to under five minutes, and lowered estimated monthly inference cost from about $1,091 to $15. A conditional retry loop surfaces budget violations for user decisions instead of silently truncating orders, with traces and evaluator scores supporting auditability.


### [Bringing custom knowledge to agents with AutoRAG](https://yomu.fyi/post/bringing-custom-knowledge-to-agents-with-autorag.md)
- Company: [Red Hat](https://yomu.fyi/company/red-hat.md)
- Author: Diego Alvarez Ponce, Diego Garcia Perez
- Published: Sep 11, 2026
- Type: Tutorial

Enterprise LLMs can hallucinate when they lack company-specific vocabulary and documentation, so the guide builds a bank agent grounded in internal data. It configures Red Hat OpenShift AI 3.5 Technology Preview features, enables OGX, AutoRAG, and the MCP catalog, and deploys PostgreSQL, Milvus, and MinIO for metadata, vector embeddings, and artifacts. AutoRAG processes documents, evaluates pipeline configurations against a benchmark dataset, and identifies a preferred setup; the example uses Qwen3-8B and embeddinggemma-300m models. A MariaDB MCP server adds access to customer records, with a patch supplying writable logging storage and a warning that unrestricted ALLOWED\_HOSTS is for demo/development only. The resulting Streamlit agent answers a customer-information query and a Gold-card-limit question using RAG context and database tools.


### [AI Functions in ClickHouse: Upgrade your SQL to the AI age](https://yomu.fyi/post/ai-functions-in-clickhouse-upgrade-your-sql-to-the-ai-age.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Sep 11, 2026
- Type: Explainer

ClickHouse’s beta AI Functions let SQL queries call an LLM or embedding provider directly, keeping classification, extraction, generation, translation, redaction, filtering, embedding, and similarity work alongside stored data. The feature addresses workflows that export rows to separate LLM, orchestration, or vector-database systems and then reload results, with the stated goal of running the full RAG cycle in ClickHouse. Functions make remote HTTP calls per input, or batch embedding inputs, and return native ClickHouse values; in open-source deployments, named collections store provider credentials and endpoint settings. Examples use Hacker News data for topic classification and natural-language filtering, while the guidance emphasizes cheap predicates, quotas, LIMIT tests, prompt-injection defenses, non-determinism, cost, latency, and provider access to data in cleartext after TLS termination.


### [Amazon Nova Models: Now Available on Heroku](https://yomu.fyi/post/amazon-nova-models-now-available-on-heroku.md)
- Company: [Heroku](https://yomu.fyi/company/heroku.md)
- Author: Anush DSouza
- Published: Aug 26, 2025
- Type: Announcement

Amazon Nova’s nova-pro and nova-lite models are now available through Heroku Managed Inference and Agents, giving applications a managed way to use them. The integration initially supports text-to-text workloads, while multimodal support is planned for a future release; both models support tool use and offer 300,000-token context windows. Nova-lite targets speed, low latency, and high-volume real-time applications at $0.06 per 1M input tokens and $0.24 output, whereas nova-pro targets accuracy and deep reasoning at $0.80 input and $3.20 output. Heroku provides an OpenAI-compatible /v1/chat/completions endpoint for chat and generation, plus /v1/agents/heroku for built-in Heroku tools and custom MCP tools, with provisioning available in US and EU regions through the add-on or CLI.