ADVANCED · 8 MODULES · 64 LESSONS

Generative AI in Production on AWS

Run a generative AI workload on AWS like any serious system: infrastructure as code, guardrails, personal data protection, and token costs under control.

For you if
You already build with language models but have never run one in production on AWS.
By the end
You'll know how to define Bedrock and its guardrails in Terraform, restrict permissions, validate outputs, and calculate cost per token.
You need
The earlier AWS guides (or equivalent), Terraform, Python with pytest, and experience building with an LLM.
  1. 01Genai In Production Vs A Notebook8 LESSONS
    1. Guide introduction: the eighth piece of the ecosystem
    2. A notebook and a production system are not the same problem
    3. Andes Cargo's AI workload: when the deterministic parser isn't enough
    4. The boundary with AI Engineering, said out loud
    5. Hands-on: inventory of what already exists
    6. Bedrock, 2026 landscape: models, families, and why the cheap path stays the default
    7. Hands-on: the honest attempt against Bedrock on LocalStack
    8. Project: Andes Cargo's AI workload map
  2. 02The Bedrock Cost Model8 LESSONS
    1. Introduction: price per token, not per hour
    2. How Bedrock is billed: on-demand tiers, Batch, and Provisioned Throughput
    3. Bedrock quotas: the limit no bill shows
    4. Hands-on: Infracost, inherited
    5. Hands-on: the honest attempt of `infracost scan` on `bedrock.tf`
    6. Why Infracost can't solve this alone, and what can
    7. Hands-on: the cost-per-token calculator
    8. Project: Andes Cargo's `GENAI-COST-PROFILE.md`
  3. 03Infrastructure As Code For An Ai Endpoint8 LESSONS
    1. Introduction: what Terraform knows how to declare without needing to invoke anything
    2. What Terraform resources exist for Bedrock
    3. Hands-on: the `modules/bedrock-guardrail/` module
    4. Hands-on: `BedrockManifestExtractorRole`, least privilege
    5. Hands-on: `terraform plan` of the complete AI infrastructure
    6. The exact limit: why the guardrail's `apply` doesn't run against LocalStack
    7. Hands-on: verifying what can actually be applied
    8. Project: Andes Cargo's AI infrastructure, declared
  4. 04Bedrock Guardrails And Defense In Depth8 LESSONS
    1. Introduction: the managed guardrail and the custom one
    2. Bedrock Guardrails' six policies, explained
    3. Hands-on: declaring the complete guardrail in HCL
    4. Why a managed guardrail isn't enough alone
    5. Hands-on: the custom, deterministic PII scrubber
    6. Hands-on: the output schema validator
    7. The exact limit: why Bedrock Guardrails' real blocking can't be tested here
    8. Project: Andes Cargo's guardrails layer
  5. 05Securing The Ai Workload8 LESSONS
    1. Introduction: the gate already exists, this workload enters it
    2. Least privilege for a model, not a service
    3. Hands-on: `bedrock-least-privilege.rego`, added to `policy/`
    4. Bedrock API keys exist: why this workload still uses an IAM role
    5. Hands-on: Trivy on the new Terraform
    6. Hands-on: signing the extractor's artifact with `cosign`
    7. STRIDE, revisited: the threats specific to an AI workload
    8. Project: Andes Cargo's security gate, extended
  6. 06Finops For Tokens8 LESSONS
    1. Module introduction: the cost gate already exists, tokens are what's new
    2. Why a token is the ecosystem's most extreme *usage-based* resource
    3. Hands-on: `bedrock-budget.rego`, added to `cost-policy/`
    4. Hands-on: the per-token cost calculator, integrated into the gate
    5. Cost allocation tagging for the AI workload
    6. Hands-on: a volume change that triggers the budget
    7. On-demand vs. Provisioned Throughput: when to use each, with real numbers
    8. Project: Andes Cargo's *cost gate*, extended to tokens
  7. 07Observability Latency And Evals In Production8 LESSONS
    1. Module introduction: the same vocabulary, new metrics
    2. SLIs for an AI workload: escalation, latency, guardrail block rate
    3. Hands-on: CloudWatch Logs and Metrics for the extractor
    4. Hands-on: the escalation rate metric
    5. What a production eval is, and why it isn't a unit test
    6. Hands-on: the smoke test harness with fixed manifests
    7. The exact limit: why real latency and quality can't be measured here
    8. Project: Andes Cargo's AI workload observability dashboard
  8. 08Capstone The Andes Cargo Genai Extractor8 LESSONS
    1. Capstone introduction: the complete extractor, closed
    2. Architecture review: the full system, two paths
    3. End-to-end walkthrough: the deterministic, cheap path, executed
    4. End-to-end walkthrough: the AI escalation path, mixed and declared
    5. What this guide left representative
    6. The boundary with AI Engineering, closed
    7. What Andes Cargo still needs
    8. Final project: the Andes Cargo GenAI package as a deliverable
Reviews

What students say

These reviews are from enrolled students who completed at least 50% of the course. We moderate reviews only on content grounds (spam, offensive language, personal data), never for being critical or negative.

No approved reviews yet.

Be the first to share your experience!

SEC. 06 · THE STUDIO

Why this studio exists

For decades, building software belonged to technical profiles with years of training, and getting a digital product into the real world took companies months or years. No-code and AI have narrowed that gap, but the knowledge is still held by a few.

Tech Benders exists to open that knowledge up, so business teams and non-technical teams can put their ideas into production with the right technical decisions behind them. AI does what you ask of it. Without a technical base, what it builds may not scale with your company’s ecosystem, and its costs can run away over time.

The team knows the pains of large organizations and the speed at which they have to move. It brings solution architecture, data engineering, product built end to end from back end to front end, and daily work with AI. Software that solves what you need in days, not months, with the cost of AI kept in check.

Founders

The studioRead about Tech Benders →

Write to ushi@techbenders.io

Made with Wislab