INTERMEDIATE · 8 MODULES · 64 LESSONS

Agents with Real SDKs: Claude Agent SDK and OpenAI Agents SDK

Build the same agent with Anthropic's SDK and OpenAI's, with human approval and cost control, and use real data to choose the one that fits you.

For you if
You already understand how an agent loop works and want to move it onto a real SDK.
By the end
You'll know how to control permissions and approvals, evaluate two SDKs on the same cases, and deploy the agent behind an API.
You need
Intermediate Python with async and an API key with credit; to compare, keys from both Anthropic and OpenAI.
  1. 01The Provider's Loop Versus Your Own8 LESSONS
    1. Introduction to the guide: from a simulated loop to a real SDK
    2. What an agent SDK actually does
    3. The loop you already know
    4. What you gain and what you give up
    5. Environment, keys, and spending limits
    6. The Andén Norte case
    7. Versions, documentation, and model names
    8. Project: the Andén workspace and the domain tests
  2. 02Manual Tool Use in Both APIs8 LESSONS
    1. Introduction to module 2: Manual tool use in both APIs
    2. The Messages API tool loop
    3. The Responses API function calling loop
    4. Two wire formats side by side
    5. A provider-neutral tool registry
    6. The Anthropic Tool Runner
    7. Limits, errors, and what hurts in a manual loop
    8. Project: the Andén manual agent on both APIs
  3. 03Claude Agent SDK Foundations8 LESSONS
    1. Introduction to Module 3: Claude Agent SDK foundations
    2. Installing and your first `query()`
    3. Reading the message stream
    4. Built-in tools, `allowed_tools`, and `cwd`
    5. Multi-turn with `ClaudeSDKClient`
    6. Sessions: resume and fork
    7. System prompts, settings, and model choice
    8. Project: the Andén policy assistant
  4. 04Claude Agent SDK, Control and Extension8 LESSONS
    1. Introduction to Module 4: From an Assistant That Reads to an Agent That Acts
    2. Custom Tools with an In-Process MCP Server
    3. Connecting External MCP Servers
    4. Permission Modes and Rules
    5. Human Approval with `can_use_tool`
    6. Hooks for Audit and Policy
    7. Subagents
    8. Project: The Andén Agent That Refunds Under Control
  5. 05OpenAI Agents SDK, foundations8 LESSONS
    1. Introduction to module 5: OpenAI Agents SDK, foundations
    2. Installation, Agent and Runner
    3. The run loop and the result
    4. Function tools
    5. Typed context and structured output
    6. Sessions
    7. Streaming and model settings
    8. Project: the Anden assistant on the Agents SDK
  6. 06OpenAI Agents SDK, Orchestration and Control8 LESSONS
    1. Introduction to Module 6: OpenAI Agents SDK, Orchestration and Control
    2. Handoffs
    3. Agents as Tools Versus Handoffs
    4. Input and Output Guardrails
    5. Human Approval and Tool Guardrails
    6. MCP Servers and Hosted Tools
    7. Tracing
    8. Project: Andén Triage and Refunds
  7. 07One Agent, Two SDKs8 LESSONS
    1. Introduction to Module 7: One Agent, Two SDKs
    2. Mapping Concepts Between the Two SDKs
    3. A Thin Common Interface
    4. A Shared Eval Set
    5. Measuring Cost per Run
    6. Turns, Latency, and Budgets
    7. How to Choose
    8. Project: The Side-by-Side Report
  8. 08Deployment and Final Project8 LESSONS
    1. Introduction to Module 8: Opening the Branch
    2. Serving the Agent Behind FastAPI
    3. Containers and the Agent SDK Runtime
    4. Secrets, Limits and Observability
    5. Persistent sessions in production
    6. Failure modes and recovery
    7. The Final Project Brief
    8. Final Project: The Andén Norte Assistant, End to End
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