Tag
10 posts tagged.
Make a LangGraph agent durable with a checkpointer: attach SqliteSaver in one line, crash the graph on purpose, and resume from disk without re-running the Claude call.
You cannot unit-test an agent like a pure function. Build a two-layer pytest harness: deterministic tool-call assertions plus an LLM-as-judge grader, a frozen eval dataset, and a CI gate. Runnable Python, no eval framework required.
Five reusable agentic workflow patterns, built from scratch in Python with runnable code and a start-simple rule.
A runnable 2026 tutorial for turning a local MCP server into a remote one over Streamable HTTP. Serve tools with FastMCP, test the endpoint with curl and MCP Inspector, validate the Origin header, add a bearer token, then connect Claude. Covers the Mcp-Session-Id requirement and the DNS-rebinding gotcha the docs warn about but most walkthroughs skip.
A runnable LangGraph human-in-the-loop tutorial for 2026: pause an agent mid-run with interrupt(), review the proposed action, then approve, edit, or reject it with Command(resume=...). Includes the checkpointer requirement and the re-run-from-the-top gotcha that breaks most tutorials.
A hands-on LangGraph tutorial for 2026: build the same tool-using AI agent two ways, with the five-line create_agent helper and as an explicit StateGraph you can customize. Fully runnable Python.
A runnable comparison of the Claude Agent SDK and LangGraph in 2026, with the same agent built in both and an honest decision matrix for when each wins.
An AI agent is just a loop: you call a model, the model asks to run a tool, you run it, you feed the result back, and you repeat until the model is done. In this tutorial you build that loop yourself in plain TypeScript against the Anthropic Messages API, no framework. You will wire up two tools (read a file, run a calculation), let the model orchestrate them, add a turn cap and basic guardrails, then verify the whole thing end to end. The result is a small research agent you fully understand and can extend with your own tools.
You do not need to rebuild your product to ship an AI agent inside it. The trick is to expose the service functions you already have, search records, create an order, fetch a customer, as tools, then run a small server-side agent loop that the model uses to orchestrate them. This tutorial wraps an existing service layer as tools, scopes every call to the authenticated user, separates safe read tools from gated write tools, exposes the agent as one authenticated endpoint, and deploys that endpoint to Totalum. Your database, auth, and business logic stay untouched.
Agents fail quietly: a prompt tweak that fixes one task often breaks three others, and manual spot-checks never re-test what used to work. The fix is a frozen eval set scored on every change. This tutorial builds that harness and tracks five metrics that actually catch regressions, task success rate, tool-call accuracy, step efficiency, cost per task, and a safety/guardrail rate. You will assemble an eval set, write a runner that scores each metric, and turn the before/after diff into a regression gate so a change only ships when the numbers hold or improve.
