Part 8 of 12 · 2 min read
Mistakes that pick the wrong structure
Common mistakes, and what the example does not do.
Mistakes that pick the wrong structure
- Choosing by popularity instead of by capability.
- Believing that a checkpoint makes side effects exactly-once.
- Treating a vendor's framework comparison table as neutral.
- Passing the whole history on every handoff without measuring the cost.
- Comparing frameworks on a toy task that none of them is stressed by.
- Depending on framework types throughout the codebase, so switching is a rewrite.
- Not pinning versions, so a change in the framework changes behaviour.
What the example does not do
About this example What the example does not do
- No framework code in this module's own experiments. Parts 1 to 7 show paradigms, not LangGraph, the Claude Agent SDK or the OpenAI Agents SDK; part 9 maps the vocabulary onto two of them without running either.
- Crashes are only at one point, after the work and before the record. Real failures also happen mid-call and in the store.
- A scripted model. There are no model errors and no variation in the number of steps.
- No storage cost. A checkpoint is free here; in practice it has latency and size.
- Token sizes are assumed and the handoff model ignores caching (module 1 of this level shows that caching changes the comparison).
- Optional real experiment: implement the same two-tool task in two frameworks, kill the process halfway, resume, and count repeated tool calls and tokens.
Check yourself
A framework offers a graph, a loop and handoffs. How do you choose between them?
Show answer
By the hardest requirement: durable multi-day runs with approvals suggest a graph with a store; a tool-using coding agent suggests an SDK built around its loop; several specialists suggest handoffs or agents as tools.
For the curious What this module cannot tell you
It measured no real framework. The simulation shows only the shape: a plain loop that restarts after a crash repeats work, a graph that resumes from a checkpoint does not, and an idempotency key stops a repeated side effect. Framework facts checked on 31 October 2026; they will drift.
What you will use daily at work
| Practice | What it looks like |
|---|---|
| Put the framework behind your own interface | Model calls, tools and state, so switching means rewriting an adapter. |
| Compare capabilities | Persistence, deployment, guardrails, tracing. |
| Re-check on a schedule | Treat any comparison table as dated. |