Comparison · · 1 min read
LangGraph vs the OpenAI Agents SDK
Two ways to write the same supervisor. Compared on control flow, tracing, provider coupling, testing and what each makes hard.
Topic
Agents
13 entries and 3 references.
Part of AI & Models: all AI & Models entries · the AI & Models lens on the map
Entries
Checklist · · 24 checks
Working with Claude, practices that hold up
Prompting, agents and tools, Claude Code, evaluation and safety. The habits that make Claude-based systems reliable, as a checklist you can run against your own setup.
Architecture pattern · · 1 min read
Pattern: the outbox for agent actions
Agents that write to systems of record need the same transactional outbox that event-driven services use. This entry covers the shape and the trade-offs.
Architecture pattern · · 1 min read
Designing a Multi-Agent System for Real-World Use
How to design and run a multi-agent system in production, using the supervisor pattern, with its trade-offs and where human approval belongs.
Deep dive · · 6 min read
Most agent controls do not actually control anything
Six days of notes on supervising autonomous systems, and the same failure shape kept turning up: the control exists, it is documented, and nothing in the running system is bound by it.
Deep dive · · 6 min read
The hard part of building an agent is not making it act. It is making it stop.
Six days of notes on agentic systems, and not one of the fixes that actually worked lived inside the model.
Explainer · · 1 min read
Where human review actually belongs in AI workflows
Why human review needs timing, authority, and context to be useful.
Explainer · · 2 min read
Why agent memory is not one database
Why useful agent memory has to be separated, scoped, and governed.
Explainer · · 1 min read
Why reflection should change the next action
Why reflection is valuable only when it decides whether to revise, retry, escalate, or stop.
Explainer · · 1 min read
Why planning reduces wasted AI actions
Why planning matters when actions have cost, risk, or dependencies.
Explainer · · 2 min read
Why agent behavior is a loop, not a single prompt
Why reliable agent behavior comes from loop design, not a single clever prompt.
Explainer · · 1 min read
Why agents need outcomes, boundaries, and stop conditions
Why agents need clear outcomes, boundaries, budgets, and stop conditions before autonomy.
Comparison · · 2 min read
When to use a chatbot, workflow, or agent
A practical way to choose between conversation, repeatable workflows, and bounded autonomy.
References
- Read
Building Reliable Agents with LangGraph
LangChain · Useful reference · A practical talk on graph-based agent control flow with the failure modes called out.
- Read
OWASP Top 10 for LLM Applications
OWASP · Recommended · The threat list to check any tool-calling agent against before it touches production data.
- Read
Building Effective Agents
Anthropic · Recommended · The clearest written case for simple, composable agent patterns over frameworks.