AI AgentsAgent Prompt Versioning: Treat Prompts Like Deployed Code
A prompt edit is a production change with no compiler and no stack trace. How to give prompts a stable identity, trace them, roll them out and roll them back.
ReadNotes on models, agents, and what inference costs
Practical writing for developers building with large language models — how they work, how to pick one, and how to keep the bill predictable.
Agents, tool calling, and the loop that makes them useful.
AI Agents
AI AgentsAgent Queueing and Backpressure: When to Say No
An unbounded queue in front of an agent fleet hides overload until every task is stale. Queue design, backpressure signals and shedding work on purpose.
Read
AI AgentsAgent Regression Suites: Catching Breaks Before Users Do
A prompt edit can silently break a workflow that worked yesterday. Here is how to build a regression suite for an agent that actually blocks merges.
Read
AI AgentsAgent Resumption Patterns: Restarting Without Starting Over
Picking up a stopped agent run safely: why it stopped changes how you resume, and why the world may have moved while the agent was not looking.
ReadAI AgentsAgent Self-Correction: When Reflection Helps and When It Does Not
Asking a model to check its own work sometimes fixes real errors and sometimes invents new ones. What separates the two, and how to build for it.
ReadAI AgentsAgent Shell Access Safety: Giving a Model a Terminal
A shell tool is the most useful and most dangerous thing you can give an agent. How to grant it without handing over the whole machine.
ReadAI AgentsAgent State Machines: Constraining the Loop That Wanders
Giving an agent explicit states and legal transitions cuts wandering and makes failures debuggable. What it buys, what it costs, and when it is overkill.
ReadAI AgentsAgent Task Decomposition: How Small Is Small Enough?
Breaking work into subtasks is the standard fix for agents that flail. Here is how to size the pieces so decomposition helps instead of adding overhead.
Read
AI AgentsAgent Test Harnesses: Testing a System That Is Not Deterministic
Agents fail intermittently, so a single passing run proves nothing. How to build a harness that measures rates rather than checking assertions.
ReadAI AgentsAgent Timeout Strategies: Bounding a Loop That Cannot Stop
An agent has no instinct for when it has taken too long. The four limits worth setting, where to put them, and how to fail without losing the work.
ReadAI AgentsAgent Token Budgets: Capping Spend Without Capping Capability
An unbounded agent can spend arbitrarily much on one task. How to set budgets that stop runaway sessions without killing legitimate long ones.
ReadAI AgentsAgent-to-Agent Protocols: What They Solve and What They Do Not
Protocols for agents talking to other agents are arriving. Here is the problem they address, how they differ from MCP, and when you genuinely need one.
ReadShowing 13–24 of 74 articles