News & guides
Building Your First Agent: A Loop, Three Tools, One Guard
Skip the framework. An agent is a while loop over a tool-calling model. Here is the minimum that works, and the four things that break it first.
· 8 min readEvaluating Agent Reliability: Past the Single Pass Rate
An agent that works four times in five is not 80 percent useful. Here is how to measure agent reliability in a way that predicts production behaviour.
· 10 min read
Human in the Loop: Designing Approval That Actually Works
Most approval gates fail not from too little oversight but from too much. Here is how to design agent checkpoints people actually read before clicking yes.
· 9 min read
Long-Running Agents: Durability, Compaction and Restarts
An agent running for hours hits limits a chat never does: context exhaustion, process restarts, stale state. The patterns that keep long jobs alive.
· 9 min read
MCP Explained: One Protocol Instead of N×M Integrations
The Model Context Protocol standardises how agents connect to tools and data. What it solves, how it works, and when a plain function call is enough.
· 8 min readMulti-Agent Systems: When They Help and When They Hurt
Two credible teams published opposite advice on multi-agent architectures within a day of each other. Both were right, because the answer depends on the task.
· 9 min read
Prompt Engineering for Coding Agents Is Mostly Context Engineering
Clever phrasing barely moves the needle. What actually improves agent output is what you put in front of it, in what order, with what constraints.
· 8 min read
Prompt Injection: Why Your Agent Is a Confused Deputy
An agent that reads untrusted content can be instructed by it. The fix is not a better prompt — it is treating the model as an untrusted client.
· 8 min readReAct vs Plan-and-Execute: Two Ways to Run an Agent Loop
ReAct decides one step at a time. Plan-and-execute commits to a plan first. The choice changes cost, latency, recoverability and how failures look.
· 9 min readStructured Outputs: Getting JSON You Can Actually Parse
Asking a model for JSON and hoping is a bug waiting to happen. Schema-enforced outputs, and the validation you still need around them.
· 7 min readSubagents and Delegation: When Splitting an Agent Helps
Subagents buy parallelism and a clean context window, and cost you shared understanding. Here is when that trade is worth making, and when it is not.
· 9 min read
Tool Calling: The Feature That Turns a Model Into an Agent
Tool calling is how a model asks your code to do something. Understanding the handshake — and designing good tools — is most of what makes an agent reliable.
· 9 min readReady to try it?
Every model behind one key. Start free and upgrade when it sticks.