Index listing of all 13 items tagged with #agents.
Work that spans sessions, people and agents needs more than a record of what happened. It needs what is currently true, and someone who owns the next step.
The difference is not tool use or sophistication. It is whether your program fixed the sequence in advance or the model gets to choose what happens next.
Seven named points where a person decides something before an AI agent acts, and the five-minute version that makes them usable.
Skill vs prompt vs agent: a prompt is input for one run, a skill is a reusable versioned package, an agent picks its own next step. Where system prompts fit.
An agent harness is the software that turns a language model into an agent: the loop, the tools, the context and the limits. What each part does, with examples.
Bounded autonomy lets an AI agent choose its own next step while limits it cannot change decide what it may do. The four bounds, and why a prompt is not one.
Agentic systems become trustworthy when they can pause, verify, and escalate instead of only continuing.
In multi-agent systems, the handoff protocol is the most critical design element.
The debugging session that taught me why observability is not optional in orchestration, and what I now look for first when a multi-agent system misbehaves.
A practical deck on agent architecture, control points, and reliability patterns.
A staged deck on assembling AI systems from intent framing to reliable execution loops.
A walk through agent orchestration patterns, handoff protocols, and building reliable multi-agent systems.
An engineering-focused deck on building agentic systems with explicit control points, checks, and observability.