AI and agents
AI and agents
Design, operation and evaluation of artificial intelligence systems and agents.
Architecture and operations
Patterns for coordinating and operating agent systems.
Explore Subcategory · 4 articlesAgentic engineering
Design of flows, context and software factories with supervisable agents.
Explore Subcategory · 2 articlesContext and memory
How to select, govern and retrieve information for agents.
Explore Subcategory · 2 articlesTools and controls
Integrations, permissions and limits for safe actions.
Explore Subcategory · 2 articlesQuality and observability
Evaluation, traces and evidence of agent behavior.
ExplorePublications
Articles in this category
Harness engineering for AI agents
The operational layer that connects goals, tools, memory and controls to make an agent governable.
Architecture and operationsRead articleLoop engineering: reliable cycles for AI agents
An explicit cycle of plan, action and evaluation keeps autonomy from turning into unproductive repetition.
Architecture and operationsRead articleContext engineering: the right information at the right time
Selecting, structuring and updating relevant context improves agents’ accuracy, cost and traceability.
Context and memoryRead articleTool engineering: tools an agent can use safely
Tools are not neutral extensions: they require contracts, validation and interpretable results.
Tools and controlsRead articleMemory engineering: useful memory without piling up noise
An agent’s memory needs policies for writing, retrieval, retention and forgetting.
Context and memoryRead articleOrchestrating multi-agent systems
Coordination turns specialized agents into a system that can split, verify and integrate complex work.
Architecture and operationsRead articleGuardrails and permissions for AI agents
Autonomy is useful when policies, permissions and limits are applied before an action.
Tools and controlsRead articleEvaluating AI agents: from demos to operational evidence
Evaluating an agent means reviewing result, process, security and cost under representative scenarios.
Quality and observabilityRead articleHuman-in-the-loop: oversight that improves decisions
Human review works when it is placed at the right point of risk, with evidence and actionable options.
Architecture and operationsRead articleObservability and tracing: making autonomy visible
Traces, metrics and events connect each result to the execution that produced it.
Quality and observabilityRead articleDark factories: what an experiment reveals about agents and architecture
Automating code writing and testing does not, on its own, automate architectural judgment. A case reported by HumanLayer helps show where human review is worth keeping.
Agentic engineeringRead articleA 4-gate workflow: reduce uncertainty before coding with agents
Separating problem, research, architecture and slices turns a broad request into reviewable decisions before an extensive diff is generated.
Agentic engineeringRead articleContext for agents: keeping focus through deliberate compaction
A large context window does not guarantee that an agent uses all the information equally well. Selection and summarization must preserve evidence and useful state.
Agentic engineeringRead article12 Factor Agents: patterns for agents that reach production
HumanLayer’s 12 factors propose agents built from explicit software, structured tools, controlled state and human pauses when needed.
Agentic engineeringRead article