Async and Await in C#: Writing Non-Blocking Code Correctly
Use async and await in C# correctly: what Task really is, ValueTask, ConfigureAwait, async void, cancellation tokens, and Task.WhenAll patterns.
Blog
Tech Insights & Engineering Notes
AI systems, platform engineering and architecture. Lessons from 13+ years of building at scale.
-
-
LINQ in C#: Querying Collections the Idiomatic Way
Write idiomatic LINQ in C#: query vs method syntax, deferred execution, IEnumerable vs IQueryable, multiple enumeration traps, and…
-
Object-Oriented C#: Classes, Inheritance, and Interfaces
Master object-oriented C#: classes, properties, constructors, inheritance, abstract classes, interfaces, records, and when composition beats inheritance.
-
Jev AI Model: The Fastest Adopted Model in AI Gateway History
Jev reached nearly 13% of paid AI Gateway teams unusually fast. Here is what that adoption curve means…
-
Tool Sandboxing and Permission Models: Least Privilege for Agents
Tool sandboxing and permissions for AI agents: least privilege, role tiers, capability isolation, and sandboxes that actually limit…
-
Prompt Injection in Agents: Indirect Attacks Through Tools and Data
How prompt injection in agents works through tools and data, and the defense-in-depth stack: least privilege, output validation,…
-
Agent State Persistence: Checkpointing and Resumable Workflows
Agent state persistence explained: checkpoints, resumable runs, replay safety, versioned state schemas, and how to resume without repeating…
-
Cost Control: Token Budgets, Caching, and Model Routing
AI agent cost control: token budgets, prompt caching, model routing, and context discipline, measured as cost per successful…
-
Reliability for Agents: Retries, Timeouts, Fallbacks, Circuit Breakers
Reliability for agents: the failure taxonomy plus retries, timeouts, fallbacks, circuit breakers, idempotency, and bounded execution that keep…
-
Deploying AI Agents: Architecture and Patterns
Deploying AI agents in production: execution boundary, gateway, orchestrator, tool gateway, state stores, queues, workers, and sync vs…
-
Tracing Agent Runs: LangSmith, Langfuse, and OpenTelemetry
Tracing agent runs: spans for model calls, tools, retrievals, and state changes in LangSmith, Langfuse, or OpenTelemetry, without…
-
How to Evaluate AI Agents: Task Success, Trajectory, and Cost
Evaluate AI agents beyond answer quality: task success, tool and argument correctness, trajectory quality, cost per successful task,…
-
Context Window Management: Summarization, Compression, Pruning
Context window management for AI agents: budgeting, summarization, compression, and pruning, so agent runs keep the right state…
-
RAG for Agents: Retrieval That Adapts to the Task
RAG for agents vs chatbot retrieval: task-aware queries, grounding, access control, freshness, and retrieval as a tool the…
