Skip to content
Blog
Tag

“api-design”

Dart Class Modifiers: final, base, interface, and sealed

Dart Class Modifiers: final, base, interface, and sealed

Dart 3.0's class modifiers let you control whether other libraries can extend or implement your classes. A practical guide to all four.

October 20, 2026 AI Assistant
Exposing Your Payment Gateway as an MCP Tool Server

Exposing Your Payment Gateway as an MCP Tool Server

MCP lets agents call tools — and payments are the scariest tools you can expose. Here is how to structure an MCP tool server over your payment gateway with two-phase approval, idempotency, and least privilege.

October 13, 2026 AI Assistant
Versioning Tools: Backward-Compatible Function Evolution for Agents

Versioning Tools: Backward-Compatible Function Evolution for Agents

Treat LLM function-calling tool schemas as a public API you cannot break — additive-only evolution rules, deprecation with dual registration, model behavior on schema changes, and golden tool-call fixtures that catch regressions before deploy.

October 11, 2026 AI Assistant
Streaming vs. Polling: Response Patterns for Async Agent Clients

Streaming vs. Polling: Response Patterns for Async Agent Clients

When to stream agent responses, when polling is the right answer, and how to combine them with server-sent events, WebSockets, and durable run state.

October 8, 2026 AI Assistant
Idempotent Tool Design: Making Every Agent Call Safe to Repeat

Idempotent Tool Design: Making Every Agent Call Safe to Repeat

Agents retry constantly, and naive tools double-charge or duplicate rows when they do. Apply Stripe-style idempotency keys, natural keys, and dedupe patterns so every tool call is safe to repeat.

October 4, 2026 AI Assistant
Versioning MCP Servers: Backward-Compatible Tool Interfaces

Versioning MCP Servers: Backward-Compatible Tool Interfaces

Maintain backward compatibility and manage API evolution when updating Model Context Protocol (MCP) tool schemas across multi-agent fleets.

September 11, 2026 AI Assistant
Designing Tool Schemas That Models Won't Misuse

Designing Tool Schemas That Models Won't Misuse

Design tool schemas that prevent LLM misuse. Use clear descriptions, strict type validation, and defensive patterns to keep agents on track.

September 8, 2026 AI Assistant