Topic

Orchestration

Coordinators, workers and scheduling, and what keeps many agents useful at once.

All technical writing

2026

  1. Deterministic wakes, reports, and memory for long-running agents

    How deterministic code can own wakes, reports and memory for long-running agents, with event batching and cold resets timed by the prompt-cache lifetime.

    SelectedOrchestrationMemoryAgent systems

  2. Treating a sixteen-agent build like a production system

    Running a sixteen-lane agent build like a production system: reviewing specifications at their seams, a rival design as adversarial review, and measuring friction from session logs.

    OrchestrationAgent systemsPerformance

  3. Inversion of control for agent pipelines and MCP servers

    Keeping a long agent job's goal and state in SQLite, splitting perception from judgment, and moving an MCP server's reasoning into the user's own assistant host.

    Agent systemsOrchestrationPlatforms

  4. Messaging live coding agents without confusing delivery with completion

    How a local MCP broker lets live Codex, Claude Code and hosted agent sessions message and wake each other, with journalled writes that never resend an unknown outcome.

    Agent systemsOrchestrationInterfaces

  5. Managing worker agents with service state instead of prompt rules

    Why a coordinator agent's duties to its workers belong in service state: stored waits with clocks for worker questions, a computed capacity line, and workers that own whole areas.

    SelectedOrchestrationAgent systems

  6. Getting an agent coordinator to brief like a product manager

    Why prompt fixes do not hold an agent coordinator's voice across hundreds of turns, and how to split rules between prompt, tool descriptions, state and services so the prompt stays short.

    SelectedOrchestrationAgent systemsInterfaces

  7. Coordinating parallel coding agents in code, not prompts

    Why parallel coding agents need coordination in code: admission control for one sandbox, reviews pinned to a source revision, and decisions journaled before acting.

    SelectedOrchestrationAgent systemsRuntime

  8. From a single loop to a coding-agent harness

    What running a minimal coding agent forces into its harness: sub-agents as context isolation, resource-keyed parallel tool calls, and deterministic course correction.

    Agent systemsRuntimeOrchestration