Notes on agents, software, and work.
Systems / August 29, 2026 / 10 min read
Multi-agent orchestration patterns: choose by control and failure propagation
Choose multi-agent orchestration patterns by workload, routing, state, authority, verification, cost, and recovery instead of labels alone.
Systems / August 28, 2026 / 10 min read
Autonomous agents and multi-agent systems: when one agent is enough
Autonomous agents and multi-agent systems differ by topology; the right choice depends on workload independence, specialization, control, cost, and recovery.
Systems / August 27, 2026 / 11 min read
Open source AI harness: inspect the architecture before you choose
An open-source AI harness earns a shortlist through inspectable state, authority, tracing, recovery, portability, maintenance, and cost.
Systems / August 26, 2026 / 10 min read
Human in the-loop vs human on the-loop: where control sits
HITL pauses selected actions before execution; HOTL supervises more autonomous execution, while undo cost determines where a human gate belongs.
Systems / August 25, 2026 / 10 min read
AI agent frameworks open-source: seven workload fits
Open-source AI agent frameworks fit different workloads; compare eight choices by execution type, use case, license, and GitHub popularity.
Systems / August 16, 2026 / 10 min read
How to choose an open-source agentic AI framework by its control contract
An open-source agentic AI framework earns its place through durable state, scoped tool authority, approval gates, tracing, evals, and crash recovery.
Systems / August 16, 2026 / 10 min read
Best open source agent harness: choose by control, recovery, and workload
Choose an open-source agent harness by context load, carried judgment, reversibility, state, approvals, recovery, maintenance, and operating cost.
Systems / August 16, 2026 / 11 min read
How to build an agent harness backward from failure
Build an agent harness from failure modes outward, with bounded authority, durable state, independent checks, monitoring, and recovery.
Systems / August 16, 2026 / 10 min read
Harness engineering framework: six control responsibilities for reliable agents
A harness engineering framework assigns context, execution, permissions, evaluation, recovery, and tracing to explicit controls.