post
AI agent frameworks: what they give you, and what they don't
What an AI agent framework actually provides, how crewAI, LangGraph, AutoGen, and the provider SDKs differ, and the infrastructure none of them ship.
notes on running a team of AI agents
what I learned building Aldena: roles, handoffs, reviews, and where a single coding agent runs out of road.
post
AI agent orchestration in production: what actually breaks
How I orchestrate AI agent teams in Aldena: why hierarchy beats a flat swarm, how work travels, what shared memory and approval gates do, and where tokens go.
post
AI-assisted development: what changed on my team
An honest report from building Aldena with its own agent teams: the agents, the guardrails, the review gate that stays human, and where the money goes.
post
AI coding agents: direct and verify, don't ask and paste
A practical guide to getting real work out of AI coding agents. Plan before you delegate, scope small, review with suspicion, and trust tests over confidence.
post
claude opus 4.5 benchmarks: which numbers predict quality
opus 4.5's reported scores, read by someone who runs agent teams on these models: which benchmarks predict delegated work, and which ones are noise.
post
claude sonnet 5 benchmarks: what the scores mean for agents
sonnet 5 beats opus 4.8 on terminal work and edges it on knowledge work at 40 percent less. i map each launch benchmark to the agent job it actually predicts.
post
Enterprise AI agents pay off when they become teams
The business case for enterprise AI agents is teams, not smarter assistants. Where the value shows up, what governance has to exist, and how I would start.
post
How to build an AI agent team that ships one deliverable
A working AI agent team needs real roles, a coordinator that only delegates, bounded channels, shared memory, and cost-tiered models. Here is the build.
comparison
llama vs gpt vs claude: pick a model per role, not a winner
an open vs closed model comparison for choosing what runs your ai agents: cost, latency, eval deltas, and why per-role assignment beats one champion.
post
Multi-agent platforms: what to demand before you buy one
A buyer's guide to multi-agent platforms. How a platform differs from a framework, what to test in orchestration and permissions, and where guardrails go.
post
Multi-Agent Systems: How They Work and Who Needs One (2026)
How multi-agent systems decompose work, coordinate, and fail in production, plus a plain test for when a single agent is the cheaper, better call.
post
what it actually takes to self-host an always-on ai agent
the real bill of materials behind a self-hosted ai agent: gateway, sandbox, memory, browser, auth, and cost. and what changes when that job is someone else's.
post
what is a multi-agent system? definition and components
a multi-agent system is several autonomous agents coordinating in a shared environment. the definition, the components, the use cases, and the failure modes.