You no longer carve software through the pain an sweat, you pour it now.

Should I release this tomorrow?

Long-read about maintaining proactive agents in production for the past ten months. 1. Wakeup storms are the worst enemy of the infrastructure. Booting a full agent sandbox on every Slack message, webhook, poll tick turns sandboxes into a furnace. Not everything needs a sandbox. 2. Autonomous agents with async replies love doing work nobody reads. They generate summaries, scripts, status checks and status updates for themselves. In my own usage this week, ~17% of all tokens went to background summaries and offline heartbeats I will never read. 3. Month-6 context is very different from Day-1 context. In a fresh setup everything works as intended, but after half a year of accumulating skills, project boards, standing instructions, safety rules, SOPs, a casual 1-line question might live agent watch three contradicting rules at the same priority, "always delegate", "always answer first", "always start with a plan", very easy to deadlock. 4. No agent goes without this. Safety must live far far outside of what agent can reach. Prompt instructions can never act as a security boundary. 5. Prompts rot faster than the models improve. We did some ablation studies across model generations, and the models are eating harnesses faster and faster. 6. Your agent must see what your user sees, otherwise it's a recipe for frustrated user and a confused agent. 7. There's no perfect sandbox solution, at this stage most of them have drawbacks at one or another layer, supervisors are not perfect, memory leaks. Agents will act as if the sandbox has infinite compute, even a tiny lightweight check might grind entire workspace to a halt at certain scale.

6/ TraceQuest is Open Source, runs on your machine and sends no telemetry. github.com/viktor-com/traceq…

2/ TraceQuest indexes sessions from Claude Code, Codex, Cursor, OpenCode, Grok, Droid. You can configure TraceQuest to collect session from your fleet over SSH, as well as Cursor Cloud.

Incidentally, this is also best Grok 4.7 computer use to date, just saying ;)

We're prompting agents, but we are not the same

A skill that turns any agent/harness into ultracode from Claude. The agent will: - Split your work into steps - Arrange them into a graph (could be cyclic) - Orchestrate shared state on the filesystem - Continue running the graph until it's fully done. The largest run I ever had was ~1400 nodes. github.com/av/skills/tree/ma…

It started with one simple chat window. Then you ran one session, then a few at once. Now you talk to dozens of agents all day. How do you scale that without losing track of them?

That was good to see in the morning

Is there such thing as opting out of A/B tests with an LLM provider?

- 98% of my agent sessions are run by other agents, not me - about a third of my sessions are agents reviewing other agents work - a typical session makes 123 tool calls Personal trace intelligence

Sea glass meant to be the actual UI there. You interact with stones, and your agents do things. As simple as three seashells. av.codes/stones

Claude: I wrote some tests to simulate an environment where this bug never existed Me: oh

My agentic coding went from a chatgpt window to an agentic fleet It'll be an armada soon

music is "Digital Lemonade" by Kevin MacLeod

I don't recognize Opus 5.5 behavior today.

A colleague asked me today "what is your typing speed?", I replied "In tokens per second?" Turns out: Claude Fable 5.1: 58 tokens/s Me: 1.64 tokens/s docs.viktor.com/human-vs-llm