Skip to content

Writing

From Instrumentation to Infrastructure

AI agents like Claude Code run dozens of CLI commands per session, orchestrating complex multi-step workflows. Without structured knowledge of each tool, the agent guesses flags, calls --help to discover syntax, or retries when the first attempt fails. Each mistake compounds: a wrong flag in step 3 can invalidate everything that follows.

kcp-commands solves this with manifests -- YAML files that encode exactly what an agent needs to use a CLI tool correctly: key flags, preferred invocations, output patterns to strip. The daemon injects the right manifest before each Bash call, turning an uninformed first attempt into a guided one.

kcp-memory adds the second dimension: episodic memory. Every session is indexed. Every tool call is logged. The agent can search what it did last week, recover the reasoning from a delegated subagent, and see which manifests are actually working in practice.

Together they make Claude Code measurably smarter: 33% of the context window recovered, --help calls eliminated, and an agent that learns from its own history instead of starting from zero every session.

The latest addition closes the loop: the tools now learn from their own performance. Every Bash call produces an outcome signal. kcp-memory tracks retry rates, help-followup rates, and error rates per manifest -- surfacing which ones are guiding the agent well and which ones are steering it wrong. The highest-failure manifests have already been rewritten based on the data. The infrastructure measures its own effectiveness and improves.

kcp-commands v0.9.0 and kcp-memory v0.4.0 were passive observers. They watched what Claude did, logged it, made it searchable. Useful, but limited. The tools had no opinions about their own data.

The work since then -- through kcp-commands v0.18.0 and kcp-memory v0.18.0 today -- has been about a different question: what happens when the tools know what to ignore, can measure their own quality, and maintain themselves?

From Capable to Trustworthy: How KCP Evolved from Discovery to Governance

AI agents are getting remarkably good at doing things. They read code, traverse APIs, generate summaries, and execute multi-step plans across sprawling codebases. What they are still bad at is knowing what they should not do.

Today, an agent dropped into a new repository does the equivalent of walking into a library and reading every book on every shelf before deciding which one is relevant. This is expensive, slow, and -- in environments where some shelves contain confidential material -- genuinely dangerous.

The Human in the Loop — at Design Time

Tim O'Reilly posted something this week about craftsmanship in the AI age. The question he was circling: how do you maintain quality standards when agents are doing the work?

The default answer in the industry is: keep the human in the loop. For every meaningful decision, have a human review before proceeding.

That model contains a fatal flaw.

The agents were forgetting everything they discovered

Something felt off.

I'd been using the Task tool heavily — delegating research tasks to Claude subagents, letting them explore codebases, map dependencies, surface patterns. The results coming back were good. But when I'd start a new session and ask about the same topic, there was no trace of that prior investigation. The context window had reset, and the episodic memory layer — kcp-memory — wasn't helping.

Here's what that looked like in practice: I'd asked a subagent to map the co-events repository ecosystem earlier this week. It came back with a clear picture — co-events is the CatalystOne HRIS event-sourcing platform, seven repos, with a dependency chain running from co-event-typelib through co-event-sdk into co-analytics-vanilla (which, by the way, uses Neo4j with APOC, not SQL — a non-obvious choice). Two days later, I started a new session, asked about co-events architecture, and got a blank stare. The agent had no idea any of this had been mapped. It treated the question as entirely novel.

My first hypothesis was handover loss. Maybe something was being compressed or summarized too aggressively when agents returned their findings. Maybe the model transition (often Opus for the delegated tasks, Sonnet for the orchestrating session) was dropping context. That felt plausible, and a little unsettling.

The real cause was more concrete — and more fixable.

The Autonomous Agentic Web Needs a Foundation Layer

The Foundation Layer of the Agentic Web — Capable models are not enough

Something is being assembled right now, mostly without a name for it.

Production pipelines where agents write code, run tests, and open pull requests. Compliance workflows where agents check controls, gather evidence, and escalate to humans when something needs a decision. Developer rigs where an agent calls a tool, the tool delegates to a sub-agent, the sub-agent calls an API, and the result flows back up the chain.

The models are capable. The tooling is solid. The use cases are real.

What we are building — collectively, across hundreds of teams and projects — is an autonomous agentic web. And like the original web, it will only become useful when the pieces can talk to each other reliably. We are not there yet. The reason is interesting.

I haven't typed apt install in three months

Last Tuesday I needed a file-watch service on my workstation. The kind of thing that monitors a directory and triggers a reindex when something changes. Normally that means ten minutes of reading systemd docs I've read fifty times before, copying a unit file from somewhere, adjusting paths, running systemctl --user enable, checking journalctl for the inevitable typo in ExecStart.

Instead I described what I wanted. Claude Code found an existing service on the machine, used it as a template, wrote the unit file, enabled it, started it, checked the logs, confirmed it was running, and updated the knowledge manifest so future sessions know the service exists. I approved three actions. The whole thing took about ninety seconds.

I haven't typed apt install in three months. Not because I stopped installing software — I install more than ever. But the person typing the commands isn't me anymore.

The Code Was Never the Moat

Bruce Perens says the entire economics of software development are dead. He said this in response to a story about a developer using Claude to rewrite a Python library from LGPL to MIT in a few hours. 130 million monthly downloads. 1.3% textual similarity to the original. A clean room implementation, or close enough that the legal distinction barely matters anymore. The whole thing took roughly five days.

Perens is half right. The economics of code as artifact are dying. The economics of knowing what to build are stronger than ever.

The Front Door and the Filing Cabinet: A2A Agent Cards Meet KCP

The Front Door and the Filing Cabinet: Composing A2A and KCP in Multi-Agent Systems

Multi-agent systems need two kinds of identity. The first answers "who is this agent and how do I call it." The second answers "what knowledge does this agent have and who is allowed to see each piece of it." Google's A2A protocol handles the first. KCP handles the second. They are not competitors. They are different layers of the same stack.

This post started as that explanation. Then, the same day it was published, we built four simulators and 150 adversarial tests against the spec. The tests found 8 concrete gaps. Those gaps are now driving KCP v0.7. The full story follows.