Most AI systems have a hard boundary between the instructions they follow and the work they do. Developers write prompts; the AI executes them. If the prompts are wrong, a human fixes them. We built an agent that fixes its own prompts.

The Skill Evolver is the third agent in our six-agent autonomous self-improvement pipeline for nomadically.work. Its scope is precisely defined: it can edit skill files, commands, hooks, CLAUDE.md, and memory files. It cannot touch application source code — that's the Code Improver's job. This agent improves the instructions that all other agents follow.

Five research papers informed its design, curated from the VoltAgent/awesome-ai-agent-papers collection. Each one solved a different aspect of the self-modification problem.

Every Claude Code session leaves a trace — tool calls made, files read, edits applied, errors encountered, and ultimately a score reflecting how well the task was completed. Most systems discard this history. We built an agent that mines it.

The Trajectory Miner is the first agent in our six-agent autonomous self-improvement pipeline for nomadically.work, a remote EU job board aggregator. Its job: analyze past sessions, extract recurring patterns and reusable skills, and feed structured intelligence to the rest of the team. It writes no code. It produces raw material that other agents — the Codebase Auditor, Skill Evolver, and Code Improver — consume.

The design draws from four research papers, curated from the VoltAgent/awesome-ai-agent-papers collection. Here is what each paper contributes and how we translated academic ideas into a working system.

An autonomous improvement system without verification is just autonomous damage. The Code Improver can write fixes. The Skill Evolver can edit prompts. But neither should be trusted to judge its own work. That's why the Verification Gate exists.

The Verification Gate is the fifth agent in our six-agent autonomous self-improvement pipeline for nomadically.work. It validates every change made by the Skill Evolver and Code Improver before those changes are accepted. It never modifies code or skills — it only reads, checks, and reports a verdict.

Five research papers shaped its design, curated from the VoltAgent/awesome-ai-agent-papers collection. The common thread: autonomous systems need calibrated self-awareness about the quality of their own outputs.

Running AI agents in a real codebase means solving three intertwined problems at once: planning and quality gates (so agents don't drift), observability (so you know what's working), and orchestration (so multiple agents divide work without clobbering each other). In nomadically.work — a remote EU job board with an AI classification and skill-extraction pipeline — these problems are solved by three complementary systems: BMAD v6, Langfuse, and Claude Code Agent Teams. This article explains how each works and how they compose.

Trigger.dev is a serverless background job platform that lets you run long-running tasks with no timeouts, automatic retries, queue-based concurrency control, and full observability. Unlike traditional job queues (BullMQ, Celery, Sidekiq), Trigger.dev manages the infrastructure — you write TypeScript tasks and deploy them like functions.

This article covers the platform end-to-end: architecture, task authoring, the queue fan-out pattern, MCP server integration for AI assistants, agent skills/rules, and a production case study of a TTS audio pipeline.

We built an Architect agent — a fully autonomous code reviewer powered by Claude Opus 4.6 — that explores a repository, runs audits, and produces a comprehensive architecture report. One command, zero human intervention, a professional-grade review in under 10 minutes.

This article covers how the agent is structured, how it leverages Anthropic's agentic tool-use loop, and what we learned shipping it.

We needed a pipeline that ingests hundreds of job postings from ATS platforms (Greenhouse, Lever, Ashby), enriches each posting with structured data from their public APIs, and then classifies whether a job is a fully remote EU position — all running on Cloudflare's edge with zero GPU costs.

This article walks through the architecture and implementation of process-jobs, a Cloudflare Python Worker that combines langchain-cloudflare with Cloudflare Workers AI, D1, and Queues to build a production classification pipeline.

Introduction​