---
title: Four weeks from user to engineer
description: Reading builds vocabulary; practice builds judgment. One project per week, each producing something you can show. Tick items as you go; progress feeds the dashboard.
author: Asem Abdo
course: Agentic Engineering
lesson: Roadmap and sources
url: https://openplanr.dev/learn/agentic-engineering/roadmap
updated: 2026-10-17
related:
  - https://openplanr.dev/learn/agentic-engineering/lab.md
  - https://openplanr.dev/learn/agentic-engineering/glossary.md
---

# Four weeks from user to engineer

By [Asem Abdo](https://www.linkedin.com/in/asemabdo/) · Updated 2026-10-17

*Roadmap and sources*

Reading builds vocabulary; practice builds judgment. One project per week, each producing something you can show. Tick items as you go; progress feeds the dashboard.

**The plan · weeks 1 to 4**

## One harness skill per week

- [ ] **Week 1: context.** Cut your AGENTS.md or CLAUDE.md to what every task needs; move one long procedure into a skill. Compare a task before and after.
- [ ] **Week 1: first sensor.** Add one blocking hook for your most expensive repeated mistake and watch it fire.
- [ ] **Week 2: observability.** Record time, tokens, cost and outcome per agent task. Compute cost per accepted task for one week of work.
- [ ] **Week 3: a goal loop.** Run one task as a loop with a verifiable exit, an iteration cap, a spend cap and a no-progress check, in its own branch.
- [ ] **Week 4: evals.** Build a 20-case golden set from real tasks, record a baseline, then rerun it after one harness change. Report pass rate over several trials.
- [ ] **Week 4: share it.** Write up one failure and the harness change that fixed it, with before and after numbers.
- [ ] **All month:** flashcards on schedule until every card reaches the last box.

**Habits**

## What experienced agentic engineers do differently

- **Read the transcript:** When a run goes wrong, read what the agent actually saw before blaming the model.
- **Fix the harness, not the run:** Every repeated failure becomes a guide, a sensor or a permission.
- **Measure before changing:** No prompt or harness change without a before and after.
- **Verify, don't trust:** "Done" means a check passed, not that the agent said so.

**Sources**

## Where the claims in this course come from

Terms in this field are young. Every definition here traces to one of these sources; read them for depth, and expect the vocabulary to keep moving.

| Source | Used for |
| --- | --- |
| [The New Stack: Karpathy's "agentic engineering" (February 2026)](https://thenewstack.io/vibe-coding-is-passe/) | Origin and meaning of agentic engineering; vibe coding |
| [Anthropic: Building effective agents](https://www.anthropic.com/engineering/building-effective-agents) | Workflows versus agents; the core patterns |
| [Anthropic: Effective context engineering for AI agents (September 2025)](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents) | Definition of context engineering, context rot, just-in-time context, compaction, structured notes, subagents |
| [martinfowler.com: Harness engineering for coding agent users](https://martinfowler.com/articles/harness-engineering.html) | Builder versus user harness; guides and sensors; computational versus inferential controls |
| [HumanLayer: Skill issue, harness engineering for coding agents](https://humanlayer.dev/blog/skill-issue-harness-engineering-for-coding-agents) | Harness configuration points; agent = model + harness |
| [ZBrain: Loop engineering](https://zbrain.ai/loop-engineering/) | Loop engineering as a young discipline above the harness |
| [Anthropic: Demystifying evals for AI agents (January 2026)](https://www.anthropic.com/engineering/demystifying-evals-for-ai-agents) | Tasks, trials, graders, pass@k and pass^k, reading transcripts |
| [agentskills.io: Agent Skills specification](https://agentskills.io/) | SKILL.md format and progressive disclosure |
| [AGENTS.md](https://agents.md/) and the Agentic AI Foundation (Linux Foundation, December 2025) | Open standards: AGENTS.md, MCP |
| [Model Context Protocol](https://modelcontextprotocol.io/) | Tools, resources, prompts over a standard protocol |
| [Simon Willison: The lethal trifecta](https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/) | Prompt injection and data exfiltration risk |
| [Claude Code docs: hooks](https://code.claude.com/docs/en/hooks) | Hook events and exit codes used in the examples |

> **Note:** **Found an error or an outdated claim?** This course is maintained by Asem Abdo. Corrections are welcome, and dated updates keep it honest as the field moves.