Commit activity
Last 12 weeks · 1 commit
Community health
3 of 6 standards met
57
✓README✓License✓Contributing○Code of Conduct○Issue Template○PR Template
Recent PRs & issues
Active · 1 in progress · Last activity 1mo ago
See all on GitHub →
Initial AI prompt: _Scan Addy's blog posts from this year at https://addyosmani.com/blog/ . See if any of them are explicitly about building agents. If so, read them, and see if they have any great advice or content that's missing from this course, and add it._ Resulting additions: Lesson 7: the orchestration tax - human review capacity as the ceiling on multi-agent parallelism Lesson 9: mistake 7 - never let the agent grade its own homework; review test diffs more carefully than code diffs Lesson 10: calibrated autonomy - three risk questions and a pre-delegation contract Lesson 13: the harness concept (agent = model + harness) and the ratchet pattern Lesson 15: write AGENTS.md by hand - the discovery filter Lesson 17: workflows not essays, anti-rationalization tables, evidence as exit criterion Lesson 18: long-running agents - the three walls, externalized state, and the Ralph loop Each addition links the source post in further reading. Ported from lsimons/agent-engineer-course commit c3d862f . Assisted-by: Claude:claude-fable-5
I noticed that the navigation(Next lesson) link at the bottom of Section 3 in the README appears to be broken. Happy to help fix this if needed ✨
Guidance currently leans on models that are in GA. Should probably make a decision about whether to include preview models more clearly, but I think this is a smaller issue for someone new to agents. Just something to make sure we're capturing clearly. e.g. You'll notice a lot of Gemini 2.x mentions in the repo vs Gemini 3.x.
Recent fixes
Fixed 6 broken redirect links across 3 documentation files: Vertex AI Agent Engine sessions (2 occurrences) Model Armor documentation (2 occurrences) Google Cloud Trace (1 occurrence) Anthropic building effective agents (1 occurrence) All updated links have been verified to return HTTP 200 status codes.
Summary Addresses issue #1 by updating all model references from Gemini 2.5 to 2.0 and adding guidance about preview vs GA models. Changes Made: Model Updates: Updated all Gemini 2.5 references to 2.0 across 5 files Preview vs GA Guidance: Added clear guidance about using GA models for production and preview models for experimentation Documentation Updates: Updated model selection tables, diagrams, and code examples Files Modified: 02-how-agents-think/README.md: Updated model spectrum diagram and added preview guidance 11-from-prototype-to-production/README.md: Updated model routing diagram 12-getting-started-with-vertex-and-adk/README.md: Updated model table and references 13-building-your-first-agent/README.md: Updated all code examples (9 instances) 18-orchestrators/README.md: Updated model selection guidance Impact: Resolves outdated model version issue mentioned in iss- Resolves outdated model version issue mentioned in iss- Resolves outdated model version issue mentioned in cross all documentation Maintains educational value while reflecting current model availability
Summary Update Vertex AI session URLs to new Agent Builder path (2 occurrences in ) Update A2A protocol spec URLs from to (4 occurrences across and ) Update ADK workflow agent URLs from to with pluralised slugs (3 occurrences in ) All broken links were detected with lychee. AI disclosure This PR was prepared with the help of Claude Code (Claude Opus 4.6). The broken links were identified by lychee; replacement URLs were sourced from the BROKEN_LINKS.md report and verified by a human before submission.
Structured data for AI agents
Repository: addyosmani/agent-engineer. Description: Agent Engineer - a practical course for software engineers Stars: 453, Forks: 75. License: Apache-2.0. Topics: agentic-framework, ai-agents, generative-ai. Open PRs: 1, open issues: 2. Last activity: 1mo ago. Community health: 57%. Top contributors: addyosmani, ivarurdalen.