Skip to content

jdg2896/agentic-engineering

Repository files navigation

Agentic Engineering Workflow — A Curated Resource Guide

Backend & infrastructure focus. Agent/language-agnostic. Continuously maintained — links verified weekly.


0. If you only read 7 things

  1. Building Effective Agents — Anthropic (Schluntz/Zhang). The "workflows vs agents" mental model that everything else builds on.
  2. Effective context engineering for AI agents — Anthropic. The successor concept to prompt engineering; defines the actual job.
  3. 12-Factor Agents — Dex Horthy / HumanLayer. Heroku's 12-factor reframed for LLM systems; the canonical "agents are mostly software" doctrine.
  4. How we built our multi-agent research system — Anthropic. The best single multi-agent case study, with concrete failure modes.
  5. Don't Build Multi-Agents — Cognition. Read alongside #4 — the productive disagreement at the heart of agent architecture in 2025/26.
  6. A practical guide to building agents (PDF) — OpenAI. The complementary canonical from the other lab.
  7. What We Learned From a Year of Building with LLMs — Yan/Bischof/Frye/Husain/Liu/Shankar. Tactical → operational → strategic; the field's distilled playbook.

1. Foundational design & "what is an agent"

2. Tool integration & MCP

3. Multi-agent orchestration frameworks

4. Durable execution for agents

5. Memory systems

6. Sandboxing & code execution

7. Inference & gateway infrastructure

8. Evaluation — philosophy (read these first)

9. Evaluation — frameworks & benchmarks

10. Observability & tracing

11. Production testing patterns & cost/latency

12. Security for agents

13. Coding agent infrastructure (read for harness design even if not building one)

14. Backend-specific agent patterns (SRE, K8s, IaC)


Worth following for ongoing signal

  • Anthropic Engineering — Engineering posts from the model-maker — agents, tooling, and operational patterns.
  • Cognition blog — Case studies on building Devin; the productive disagreement to "Don't Build Multi-Agents."
  • Simon Willison — The field's running curator — daily-ish takes on LLMs, agents, and prompt injection.
  • Embrace The Red — Johann Rehberger's red-team blog — concrete agent exploits and bypass techniques.
  • Cloudflare AI agents tag — Agent-runtime and infra posts from Cloudflare's edge platform.
  • LangChain blog — Framework updates, multi-agent patterns, and ecosystem news.
  • Hamel's blog — Applied LLM engineering and evals from a practitioner perspective.

About

Self-maintaining curated guide to agentic engineering, kept fresh by link-health and scout agents.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors