feat: quiz on M1, sitemap, robots.txt, model selection blog post

site/.vitepress/config.mjs

@@ -6,6 +6,9 @@ export default defineConfig({
   lang: 'en-US',
   lastUpdated: true,
   cleanUrls: true,
+  sitemap: {
+    hostname: 'https://git.fdsa.agency',
+  },
 
   head: [
     ['link', { rel: 'icon', href: '/favicon.svg' }],

site/.vitepress/dist/assets/modules_m1-foundations.md.DHFyTzWj.lean.js

@@ -1 +0,0 @@
-import{c as e,Q as t,j as a,m as i}from"./chunks/framework.BPKcPtvA.js";const u=JSON.parse('{"title":"Module 1: Foundations","description":"","frontmatter":{},"headers":[],"relativePath":"modules/m1-foundations.md","filePath":"modules/m1-foundations.md","lastUpdated":1780488246000}'),n={name:"modules/m1-foundations.md"};function o(l,s,r,h,p,d){return t(),a("div",null,[...s[0]||(s[0]=[i("",88)])])}const k=e(n,[["render",o]]);export{u as __pageData,k as default};

site/.vitepress/dist/hashmap.json

@@ -1 +1 @@
-{"404.md":"BiCvjdaY","api-keys.md":"D2Kyj8T3","blog_index.md":"ej0SMQFJ","blog_posts_agent-loops-complete-guide.md":"DcCNOI9M","blog_posts_cascade-routing.md":"DvBM3TSf","blog_posts_choosing-security-level.md":"BYXRZEDN","blog_posts_context-window-management.md":"Dr1RUj8G","blog_posts_mental-models.md":"BRY80gtq","blog_posts_repo-is-spec.md":"BxY1cXc_","blog_posts_security-ladder.md":"DQaqn6Yt","blog_posts_three-x-rule.md":"BHO6bhvz","blog_posts_verifier-pattern.md":"Gha_L_u5","blog_posts_vibe-vs-agentic.md":"7mduPfz1","blog_posts_what-is-an-agent.md":"BU2wUq_Y","blog_posts_why-multi-agent.md":"BVRIN2vH","buy.md":"qEifz7WE","certificate.md":"DZ26T6CI","checkout.md":"Ccj6L__h","checkout_cancel.md":"DwL5mulX","checkout_success.md":"CYTg6xhL","downloads.md":"CEHJXSp0","free-preview.md":"C5BtRucn","getting-started.md":"Boo_V9xC","index.md":"BNS2TR1g","labs_index.md":"sAzXzfkI","labs_l1-first-agent.md":"BwU9yf-G","labs_l2-context.md":"BexGm8_s","labs_l2-multi-tool.md":"Bj3Mb-oj","labs_l3-verifier.md":"xilrGGap","labs_l3-whitelist-hook.md":"DJtbL66Y","labs_l4-agent-chain.md":"D89P8dwJ","labs_l4-multi-team.md":"DmSK8e2P","labs_l5-cicd.md":"Dz1Jl78z","labs_l5-observability.md":"BDpqVYjT","labs_l6-cost-optimization.md":"CabFK4GB","labs_l6-eval-harness.md":"CBwH6xOR","labs_l7-autoresearch.md":"BYlzPLYo","labs_l7-meta-agent.md":"iTswbOPg","modules_competitive-analysis.md":"BHMHacei","modules_curriculum.md":"D7UeKRfo","modules_debate.md":"DWctKMlA","modules_feynman.md":"DBw5sPBP","modules_field-manual.md":"hmt_NLf1","modules_m1-foundations.md":"DHFyTzWj","modules_m2-architecture.md":"DVowtmf9","modules_m3-safety.md":"RiQQ_HWX","modules_m4-orchestration.md":"DFLcAKBv","modules_m5-production.md":"DTkLIrwQ","modules_m6-economics.md":"HihVEOPb","modules_m7-advanced.md":"B_jVHqsw","modules_m8-capstone.md":"CqV39Gzl","modules_non-technical.md":"BnvuUCRo","modules_reference-stack.md":"D9FXitvn","modules_software-factory.md":"C5Yf8Zwe","modules_tool-reference.md":"B40mlgZJ","public_certificate_template.md":"Cg1kPB1b","resources.md":"DcUu1NrK","skills.md":"BX3RBeCK","troubleshooting.md":"B6difx2I","verify.md":"Cl5ZMWNd"}
+{"404.md":"BiCvjdaY","api-keys.md":"D2Kyj8T3","blog_index.md":"CH9ul8Qh","blog_posts_agent-loops-complete-guide.md":"DrdeWzm3","blog_posts_cascade-routing.md":"DvBM3TSf","blog_posts_choosing-security-level.md":"BYXRZEDN","blog_posts_context-window-management.md":"40drllBG","blog_posts_mental-models.md":"BRY80gtq","blog_posts_model-selection-guide.md":"Ca-IsHa3","blog_posts_repo-is-spec.md":"BxY1cXc_","blog_posts_security-ladder.md":"DQaqn6Yt","blog_posts_three-x-rule.md":"BHO6bhvz","blog_posts_verifier-pattern.md":"Gha_L_u5","blog_posts_vibe-vs-agentic.md":"7mduPfz1","blog_posts_what-is-an-agent.md":"BU2wUq_Y","blog_posts_why-multi-agent.md":"BVRIN2vH","buy.md":"qEifz7WE","certificate.md":"DZ26T6CI","checkout.md":"Ccj6L__h","checkout_cancel.md":"DwL5mulX","checkout_success.md":"CYTg6xhL","downloads.md":"CEHJXSp0","free-preview.md":"C5BtRucn","getting-started.md":"Boo_V9xC","index.md":"BNS2TR1g","labs_index.md":"sAzXzfkI","labs_l1-first-agent.md":"BwU9yf-G","labs_l2-context.md":"BexGm8_s","labs_l2-multi-tool.md":"Bj3Mb-oj","labs_l3-verifier.md":"xilrGGap","labs_l3-whitelist-hook.md":"DJtbL66Y","labs_l4-agent-chain.md":"D89P8dwJ","labs_l4-multi-team.md":"DmSK8e2P","labs_l5-cicd.md":"Dz1Jl78z","labs_l5-observability.md":"BDpqVYjT","labs_l6-cost-optimization.md":"CabFK4GB","labs_l6-eval-harness.md":"CBwH6xOR","labs_l7-autoresearch.md":"BYlzPLYo","labs_l7-meta-agent.md":"iTswbOPg","modules_competitive-analysis.md":"BHMHacei","modules_curriculum.md":"D7UeKRfo","modules_debate.md":"DWctKMlA","modules_feynman.md":"DBw5sPBP","modules_field-manual.md":"hmt_NLf1","modules_m1-foundations.md":"CgHO7sNo","modules_m2-architecture.md":"DVowtmf9","modules_m3-safety.md":"RiQQ_HWX","modules_m4-orchestration.md":"DFLcAKBv","modules_m5-production.md":"DTkLIrwQ","modules_m6-economics.md":"HihVEOPb","modules_m7-advanced.md":"B_jVHqsw","modules_m8-capstone.md":"CqV39Gzl","modules_non-technical.md":"BnvuUCRo","modules_reference-stack.md":"D9FXitvn","modules_software-factory.md":"C5Yf8Zwe","modules_tool-reference.md":"B40mlgZJ","public_certificate_template.md":"Cg1kPB1b","resources.md":"DcUu1NrK","skills.md":"BX3RBeCK","troubleshooting.md":"B6difx2I","verify.md":"Cl5ZMWNd"}

site/blog/index.md

@@ -4,6 +4,9 @@ Essays on agentic engineering, security, multi-agent systems, and production dep
 
 ## Latest Posts
 
+### [How to Choose the Right Model for Your Agent](/blog/posts/model-selection-guide) — June 22
+A practical decision framework for model selection. Cascade routing, anti-patterns, and when to use local models.
+
 ### [Context Window Management for AI Agents](/blog/posts/context-window-management) — June 18
 Sliding windows, summarization, mental models, and the 80/20 rule of context budget allocation.
 

site/blog/posts/model-selection-guide.md

@@ -0,0 +1,133 @@
+# How to Choose the Right Model for Your Agent
+
+**June 22, 2026**
+
+You're building an agent. Which model do you use? The answer isn't "the best one" — it's "the right one for this subtask."
+
+---
+
+## The Model Landscape (Mid-2026)
+
+| Tier | Models | Cost/1M tokens | Best For |
+|------|--------|----------------|----------|
+| **Frontier** | Claude Opus 4, GPT-5, Gemini Ultra 2.0 | $12-30 | Complex reasoning, code generation, safety-critical decisions |
+| **Mid** | Claude Sonnet 4, GPT-5-mini, Gemini Pro 2.0 | $3-8 | Analysis, classification, summarization |
+| **Cheap** | Claude Haiku 3.5, GPT-5-flash, Gemini Flash 2.0 | $0.15-0.50 | Bulk processing, extraction, simple tool calls |
+| **Local** | Llama 4, DeepSeek Coder, Mistral Large 2 | Free (HW cost) | Private data, offline, latency-sensitive |
+
+The price range from cheapest to most expensive is **200x**. Using the wrong tier for a task is like renting a dump truck to move a shoebox.
+
+---
+
+## The Decision Framework
+
+```
+Task complexity
+      │
+      ├─ Is it deterministic? (grep, parse, format, extract)
+      │     → Use CHEAP model (Haiku/Flash)
+      │
+      ├─ Does it need reasoning? (analyze, explain, plan)
+      │     → Use MID model (Sonnet/Pro)
+      │
+      ├─ Is it customer-facing? (report, email, summary)
+      │     → Use FRONTIER model (Opus/GPT-5)
+      │
+      └─ Does it involve private data? (PII, IP, secrets)
+            → Use LOCAL model (Llama/DeepSeek)
+```
+
+---
+
+## Cascade Routing in Practice
+
+```python
+MODEL_TIERS = {
+    "cheap": {
+        "model": "claude-haiku-3.5-20260501",
+        "cost_per_m_tokens": 0.15,
+        "max_tokens": 4000,
+    },
+    "mid": {
+        "model": "claude-sonnet-4-20260501",
+        "cost_per_m_tokens": 3.00,
+        "max_tokens": 8000,
+    },
+    "premium": {
+        "model": "claude-opus-4-20260501",
+        "cost_per_m_tokens": 15.00,
+        "max_tokens": 16000,
+    },
+}
+
+def route_to_tier(task_type, prompt):
+    if task_type in ("extract", "parse", "format", "search", "classify"):
+        tier = "cheap"
+    elif task_type in ("analyze", "explain", "plan", "review"):
+        tier = "mid"
+    elif task_type in ("generate", "synthesize", "report", "decide"):
+        tier = "premium"
+    else:
+        tier = "mid"  # safe default
+
+    model = MODEL_TIERS[tier]
+    response = call_llm(model["model"], prompt, model["max_tokens"])
+    cost = (count_tokens(prompt) / 1_000_000) * model["cost_per_m_tokens"]
+
+    return {"response": response, "tier": tier, "cost": cost}
+```
+
+---
+
+## Model Selection Anti-Patterns
+
+### "Just Use the Best Model"
+
+The most expensive anti-pattern. Running every task through Opus costs 100x more than routing simple tasks to Haiku. For a production agent making 500 calls/day:
+- All Opus: ~$75/day
+- Cascaded: ~$8/day
+
+**Savings: 89%**
+
+### "Use the Cheapest Model Everywhere"
+
+Saves money, loses quality. Cheap models hallucinate more, follow instructions less reliably, and produce worse output on complex tasks. A single bad output from a cheap model can cost more in debugging time than you saved in API fees.
+
+### "One Model Per Agent"
+
+This is acceptable for simple agents but misses optimization opportunities. Within a single agent session, you can route different subtasks to different models. The same agent can use Haiku for file discovery and Opus for synthesis.
+
+---
+
+## When Local Models Make Sense
+
+Local models (Llama 4, DeepSeek) are not competitive with cloud APIs on quality. But they win on:
+
+1. **Privacy** — Data never leaves your machine
+2. **Latency** — No network calls (5ms vs 500ms)
+3. **Cost at scale** — Free after hardware purchase
+4. **Offline operation** — Works without internet
+
+**Best use cases**: Code completion, local file analysis, private document review, development assistance.
+
+**Worst use cases**: Complex reasoning, multi-step planning, tasks requiring up-to-date knowledge.
+
+---
+
+## The 80/20 Rule of Model Selection
+
+80% of cost savings come from one change: **stop using frontier models for routine work**.
+
+| Task Type | Current Model | Recommended Model | Savings |
+|-----------|--------------|-------------------|---------|
+| File discovery | Opus/Sonnet | Haiku/Flash | 95% |
+| Data extraction | Opus/Sonnet | Haiku/Flash | 95% |
+| Classification | Opus/Sonnet | Haiku/Flash | 95% |
+| Analysis | Opus | Sonnet | 80% |
+| Code review | Opus | Sonnet | 80% |
+| Report generation | Opus | Opus (keep) | 0% |
+| Complex reasoning | Opus | Opus (keep) | 0% |
+
+---
+
+*This is adapted from Module 6: Economics of the [Agentic Engineering the Hard Way](/free-preview) course. Full course includes 65 lessons, 13 labs, and 20 skill kits.*

site/modules/m1-foundations.md

@@ -278,6 +278,45 @@ This single pattern:
 
 ---
 
+## Module 1 Quiz
+
+Test your understanding of the foundations.
+
+<Quiz :questions="[
+  {
+    q: 'What three components define an AI agent?',
+    opts: ['LLM + Data + Training', 'LLM + Tools + Loop', 'Model + API + Frontend', 'Prompt + Response + Memory'],
+    ans: 1,
+    exp: 'An agent is defined by its reasoning engine (LLM), its capability surface (Tools), and its autonomous decision cycle (Loop). Remove any one and it is not an agent.'
+  },
+  {
+    q: 'What does the harness determine that the model does NOT?',
+    opts: ['Response quality', 'Token pricing', 'Tool selection accuracy + loop termination + security', 'Training data quality'],
+    ans: 2,
+    exp: 'The harness controls loop termination, security hooks, context management, retry logic, and cost — not the model. A good harness with a mediocre model outperforms a bad harness with the best model.'
+  },
+  {
+    q: 'What is the main risk of not setting MAX_ITERATIONS on an agent loop?',
+    opts: ['The agent runs too slowly', 'The agent can loop forever, burning unlimited tokens', 'The model refuses to answer', 'Tools stop working after 10 calls'],
+    ans: 1,
+    exp: 'Without a maximum iteration limit, an agent can loop indefinitely on an ambiguous task, potentially costing $50+ in runaway token usage before you notice.'
+  },
+  {
+    q: 'Which of these is NOT one of the 5 subsystems of a harness?',
+    opts: ['Tool execution system', 'Loop control system', 'Model training system', 'Context management system'],
+    ans: 2,
+    exp: 'Model training is not part of the harness. The 5 subsystems are: Tool Execution, Loop Control, Context Management, Security & Safety, and Observability & Cost.'
+  },
+  {
+    q: 'In the decision framework, what does P (Process) vs F (First Principles) distinguish?',
+    opts: ['Python vs FastAPI', 'Following a known procedure vs reasoning from fundamentals', 'Public vs Private agents', 'Primary vs Fallback models'],
+    ans: 1,
+    exp: 'P-threads follow known procedures (optimized, safe, repeatable). F-threads reason from first principles (creative, adaptive, expensive). Knowing which to use is the core of agentic engineering.'
+  }
+]" />
+
+---
+
 ## Lab 1.9: Your First Agent
 
 **Objective**: Build a single-tool agent from scratch in under 50 lines.

site/public/robots.txt

@@ -0,0 +1,3 @@
+User-agent: *
+Allow: /
+Sitemap: https://git.fdsa.agency/sitemap.xml