Convert 73 Typst tables to Markdown across 29 chapters

Co-authored-by: Ona <no-reply@ona.com>

Author: Siddhant-K-code

src/content/chapters/01-agentic-landscape.mdx

@@ -34,34 +34,15 @@ next based on what it observes.
 
 The distinction matters because it changes the engineering requirements:
 
-#align(center)[#table(
-  columns: 3,
-  align: (col, row) => (auto,auto,auto,).at(col),
-  inset: 6pt,
-  [Dimension], [Chatbot], [Agent],
-  [**Actions**],
-  [Generates text],
-  [Executes code, calls APIs, modifies systems],
-  [**Autonomy**],
-  [Responds to prompts],
-  [Decides what to do next],
-  [**Duration**],
-  [Single turn],
-  [Minutes to hours],
-  [**Risk**],
-  [Wrong answer],
-  [Wrong action (data loss, security breach, cost overrun)],
-  [**Authorization**],
-  [User’s permissions],
-  [Needs its own permission model],
-  [**Observability**],
-  [Log the response],
-  [Trace every decision and action],
-  [**Failure mode**],
-  [Bad text],
-  [Production incident],
-)
-]
+| Dimension | Chatbot | Agent |
+| --- | --- | --- |
+| **Actions** | Generates text | Executes code, calls APIs, modifies systems |
+| **Autonomy** | Responds to prompts | Decides what to do next |
+| **Duration** | Single turn | Minutes to hours |
+| **Risk** | Wrong answer | Wrong action (data loss, security breach, cost overrun) |
+| **Authorization** | User’s permissions | Needs its own permission model |
+| **Observability** | Log the response | Trace every decision and action |
+| **Failure mode** | Bad text | Production incident |
 
 When you deploy an agent, you’re deploying a system that can act on your
 infrastructure. That’s a fundamentally different engineering problem
@@ -156,98 +137,39 @@ The agent ecosystem has consolidated around a few key players and
 patterns.
 
 ### Frameworks
-#align(center)[#table(
-  columns: 4,
-  align: (col, row) => (auto,auto,auto,auto,).at(col),
-  inset: 6pt,
-  [Framework], [Version], [Strengths], [Best For],
-  [[**LangChain / LangGraph**](https://github.com/langchain-ai/langchain)],
-  [v1.1.0],
-  [Mature ecosystem, graph-based orchestration],
-  [Complex multi-step workflows],
-  [[**CrewAI**](https://github.com/crewAIInc/crewAI)],
-  [v1.9.0],
-  [Role-based agents, simple API],
-  [Team-of-agents patterns],
-  [[**OpenAI Agents SDK**](https://github.com/openai/openai-agents-python)],
-  [GA (Mar 2025)],
-  [Native OpenAI integration, handoffs],
-  [OpenAI-first teams],
-  [[**Anthropic Claude Code**](https://docs.anthropic.com/en/docs/claude-code)],
-  [Production],
-  [Deep codebase understanding, tool use],
-  [Software engineering tasks],
-  [[**Microsoft AutoGen**](https://github.com/microsoft/autogen)],
-  [v0.4],
-  [Multi-agent conversations, research-grade],
-  [Research and experimentation],
-  [[**Goose (Block)**](https://github.com/block/goose)],
-  [Open source],
-  [MCP-native, extensible, observable],
-  [Production agent deployments],
-)
-]
+| Framework | Version | Strengths | Best For |
+| --- | --- | --- | --- |
+| [**LangChain / LangGraph**](https://github.com/langchain-ai/langchain) | v1.1.0 | Mature ecosystem, graph-based orchestration | Complex multi-step workflows |
+| [**CrewAI**](https://github.com/crewAIInc/crewAI) | v1.9.0 | Role-based agents, simple API | Team-of-agents patterns |
+| [**OpenAI Agents SDK**](https://github.com/openai/openai-agents-python) | GA (Mar 2025) | Native OpenAI integration, handoffs | OpenAI-first teams |
+| [**Anthropic Claude Code**](https://docs.anthropic.com/en/docs/claude-code) | Production | Deep codebase understanding, tool use | Software engineering tasks |
+| [**Microsoft AutoGen**](https://github.com/microsoft/autogen) | v0.4 | Multi-agent conversations, research-grade | Research and experimentation |
+| [**Goose (Block)**](https://github.com/block/goose) | Open source | MCP-native, extensible, observable | Production agent deployments |
 
 ### Coding agents in production
-#align(center)[#table(
-  columns: 3,
-  align: (col, row) => (auto,auto,auto,).at(col),
-  inset: 6pt,
-  [Agent], [Deployment Model], [Notable Capability],
-  [[**Ona**](https://ona.com)],
-  [Cloud (sandboxed environments)],
-  [Autonomous end-to-end: plans, codes, builds, tests, opens PRs. Each
+| Agent | Deployment Model | Notable Capability |
+| --- | --- | --- |
+| [**Ona**](https://ona.com) | Cloud (sandboxed environments) | Autonomous end-to-end: plans, codes, builds, tests, opens PRs. Each
   agent gets an isolated ephemeral environment. Fleet-scale parallelism
-  for migrations. Runs in your VPC.],
-  [[**Claude Code**](https://docs.anthropic.com/en/docs/claude-code)],
-  [CLI + IDE],
-  [Full codebase reasoning, multi-file edits],
-  [[**OpenAI Codex**](https://openai.com/index/introducing-codex/)],
-  [Cloud-based],
-  [Parallel task execution, sandboxed],
-  [[**Cursor**](https://cursor.com)],
-  [IDE-integrated],
-  [Real-time code generation, tab completion],
-  [[**Windsurf**](https://windsurf.com)],
-  [IDE-integrated],
-  [Cascade multi-file editing],
-  [[**Devin**](https://devin.ai)],
-  [Autonomous],
-  [End-to-end task completion],
-  [[**GitHub Copilot**](https://github.com/features/copilot)],
-  [IDE + CLI],
-  [Workspace-aware, agent mode],
-)
-]
+  for migrations. Runs in your VPC. |
+| [**Claude Code**](https://docs.anthropic.com/en/docs/claude-code) | CLI + IDE | Full codebase reasoning, multi-file edits |
+| [**OpenAI Codex**](https://openai.com/index/introducing-codex/) | Cloud-based | Parallel task execution, sandboxed |
+| [**Cursor**](https://cursor.com) | IDE-integrated | Real-time code generation, tab completion |
+| [**Windsurf**](https://windsurf.com) | IDE-integrated | Cascade multi-file editing |
+| [**Devin**](https://devin.ai) | Autonomous | End-to-end task completion |
+| [**GitHub Copilot**](https://github.com/features/copilot) | IDE + CLI | Workspace-aware, agent mode |
 
 ### The numbers
 The adoption numbers tell a clear story:
 
-#align(center)[#table(
-  columns: 3,
-  align: (col, row) => (auto,auto,auto,).at(col),
-  inset: 6pt,
-  [Metric], [Value], [Source],
-  [Fortune 500 companies using AI agents],
-  [80%],
-  [Microsoft Security Blog, Feb 2026],
-  [Coding tasks that are AI-assisted],
-  [~60%],
-  [Anthropic Agentic Coding Trends, 2026],
-  [Enterprises already using AI agents],
-  [65%],
-  [CrewAI State of Agentic AI, Feb 2026],
-  [MCP servers publicly visible],
-  [8,000+],
-  [Security researchers, Feb 2026],
-  [MCP SDK monthly downloads],
-  [97M+],
-  [npm/PyPI, Jan 2026],
-  [Projects with AGENTS.md],
-  [60,000+],
-  [GitHub, Jan 2026],
-)
-]
+| Metric | Value | Source |
+| --- | --- | --- |
+| Fortune 500 companies using AI agents | 80% | Microsoft Security Blog, Feb 2026 |
+| Coding tasks that are AI-assisted | ~60% | Anthropic Agentic Coding Trends, 2026 |
+| Enterprises already using AI agents | 65% | CrewAI State of Agentic AI, Feb 2026 |
+| MCP servers publicly visible | 8,000+ | Security researchers, Feb 2026 |
+| MCP SDK monthly downloads | 97M+ | npm/PyPI, Jan 2026 |
+| Projects with AGENTS.md | 60,000+ | GitHub, Jan 2026 |
 
 ## Why "agentic engineering" is a discipline
 Building with agents isn’t just "using AI tools." It requires new

src/content/chapters/02-capability-jump.mdx

@@ -252,21 +252,12 @@ Lattner’s key observations:
 
 What this means for your agent strategy:
 
-#align(center)[#table(
-  columns: 2,
-  align: (col, row) => (auto,auto,).at(col),
-  inset: 6pt,
-  [Before CCC], [After CCC],
-  [Agents write functions],
-  [Agents design systems],
-  [Human architects, AI coders],
-  [AI participates in architecture],
-  [Agents need detailed specs],
-  [Agents can infer architectural intent],
-  [Trust agents with files],
-  [Consider trusting agents with subsystems],
-)
-]
+| Before CCC | After CCC |
+| --- | --- |
+| Agents write functions | Agents design systems |
+| Human architects, AI coders | AI participates in architecture |
+| Agents need detailed specs | Agents can infer architectural intent |
+| Trust agents with files | Consider trusting agents with subsystems |
 
 This doesn’t mean agents replace architects. It means the boundary of
 what you can delegate has moved significantly. The Conductor Model
@@ -324,46 +315,17 @@ provider charges per million tokens, with output tokens costing 3-5x
 more than input tokens. Understanding the pricing structure helps you
 make informed decisions about model routing and cost optimization.
 
-#align(center)[#table(
-  columns: 4,
-  align: (col, row) => (auto,auto,auto,auto,).at(col),
-  inset: 6pt,
-  [Model], [Input \$/1M tokens], [Output \$/1M tokens], [Effective cost
-  for 100K input + 10K output],
-  [GPT-5.2],
-  [\$1.75],
-  [\$14.00],
-  [\$0.315],
-  [GPT-5.2-mini],
-  [\$0.15],
-  [\$0.60],
-  [\$0.021],
-  [Claude Opus 4.6],
-  [\$5.00],
-  [\$25.00],
-  [\$0.750],
-  [Claude Sonnet 4.6],
-  [\$3.00],
-  [\$15.00],
-  [\$0.450],
-  [Claude Haiku 4],
-  [\$1.00],
-  [\$5.00],
-  [\$0.150],
-  [Gemini 3.1 Pro],
-  [\$2.00],
-  [\$12.00],
-  [\$0.320],
-  [Gemini 3 Flash],
-  [\$0.075],
-  [\$0.30],
-  [\$0.011],
-  [DeepSeek V3.2],
-  [\$0.27],
-  [\$1.10],
-  [\$0.038],
-)
-]
+| Model | Input $/1M tokens | Output $/1M tokens | Effective cost
+  for 100K input + 10K output |
+| --- | --- | --- | --- |
+| GPT-5.2 | $1.75 | $14.00 | $0.315 |
+| GPT-5.2-mini | $0.15 | $0.60 | $0.021 |
+| Claude Opus 4.6 | $5.00 | $25.00 | $0.750 |
+| Claude Sonnet 4.6 | $3.00 | $15.00 | $0.450 |
+| Claude Haiku 4 | $1.00 | $5.00 | $0.150 |
+| Gemini 3.1 Pro | $2.00 | $12.00 | $0.320 |
+| Gemini 3 Flash | $0.075 | $0.30 | $0.011 |
+| DeepSeek V3.2 | $0.27 | $1.10 | $0.038 |
 
 The 35x cost difference between Opus 4.6 (\$0.750) and Gemini 3 Flash
 (\$0.011) for the same token volume makes model routing a financial

src/content/chapters/04-context-windows.mdx

@@ -23,28 +23,13 @@ and how much of your codebase the agent can "see" at any given time.
 Understanding this constraint - and engineering around it - is the
 single most impactful skill in agent development.
 
-#align(center)[#table(
-  columns: 3,
-  align: (col, row) => (auto,auto,auto,).at(col),
-  inset: 6pt,
-  [Model], [Context Window], [Approximate Pages of Text],
-  [GPT-5.2],
-  [400K tokens],
-  [~640 pages],
-  [GPT-5.3-Codex],
-  [400K tokens],
-  [~640 pages],
-  [Claude Sonnet 4.6],
-  [200K (1M beta)],
-  [~320 pages (1,600 beta)],
-  [Claude Opus 4.6],
-  [200K (1M beta)],
-  [~320 pages (1,600 beta)],
-  [Gemini 3.1 Pro],
-  [1M tokens],
-  [~1,600 pages],
-)
-]
+| Model | Context Window | Approximate Pages of Text |
+| --- | --- | --- |
+| GPT-5.2 | 400K tokens | ~640 pages |
+| GPT-5.3-Codex | 400K tokens | ~640 pages |
+| Claude Sonnet 4.6 | 200K (1M beta) | ~320 pages (1,600 beta) |
+| Claude Opus 4.6 | 200K (1M beta) | ~320 pages (1,600 beta) |
+| Gemini 3.1 Pro | 1M tokens | ~1,600 pages |
 
 These numbers look large. They’re not.
 
@@ -87,25 +72,11 @@ Tokens cost money, and the cost scales linearly with context size. Every
 token you send is a token you pay for, and every token the model
 processes adds latency.
 
-#align(center)[#table(
-  columns: 4,
-  align: (col, row) => (auto,auto,auto,auto,).at(col),
-  inset: 6pt,
-  [Approach], [Tokens Sent], [Cost per Request], [Latency],
-  [Naive (dump everything)],
-  [100K],
-  [\$0.30],
-  [~8s],
-  [With context engineering],
-  [15K],
-  [\$0.045],
-  [~2s],
-  [**Savings**],
-  [**85%**],
-  [**85%**],
-  [**75%**],
-)
-]
+| Approach | Tokens Sent | Cost per Request | Latency |
+| --- | --- | --- | --- |
+| Naive (dump everything) | 100K | $0.30 | ~8s |
+| With context engineering | 15K | $0.045 | ~2s |
+| **Savings** | **85%** | **85%** | **75%** |
 
 At scale, this is the difference between a viable product and a money
 pit. A team running 500 agent tasks per day at 100K tokens each spends