AI Agents: A Primer - Revision history

Ajshen at 05:41, 29 October 2026

2026-10-29T05:41:27Z

← Older revision		Revision as of 05:41, 29 October 2026
Line 10:		Line 10:
	This article is adapted from the StatBytes talk [https://drive.google.com/drive/folders/1KnyUo9YNr2XL9N5nJgpzW5jWyulSfTIg?usp=drive_link\|''Piloting the Suit: Workflow tips for agentic AI in statistical research'']. A small demo repository that goes with it is at [https://github.com/Alex-Shen-CMU/statbytes-agentic-example github.com/Alex-Shen-CMU/statbytes-agentic-example]. Most examples below use Claude Code, but almost everything applies to other coding agents too.		This article is adapted from the StatBytes talk [https://drive.google.com/drive/folders/1KnyUo9YNr2XL9N5nJgpzW5jWyulSfTIg?usp=drive_link\|''Piloting the Suit: Workflow tips for agentic AI in statistical research'']. A small demo repository that goes with it is at [https://github.com/Alex-Shen-CMU/statbytes-agentic-example github.com/Alex-Shen-CMU/statbytes-agentic-example]. Most examples below use Claude Code, but almost everything applies to other coding agents too.
	<br><br>		<br><br>
	See [https://github.com/Alex-Shen-CMU/stats-agent-setup\|https://github.com/Alex-Shen-CMU/stats-agent-setup] for a collection of commonly used agent skills and agent instruction files relevant for statistics research.		See [https://github.com/Alex-Shen-CMU/stats-agent-setup https://github.com/Alex-Shen-CMU/stats-agent-setup] for a collection of commonly used agent skills and agent instruction files relevant for statistics research.
	</div>		</div>

Ajshen at 05:39, 29 October 2026

2026-10-29T05:39:51Z

← Older revision		Revision as of 05:39, 29 October 2026
Line 10:		Line 10:
	This article is adapted from the StatBytes talk [https://drive.google.com/drive/folders/1KnyUo9YNr2XL9N5nJgpzW5jWyulSfTIg?usp=drive_link\|''Piloting the Suit: Workflow tips for agentic AI in statistical research'']. A small demo repository that goes with it is at [https://github.com/Alex-Shen-CMU/statbytes-agentic-example github.com/Alex-Shen-CMU/statbytes-agentic-example]. Most examples below use Claude Code, but almost everything applies to other coding agents too.		This article is adapted from the StatBytes talk [https://drive.google.com/drive/folders/1KnyUo9YNr2XL9N5nJgpzW5jWyulSfTIg?usp=drive_link\|''Piloting the Suit: Workflow tips for agentic AI in statistical research'']. A small demo repository that goes with it is at [https://github.com/Alex-Shen-CMU/statbytes-agentic-example github.com/Alex-Shen-CMU/statbytes-agentic-example]. Most examples below use Claude Code, but almost everything applies to other coding agents too.
	<br><br>		<br><br>
	See [https://github.com/Alex-Shen-CMU/stats-agent-setup] for a collection of commonly used agent skills and agent instruction files relevant for statistics research.		See [https://github.com/Alex-Shen-CMU/stats-agent-setup\|https://github.com/Alex-Shen-CMU/stats-agent-setup] for a collection of commonly used agent skills and agent instruction files relevant for statistics research.
	</div>		</div>

Ajshen at 05:37, 29 October 2026

2026-10-29T05:37:54Z

← Older revision		Revision as of 05:37, 29 October 2026
Line 9:		Line 9:
	'''Based on a StatBytes talk'''<br>		'''Based on a StatBytes talk'''<br>
	This article is adapted from the StatBytes talk [https://drive.google.com/drive/folders/1KnyUo9YNr2XL9N5nJgpzW5jWyulSfTIg?usp=drive_link\|''Piloting the Suit: Workflow tips for agentic AI in statistical research'']. A small demo repository that goes with it is at [https://github.com/Alex-Shen-CMU/statbytes-agentic-example github.com/Alex-Shen-CMU/statbytes-agentic-example]. Most examples below use Claude Code, but almost everything applies to other coding agents too.		This article is adapted from the StatBytes talk [https://drive.google.com/drive/folders/1KnyUo9YNr2XL9N5nJgpzW5jWyulSfTIg?usp=drive_link\|''Piloting the Suit: Workflow tips for agentic AI in statistical research'']. A small demo repository that goes with it is at [https://github.com/Alex-Shen-CMU/statbytes-agentic-example github.com/Alex-Shen-CMU/statbytes-agentic-example]. Most examples below use Claude Code, but almost everything applies to other coding agents too.
			<br><br>
			See [https://github.com/Alex-Shen-CMU/stats-agent-setup] for a collection of commonly used agent skills and agent instruction files relevant for statistics research.
	</div>		</div>

Ajshen: /* Common Pitfalls */

2026-10-29T05:35:33Z

Common Pitfalls

← Older revision		Revision as of 05:35, 29 October 2026
Line 431:		Line 431:

	<div style="background-color: #e8f4f8; padding: 15px; text-align: center; margin-top: 20px; font-style: italic;">		<div style="background-color: #e8f4f8; padding: 15px; text-align: center; margin-top: 20px; font-style: italic;">
	'''Note:''' The tools change quickly, but the principles here don't: keep the context small and focused, write prompts like specifications, plan before building, and stay the pilot. For a full worked example, see [[~~Claude Code~~ GitHub ~~Issue Workflow~~]] and the [https://github.com/Alex-Shen-CMU/statbytes-agentic-example demo repository]. <!-- TODO: fix this link to match the actual title of the GitHub issue workflow article -->		'''Note:''' The tools change quickly, but the principles here don't: keep the context small and focused, write prompts like specifications, plan before building, and stay the pilot. For a full worked example, see [[Agentic Workflow via GitHub Issues]] and the [https://github.com/Alex-Shen-CMU/statbytes-agentic-example demo repository]. <!-- TODO: fix this link to match the actual title of the GitHub issue workflow article -->
	</div>		</div>

Ajshen: /* What Goes in CLAUDE.md */

2026-10-29T05:34:10Z

What Goes in CLAUDE.md

← Older revision		Revision as of 05:34, 29 October 2026
Line 414:		Line 414:

	Things that belong elsewhere: long procedures (make them [[#Skills\|skills]]), anything secret such as passwords or tokens (never put these in the repository), and task-specific plans (put them in a <code>PLAN.md</code> or an issue).		Things that belong elsewhere: long procedures (make them [[#Skills\|skills]]), anything secret such as passwords or tokens (never put these in the repository), and task-specific plans (put them in a <code>PLAN.md</code> or an issue).

	~~<!-- SCREENSHOT: Slide "A concrete workflow: making it work" (left column, the CLAUDE.md terminal example). -->~~
	~~[[File:Claude-md-example.png\|thumb\|center\|450px\|An example CLAUDE.md.]]~~

	== Common Pitfalls ==		== Common Pitfalls ==

Ajshen: /* Running Agents on a Remote Server */

2026-10-29T05:31:59Z

Running Agents on a Remote Server

← Older revision		Revision as of 05:31, 29 October 2026
Line 393:		Line 393:
	* '''Git is your undo button:''' work on branches, protect <code>main</code>, and review every change before it is merged.		* '''Git is your undo button:''' work on branches, protect <code>main</code>, and review every change before it is merged.

	For a complete end-to-end workflow built on this setup, in which tasks are written as GitHub issues and the agent plans, implements, runs experiments on the cluster, and opens a pull request for review, see [[~~Claude Code~~ GitHub ~~Issue Workflow~~]]. ~~<!-- TODO: fix this link to match the actual title of the GitHub issue workflow article -->~~		For a complete end-to-end workflow built on this setup, in which tasks are written as GitHub issues and the agent plans, implements, runs experiments on the cluster, and opens a pull request for review, see [[Agentic Workflow via GitHub Issues]].

	== What Goes in CLAUDE.md ==		== What Goes in CLAUDE.md ==

Ajshen: /* Running Agents on a Remote Server */

2026-10-29T05:29:28Z

Running Agents on a Remote Server

← Older revision		Revision as of 05:29, 29 October 2026
Line 392:		Line 392:
	* '''Shared server etiquette:''' the agent edits code and submits jobs; the cluster does the computing. Never let an agent run heavy computations on a shared login or interactive server.		* '''Shared server etiquette:''' the agent edits code and submits jobs; the cluster does the computing. Never let an agent run heavy computations on a shared login or interactive server.
	* '''Git is your undo button:''' work on branches, protect <code>main</code>, and review every change before it is merged.		* '''Git is your undo button:''' work on branches, protect <code>main</code>, and review every change before it is merged.

	~~<!-- SCREENSHOT: Slide "A concrete workflow: my setup" (laptop → dept. server with tmux + Claude Code + repo clone → GitHub and HPC cluster). -->~~
	~~[[File:Agent-remote-server-setup.png\|thumb\|center\|700px\|Running the agent on an always-on server, with access to GitHub and the cluster.]]~~

	For a complete end-to-end workflow built on this setup, in which tasks are written as GitHub issues and the agent plans, implements, runs experiments on the cluster, and opens a pull request for review, see [[Claude Code GitHub Issue Workflow]]. <!-- TODO: fix this link to match the actual title of the GitHub issue workflow article -->		For a complete end-to-end workflow built on this setup, in which tasks are written as GitHub issues and the agent plans, implements, runs experiments on the cluster, and opens a pull request for review, see [[Claude Code GitHub Issue Workflow]]. <!-- TODO: fix this link to match the actual title of the GitHub issue workflow article -->

Ajshen: /* How skills work */

2026-10-29T05:27:41Z

How skills work

← Older revision		Revision as of 05:27, 29 October 2026
Line 341:		Line 341:
	Because skills can bundle scripts, they also let the agent ''run'' a deterministic tool instead of ''regenerating'' its logic each time. A summary script that always computes Monte Carlo standard errors the same way is more reliable than asking the model to rewrite that code in every session, and it saves tokens too.		Because skills can bundle scripts, they also let the agent ''run'' a deterministic tool instead of ''regenerating'' its logic each time. A summary script that always computes Monte Carlo standard errors the same way is more reliable than asking the model to rewrite that code in every session, and it saves tokens too.

	<!-- SCREENSHOT: A Claude Code session where the agent picks up a skill automatically (e.g. a request to "run a simulation study comparing ..." with the agent reading .claude/skills/simstudy/SKILL.md). -->
	~~[[File:Claude-code-skill-invocation.png\|thumb\|center\|600px\|The agent loading a skill when a request matches its description.]]~~

	<div style="background-color: #f8f9fa; border-left: 4px solid #005A9C; padding: 15px; margin-bottom: 10px;">		<div style="background-color: #f8f9fa; border-left: 4px solid #005A9C; padding: 15px; margin-bottom: 10px;">

Ajshen: /* Prompts as specs */

2026-10-29T05:25:59Z

Prompts as specs

← Older revision		Revision as of 05:25, 29 October 2026
Line 287:		Line 287:

	A good prompt has five parts: the '''goal''', the relevant '''context''' (and where to find it), the '''constraints''', a checkable '''definition of done''', and an instruction to '''plan and ask questions first'''.		A good prompt has five parts: the '''goal''', the relevant '''context''' (and where to find it), the '''constraints''', a checkable '''definition of done''', and an instruction to '''plan and ask questions first'''.

	~~<!-- SCREENSHOT: Slide "Prompts as specs: before and after" (final overlay). -->~~
	~~[[File:Agent-prompt-before-after.png\|thumb\|center\|700px\|A vague prompt vs. a structured one.]]~~

	== Skills ==		== Skills ==

Ajshen: /* Agentic AI is an Iron Man suit */

2026-10-29T05:25:18Z

Agentic AI is an Iron Man suit

← Older revision		Revision as of 05:25, 29 October 2026
Line 210:		Line 210:

	A great suit makes a skilled pilot '''superhuman'''. It makes an unskilled pilot crash '''faster'''.		A great suit makes a skilled pilot '''superhuman'''. It makes an unskilled pilot crash '''faster'''.

	~~<!-- SCREENSHOT: Slide "Agentic AI is an Iron Man suit" (final overlay). -->~~
	~~[[File:Agent-iron-man-suit.png\|thumb\|center\|650px\|You are the pilot; the agent is the suit.]]~~

	== Best Practices ==		== Best Practices ==