{"product_id":"claude-code-in-action-wes-halloran-9798181720947","title":"Claude Code in Action: Real Agentic Workflows, \/goal Loops, and Shipping Products Fast","description":"\u003cp\u003e\u003cb\u003eThe agent said \"Done.\" You opened the app. It was broken.\u003c\/b\u003e\u003c\/p\u003e\u003cp\u003eYou are a competent developer. You can smell a bug from across the room. So why does AI pair programming feel like babysitting a confident intern who reports success it never checked? It is not your prompt engineering. Nobody defined what done meant, so the agent got to declare the word instead of earning it.\u003c\/p\u003e\u003cp\u003eThat checkmark over broken work is the green lie, and it is why \"done\" is the most expensive sentence in agentic coding. It is why you still read every token instead of walking away, why vibe coding runs out of road the moment the work matters, and why good developers quietly downgrade an autonomous coding agent to faster autocomplete.\u003c\/p\u003e\u003cp\u003e\u003ci\u003eClaude Code in Action\u003c\/i\u003e is about making the agent earn the word. You hand it a definition of done it cannot fake, wrap that in a goal loop that refuses to stop until the work is actually green, and build a harness around it so autonomy is productive instead of dangerous. The fix is a loop, not a vibe, and every workflow in these pages was run against the real tool before it was written down.\u003c\/p\u003e\u003cp\u003e\u003cb\u003eThe working developer's method for agentic AI software engineering: \u003c\/b\u003e\u003c\/p\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cb\u003eThe definition of done\u003c\/b\u003e: a completion test the agent has to satisfy, so \"done\" stops being a lie.\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eThe goal loop\u003c\/b\u003e: goal, completion test, cycle until green, for any task you hand off.\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eThe harness\u003c\/b\u003e: project memory, a custom command, a verification step, and scoped permissions, built on a real repo.\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eThe fan-out\u003c\/b\u003e: independent work sent to parallel subagents, with the results merged back clean.\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eThe weekend ship\u003c\/b\u003e: one real product, idea to running software, in a single weekend.\u003c\/li\u003e\n\u003c\/ul\u003e\u003cp\u003eRead it and you will hand off work you do not have to re-read, catch the green lie before you act on it, and ship a real product over one weekend, the way the people you assumed were lying actually do it.\u003c\/p\u003e\u003cp\u003eFor developers who can already code and are a few weeks into using a coding agent seriously. You have watched it break something with complete confidence, and maybe lost a Saturday to the revert. Part of the AI and Agentic Engineering series.\u003c\/p\u003e\u003cbr\u003e\u003cbr\u003e\u003cb\u003eAuthor:\u003c\/b\u003e Wes Halloran\u003cbr\u003e\u003cb\u003eISBN-13:\u003c\/b\u003e 9798181720947\u003cbr\u003e\u003cb\u003ePublisher:\u003c\/b\u003e Independently Published\u003cbr\u003e\u003cb\u003eLanguage:\u003c\/b\u003e English\u003cbr\u003e\u003cb\u003ePublished:\u003c\/b\u003e 06\/15\/2026\u003cbr\u003e\u003cb\u003ePages:\u003c\/b\u003e 158\u003cbr\u003e\u003cb\u003eFormat:\u003c\/b\u003e Paperback\u003cbr\u003e\u003cb\u003eWeight:\u003c\/b\u003e 0.48lbs\u003cbr\u003e\u003cb\u003eSize:\u003c\/b\u003e 9.00h x 6.00w x 0.34d","brand":"Wes Halloran","offers":[{"title":"Paperback","offer_id":49084234531071,"sku":"9798181720947","price":24.99,"currency_code":"USD","in_stock":true}],"url":"https:\/\/www.whiterainbookhouse.com\/products\/claude-code-in-action-wes-halloran-9798181720947","provider":"WR Book House","version":"1.0","type":"link"}