Hacker ApprovedDepartments

Agentic Engineering Patterns

Agentic Engineering Patterns by Simon Willison

by Simon Willison

Shares rank 12 of 21 software engineering books by recommenders

Recommended for responsibly applying AI in software development. Main caveat: critics say the patterns go out of date quickly.

Recommended for responsibly applying AI in software development. Main caveat: critics say the patterns go out of date quickly.

7 people gave an opinion

recommend it
5
criticize it
2
approval share
71%
Each figure is one person. RecommendsCriticizes

Recommended in 3 of 13 months

  1. November 2025: not recommended
  2. December 2025: not recommended
  3. January 2026: not recommended
  4. February 2026: not recommended
  5. March 2026: recommended
  6. April 2026: not recommended
  7. May 2026: not recommended
  8. June 2026: recommended
  9. July 2026: not recommended
  10. August 2026: recommended
  11. September 2026: not recommended
  12. October 2026: not recommended
  13. November 2026: not recommended (month in progress)

Why it doesn’t carry the badge

  • 5 people recommend itNeeds 10 or more, not met.
  • 2.5 recommenders for every criticNeeds 2 to 1 or better, met.
  • Recommended in 3 of 13 monthsNeeds 4 or more, not met.

The same three rules apply to every product, and the badge can’t be bought. How the badge works

What people say about it

The reasons people give, with the number of comments that give each one. Open a reason to read what they said.

Why people recommend it

Each mark is one comment

  • Trusted author; good place to start

    “simon's agentic series is a good place to start”

    Comment from 11 Jun 2026 in “Policy on the AI Exponential”

    “even though I love Simon's contributions”

    Comment from 4 Mar 2026 in “Agentic Engineering Patterns”

What people warn about

Each mark is one comment

  • Content goes out of date quickly

    “Without this, I believe the book's content will be less relevant in 3 months”

    Comment from 23 Aug 2026 in “Software Engineering in the Agentic Era”

    “These patterns are all out of date by at least a year”

    Comment from 4 Mar 2026 in “Agentic Engineering Patterns”

Other software engineering books people recommend

The four most recommended other software engineering books, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.

Agentic Engineering Patterns by Simon Willison compared with 4 alternatives
ProductRecommendCriticizeApprovalMonthsOwnedBadge
The Mythical Man-Monthby Fred Brooks56395%12—Approved
Designing Data-Intensive Applicationsby Martin Kleppmann37197%12—Approved
A Philosophy of Software Designby John Ousterhout28197%11—Approved
Code Completeby Steve McConnell140100%7—Approved
Agentic Engineering Patternsby Simon WillisonThis page5271%3——
See all 21 software engineering books, ranked

What people said

7 of the 8 comments that mention it, newest first. Each links to the original comment.

“Without this, I believe the book's content will be less relevant in 3 months”

MixedComment from 23 Aug 2026 in “Software Engineering in the Agentic Era”

“simon's agentic series is a good place to start”

RecommendsComment from 11 Jun 2026 in “Policy on the AI Exponential”

“These patterns are all out of date by at least a year”

CriticizesComment from 4 Mar 2026 in “Agentic Engineering Patterns”

“I think your site will become an invaluable source for software engineers who want to responsibly apply AI in their development flow.”

RecommendsComment from 4 Mar 2026 in “Agentic Engineering Patterns”

“even though I love Simon's contributions”

RecommendsComment from 4 Mar 2026 in “Agentic Engineering Patterns”

“This chapter describes a technique for making code reviews less mentally burdensome”

RecommendsComment from 4 Mar 2026 in “Agentic Engineering Patterns”

“the ChatGPT generated test suite is not robust”

CriticizesComment from 25 Feb 2026 in “Writing code is cheap now”

Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.