● Field Notes · published continuously

Short notes from inside the engine.

Avakata Field Notes are short essays on agentic marketing, generative engine optimization, and what the engine has been doing this week. Some are written by Ryan. Some are written by the engine, edited by Ryan, and clearly marked.

The Operator’s Brief · weekly

Want the move, not just the news?

Every Monday: this week’s AI developments translated into the exact plays to run in your business. First issue free.

Get the Brief →
The full archive · 90 notes

Every note, in running order.

  1. 01 Jul 18 The 90-minute website audit you can run yourself ● Today
  2. 02 Jul 17 Case note: the F-grade site that hit a B in fourteen days ● Today
  3. 03 Jul 16 Entity SEO: making your brand a thing machines know ● Today
  4. 04 Jul 15 Prompt injection is a supply-chain problem ● Today
  5. 05 Jul 14 Engine log: the week the palette learned restraint ● Today
  6. 06 Jul 13 The client report nobody reads — and the one-line memo they do ● Today
  7. 07 Jul 12 How answer engines pick between two similar sources ● Today
  8. 08 Jul 11 Case note: 30 days of per-client learning on a Shopify store ● Today
  9. 09 Jul 10 The compounding content queue: never miss a publishing day again ● Today
  10. 10 Jul 9 FAQ blocks that get quoted: structure, length, phrasing ● Today
  11. 11 Jul 8 Tool use is the new API design ● Today
  12. 12 Jul 7 Engine log: teaching the brain to write in a client's brand voice ● Today
  13. 13 Jul 6 When not to automate: a decision framework ● Today
  14. 14 Jul 5 The solopreneur's playbook for Claude Fable 5: what $10/$50 pricing actually buys you ● Today
  15. 15 Jul 5 Claude Fable 5 is back worldwide: the two-week ban, what it is, and why it matters ● Today
  16. 16 Jul 5 Being the source: writing statistics AI engines quote ● Today
  17. 17 Jul 4 Case note: the booking conversation that outconverted the contact form ● Today
  18. 18 Jul 3 Agent memory: what to persist, what to forget, what to never store ● Today
  19. 19 Jul 2 Freshness signals: why updatedAt is the cheapest citation lever ● Today
  20. 20 Jul 1 Q3 capacity math for a solopreneur running agents ● Today
  21. 21 Jun 30 Engine log: June in review — what shipped, what learned, what got reverted ● Today
  22. 22 Jun 29 How AI crawlers actually read your site (and what they skip) ● Today
  23. 23 Jun 28 Human-in-the-loop without becoming the bottleneck ● Today
  24. 24 Jun 27 The one-person agency org chart, drawn as software ● Today
  25. 25 Jun 26 Case note: reviving a dead service page with answer-first rewrites ● Today
  26. 26 Jun 25 The five schema.org types that actually move AI citation ● Today
  27. 27 Jun 24 Engine log: what the bandit learned from 10,000 impressions ● Today
  28. 28 Jun 23 Pricing agentic work when the labor is robotic ● Today
  29. 29 Jun 22 Six agent failure modes and the guardrails that catch them ● Today
  30. 30 Jun 21 The llms.txt file: what it is and exactly what to put in it ● Today
  31. 31 Jun 20 The AI solopreneur's weekly operating rhythm ● Today
  32. 32 Jun 20 How to use AI to build a personal brand that gets cited ● Today
  33. 33 Jun 19 The case for running your business on fewer, better AI systems ● Today
  34. 34 Jun 19 The solopreneur's guide to AI-powered project management ● Today
  35. 35 Jun 18 What Perplexity actually looks for when it cites a source ● Today
  36. 36 Jun 18 How to use AI to onboard clients faster and retain them longer ● Today
  37. 37 Jun 17 The AI tools worth paying for in 2026 (and the ones that are not) ● Today
  38. 38 Jun 17 How to build an AI-powered newsletter as a solopreneur ● Today
  39. 39 Jun 16 How to get your website cited in Google AI Mode ● Today
  40. 40 Jun 16 The AI solopreneur's guide to pricing and positioning ● Today
  41. 41 Jun 15 How agentic AI is changing what it means to be a founder ● Today
  42. 42 Jun 15 Why AI-generated content fails (and the three fixes that work) ● Today
  43. 43 Jun 14 The AI content calendar: how to plan a month of posts in two hours ● Today
  44. 44 Jun 14 How to use AI to run your finances as a solopreneur ● Today
  45. 45 Jun 13 What the best AI solopreneurs have in common ● Today
  46. 46 Jun 13 The solopreneur's guide to AI-powered customer support ● Today
  47. 47 Jun 12 How to measure whether your AI is actually working ● Today
  48. 48 Jun 12 AI and the solopreneur's biggest fear: losing the human touch ● Today
  49. 49 Jun 11 The compounding advantage: why starting your AI stack now matters ● Today
  50. 50 Jun 11 How to write a brand brief that makes AI sound like you ● Today
  51. 51 Jun 10 AI for solopreneurs: the honest guide to what works and what does not ● Today
  52. 52 Jun 10 How to use AI to deliver better client work in less time ● Today
  53. 53 Jun 9 The future of work is not AI replacing you. It is AI reporting to you ● Today
  54. 54 Jun 9 From overwhelmed to operational: a solopreneur's 90-day AI reset ● Today
  55. 55 Jun 8 The GEO audit: how to check if AI engines can find your content ● Today
  56. 56 Jun 8 How to run a one-person sales operation with AI ● Today
  57. 57 Jun 7 Why the next wave of AI will make solopreneurs more competitive, not less ● Today
  58. 58 Jun 7 The AI solopreneur's guide to client acquisition ● Today
  59. 59 Jun 6 What solopreneurs get wrong about AI automation ● Today
  60. 60 Jun 5 How to use AI to write content that gets cited, not just ranked ● Today
  61. 61 Jun 5 The AI skills that will matter in five years (and the ones that will not) ● Today
  62. 62 Jun 4 Stop using AI as a search engine. Start using it as a thinking partner ● Today
  63. 63 Jun 4 How AI changes the economics of a one-person consulting business ● Today
  64. 64 Jun 3 Decision fatigue is the real AI problem. Here is the cure ● Today
  65. 65 Jun 3 The AI solopreneur stack for 2026: what we actually run ● Today
  66. 66 Jun 2 Why your AI outputs sound generic (and how to fix it in one prompt) ● Today
  67. 67 Jun 2 Running a one-person marketing department with AI ● Today
  68. 68 Jun 1 How to pick your first AI agent without wasting a month ● Today
  69. 69 Jun 1 AI search is replacing Google for 40% of queries. Here is what to do ● Today
  70. 70 May 31 The solopreneur content machine: publish daily without burning out ● Today
  71. 71 May 31 Your AI stack is only as good as your evaluation layer ● Today
  72. 72 May 30 Agentic AI in 2026: what it means for your business right now ● Today
  73. 73 May 30 How to build a prompt library that actually saves you time ● Today
  74. 74 May 29 The shiny object trap: why most solopreneurs never get AI working ● Today
  75. 75 May 29 GEO for solopreneurs: how to get cited by ChatGPT and Perplexity ● Today
  76. 76 May 28 Five business functions a solopreneur can hand to AI today ● Today
  77. 77 May 28 The AI future of business is already here. Most companies are not in it ● Today
  78. 78 May 27 How to make AI work for you in the next 30 days ● Today
  79. 79 May 27 What AI agents actually do all day ● Today
  80. 80 May 26 AI overload is real. Here is how to stop drowning in it ● Today
  81. 81 May 26 The one-person business is no longer a compromise ● Today
  82. 82 May 25 Why citation is the new ranking ● Today
  83. 83 May 24 The case for boring agents ● Today
  84. 84 May 23 14 changes shipped this week. Here is the diff ● Today
  85. 85 May 19 Freshness stamps are a ranking signal for LLMs ● Today
  86. 86 May 14 Five-person agency, one engine ● Today
  87. 87 May 9 Why the orchestration graph stays a black box ● Today
  88. 88 May 2 Three rollbacks. None of them ours ● Today
  89. 89 Apr 28 The critic gate matters more than the writer ● Today
  90. 90 Apr 20 Hiring an in-house AI lead. What to insist on ● Today
SEO GEO DATA FLOW →
● Featured · Strategy

The 90-minute website audit you can run yourself

This is the audit we run on discovery calls, converted into a timed solo exercise: 15 minutes on crawler access, 25 on extractability, 20 on identity signals, 20 asking the engines directly, and 10 building a punch list ordered by effort. Most fixes need an editor, not an engineer.

Topic
The field, mapped

90 notes, one brain.

Case noteJul 17
Case note: the F-grade site that hit a B in fourteen days

An HVAC contractor ran our free homepage grader and scored 31 out of 100, with sixteen of 22 checks failing. Fourteen days of fixes later the site regraded at 82, and Perplexity began citing it for local service queries. Here is the day-by-day log.

6 min readRyan W.
GEOJul 16
Entity SEO: making your brand a thing machines know

If ChatGPT cannot say what your brand is, you have an entity problem, not a content problem. Here is the process we run: a five-engine baseline test, one canonical sentence, Organization schema with sameAs links, a parseable about page, and the 60-day timeline it honestly takes.

6 min readRyan W.
AgenticJul 15
Prompt injection is a supply-chain problem

Prompt injection is not a prompt-writing problem. Every page, email, and PDF your agent reads is an unvetted dependency with a stranger as maintainer. Here is the supply-chain posture we run: mapped inputs, least-privilege tools, a quarantine airlock, and human gates on the irreversible three.

6 min readRyan W.
● Engine logJul 14
Engine log: the week the palette learned restraint

Bounce rose six points where our engine's hero animations got loud, so the system cut its own motion and palette theatrics across nine sites — and wrote the restraint into policy. A dispatch on calm as a learned behavior, with the numbers that taught it.

6 min readRyan W.
StrategyJul 13
The client report nobody reads — and the one-line memo they do

We spent six hours a month on a fourteen-page client report that earned 47 seconds of attention. We replaced it with a one-sentence memo — change, cause, next move — and reply rates hit 78%. Here is the formula, three real examples, and the two times a year the long report still matters.

6 min readRyan W.
GEOJul 12
How answer engines pick between two similar sources

When two pages make the same claim, an answer engine cites one and ignores the other. We ran 60 paired buyer prompts across three engines to find the tie-breakers. Four signals decided almost every head-to-head, and most are fixable in an afternoon.

6 min readRyan W.
Case noteJul 11
Case note: 30 days of per-client learning on a Shopify store

A nine-person Shopify home fragrance brand turned on per-client learning June 1. Thirty days later: organic sessions up 18 percent, AI citations up from 2 to 19 a month, edit rate down from 70 to 12 percent, and the owner's content time cut from six hours a week to 50 minutes.

6 min readRyan W.
StrategyJul 10
The compounding content queue: never miss a publishing day again

Publishing daily is an inventory problem, not a discipline problem. A 14-day queue of finished posts absorbs sick days, launches, and client crunches, refilled by two 90-minute batch sessions a week. Here is the full system, including the 20-minute weekly review that runs it.

6 min readRyan W.
drag the cards · the engine routes between them