--- title: 1682 Conference: The PB&J Principle | daily.dev description: Wawa's customer experience team spent 12 weeks running workshops with 26 participants to surface over 550 customer and associate friction points, then coded... canonical: https://daily.dev/posts/1682-conference-the-pb-j-principle-wd92ccrjz twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: 1682 Conference: The PB&J Principle | daily.dev og:description: Wawa's customer experience team spent 12 weeks running workshops with 26 participants to surface over 550 customer and associate friction points, then coded... og:url: https://daily.dev/posts/1682-conference-the-pb-j-principle-wd92ccrjz og:image: https://api.daily.dev/og/posts/Wd92CCRjz.png og:image:alt: 1682 Conference: The PB&J Principle og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # 1682 Conference: The PB&J Principle **[RUBYLAND](https://daily.dev/sources/rubyla)** · 13 min read · 1 upvotes · 0 comments ## Summary Wawa's customer experience team spent 12 weeks running workshops with 26 participants to surface over 550 customer and associate friction points, then coded each one with attributes like context, affected parties, and underlying need, before trying to feed that structured data to AI. Mike Pitone, who led the project, argues the hard part wasn't prompt design but making the context detailed enough for a model to use, comparing vague AI requests to kids literally following PB&J sandwich instructions. The team is now designing multiple agents (intake, connection, journey, storytelling, alignment) on top of that coded data, with two pilots underway and human judgment kept as a check on AI output. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How many customer friction points did Wawa identify before building AI agents for customer experience? Wawa's customer experience team identified more than 550 friction points through five internal workshops with 26 participants held over 12 weeks. Of these, 355 affected customers, 145 affected associates, and 55 affected the company's corporate campus, nicknamed 'Red Roof'. The team coded each friction point with attributes like context, evidence source, and underlying need before considering how AI could help. _Teams structuring customer feedback before layering on AI can track approaches like this one on daily.dev._ ### Why does AI struggle to give useful answers even when given a clear request? Vague requests to an AI model produce vague, unreliable output because the model lacks enough context to understand the real situation, much like a child literally following written instructions for making a peanut butter and jelly sandwich. Mike Pitone of Wawa argues the fix isn't better prompt design but being far more descriptive with the context you give the model, including who's affected, where an issue happens, and what need it blocks. _Developers refining how they feed context to coding assistants can follow more framing like this on daily.dev._ ## Similar posts on daily.dev - [AI workslop is a standards problem](https://daily.dev/posts/ai-workslop-is-a-standards-problem-huzhxa4kt) · Atlassian · 1 upvotes · 0 comments - [thoughtbot at Just Product 2025](https://daily.dev/posts/thoughtbot-at-just-product-2025-qfup3kc8g) · thoughbot · 0 upvotes · 0 comments - [Building AI agents for 127 million customers](https://daily.dev/posts/building-ai-agents-for-127-million-customers-yk2dcgusz) · Nubank · 1 upvotes · 0 comments - [The Brain Sandwich](https://daily.dev/posts/the-brain-sandwich-1xznwdvve) · Terrible Software · 36 upvotes · 8 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#prompt-engineering](https://daily.dev/tags/prompt-engineering) [View this post on daily.dev](https://daily.dev/posts/1682-conference-the-pb-j-principle-wd92ccrjz) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"1682 Conference: The PB\u0026J Principle","url":"https://daily.dev/posts/1682-conference-the-pb-j-principle-wd92ccrjz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/1682-conference-the-pb-j-principle-wd92ccrjz"},"datePublished":"2026-10-27T18:25:12.019Z","dateModified":"2026-10-27T19:01:45.265Z","description":"Wawa's customer experience team spent 12 weeks running workshops with 26 participants to surface over 550 customer and associate friction points, then coded...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/fd53c1b47fad51cb226a9f859f9a2996?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/fd53c1b47fad51cb226a9f859f9a2996?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"RUBYLAND","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"RUBYLAND","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/rubyla","url":"https://daily.dev/sources/rubyla"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/1682-conference-the-pb-j-principle-wd92ccrjz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,prompt-engineering","timeRequired":"PT13M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"RUBYLAND","item":"https://daily.dev/sources/rubyla"},{"@type":"ListItem","position":3,"name":"1682 Conference: The PB\u0026J Principle"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/1682-conference-the-pb-j-principle-wd92ccrjz#faq","mainEntity":[{"@type":"Question","name":"How many customer friction points did Wawa identify before building AI agents for customer experience?","acceptedAnswer":{"@type":"Answer","text":"Wawa's customer experience team identified more than 550 friction points through five internal workshops with 26 participants held over 12 weeks. Of these, 355 affected customers, 145 affected associates, and 55 affected the company's corporate campus, nicknamed 'Red Roof'. The team coded each friction point with attributes like context, evidence source, and underlying need before considering how AI could help. Teams structuring customer feedback before layering on AI can track approaches like this one on daily.dev."}},{"@type":"Question","name":"Why does AI struggle to give useful answers even when given a clear request?","acceptedAnswer":{"@type":"Answer","text":"Vague requests to an AI model produce vague, unreliable output because the model lacks enough context to understand the real situation, much like a child literally following written instructions for making a peanut butter and jelly sandwich. Mike Pitone of Wawa argues the fix isn't better prompt design but being far more descriptive with the context you give the model, including who's affected, where an issue happens, and what need it blocks. Developers refining how they feed context to coding assistants can follow more framing like this on daily.dev."}}]} ```