BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Palaner//palaner Single Event//EN
METHOD:PUBLISH
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:meetup-c942597d96@palaner.app
DTSTAMP:20260802T162637Z
DTSTART:20260820T173000Z
DTEND:20260820T190000Z
SUMMARY:Dylan Lake + Dmitrijs Jurins + Daramola Benjamin
LOCATION:Bonded Warehouse
DESCRIPTION:Saved in Palaner as: saved\n\nPalaner match: 41% · why: lots of
  people going\n\nAs AI tooling evolves at an incredible pace\, one questio
 n keeps coming up: how do we build systems that last when the capabilities
  of the models themselves are changing every few months?\n\nThis month\, w
 e're joined by two speakers exploring different sides of that question. On
 e looks at the reality of building sophisticated AI engineering workflows 
 in a world where today's innovation can become tomorrow's built-in feature
 . The other looks further ahead\, asking how AI agents will fundamentally 
 change the identity layer of the web.\n\nWhether you're building developer
  tools\, AI-powered products\, or thinking about the future of agentic sys
 tems\, these talks will challenge some assumptions and provide practical i
 nsights into where AI engineering is heading.\n\nBuilding on Borrowed Grou
 nd: What I Learned Letting Anthropic Absorb My Work\nDylan Lake - Engineer
 \, Crown Gas & Power\n\nAs foundation models become more capable\, many of
  the workflows engineers painstakingly build eventually become native feat
 ures of the models themselves. Rather than seeing this as wasted effort\, 
 Dylan shares why the real value lies in the knowledge gained along the way
 .\n\nDrawing from his experience building multi-agent systems modelled on 
 real workplace structures\, Dylan explores the evolution of agent orchestr
 ation\, what happens when platform capabilities catch up\, and how to deci
 de when custom engineering still provides value.\n\nYou'll learn:\n\nWhen 
 to build custom AI workflows versus relying on model capabilities\nLessons
  from designing multi-agent orchestration systems\nHow AI tooling has evol
 ved over the last year\nWhere frontier models still provide unique advanta
 ges\nA practical framework for choosing the right tool for the job\n\n----
 --------------------------------------------------------------------------
 -\n\nBeyond the Pilot: Claude for the Other 90% - Dmitrijs Jurins\, Techno
 logy Director at Crown Gas & Power\n\nEveryone has an AI pilot — few turn 
 it into a company-wide operating model. Crown Gas & Power's Technology Dir
 ector shares how a mid-sized UK energy supplier rolled Claude out to non-e
 ngineers: the tiered adoption model\, the governance that kept the board c
 omfortable\, and the ROI that made it stick.\n\n--------------------------
 -----------------------------------------------------\n\nThe Intent Graph:
  Rebuilding Web Identity for the Agentic Internet\nDaramola Benjamin - Fou
 nder\, Levered\n\nFor years\, web applications have been built around beha
 vioural data—clicks\, sessions\, cookies and analytics. But what happens w
 hen AI agents become the primary users of our applications?\n\nDaramola in
 troduces the concept of the Intent Graph\, exploring how identity\, authen
 tication and authorisation may evolve in a world where autonomous agents r
 esearch\, negotiate and complete tasks on behalf of users.\n\nRather than 
 focusing on marketing or analytics\, this session takes a software enginee
 ring perspective on what AI-native products might require from the next ge
 neration of web architecture.\n\nYou'll learn:\n\nWhy behavioural tracking
  breaks down in agent-mediated workflows\nHow user identity differs from a
 gent identity and task identity\nThe role of OAuth-style permissions and s
 coped delegation for AI agents\nHow event schemas may evolve in AI-native 
 applications\nWhat developers should consider when building products for a
 n agentic web\n\n---------------------------------------------------------
 ----------------------\n\nWho Should Attend\n\nSoftware engineers\, archit
 ects\, platform engineers\, engineering managers and technical leaders int
 erested in AI-native software development\, agentic systems\, developer to
 oling and the future architecture of AI-powered applications.\n\nWhy It's 
 Worth Attending\n\nPractically AI is about sharing real engineering experi
 ences rather than product pitches. This month's talks combine lessons lear
 ned from building production AI systems today with thoughtful discussion a
 bout where AI platforms and web architecture are heading next. Whether you
 're building with LLMs already or planning your next AI-native product\, y
 ou'll leave with practical ideas\, fresh perspectives and plenty to discus
 s over pizza afterwards.\n\nAgenda\n\n18:30 – Doors\, pizza & mingling\n18
 :50 – Introductions + AI spotlight\n19:00 – Building on Borrowed Ground: W
 hat I Learned Letting Anthropic Absorb My Work - Dylan Lake\n19:15 – Q&A\n
 19.20 - Beyond the Pilot: Claude for the Other 90% - Dmitrijs Jurins\n19:3
 5 – Q&A\n19:40 – The Intent Graph: Rebuilding Web Identity for the Agentic
  Internet - Daramola Benjamin\n20:15 – Q&A\n20:30 – Open social & refreshm
 ents\n21:00 – Close
URL:https://www.meetup.com/practically-ai-applied-ai-for-software-engineers
 -manchester/events/315615663/
CATEGORIES:palaner,saved
STATUS:TENTATIVE
END:VEVENT
END:VCALENDAR