Zápisky:

• Agentforce vs. Coworker – jasné rozlišení. Coworker je skvělý pro jednoduché věci (sumarizace accountů, příležitostí), ale nedá se nijak nastavit. Agentforce má smysl tam, kde potřebuješ vlastní pravidla, metodiku a firemní kontext – například u case resolution asistenta, kde zákazník má přesná pravidla, co nabídnout v jakém případě.
• Prompt Builder ≠ Agent. Agent dělá vlastní rozhodnutí, volí nástroje a iteruje nad výsledkem. Prompt Builder je deterministický, levnější, předvídatelnější, vhodný pro jednoduché úlohy. V praxi se obojí kombinuje: agent volá prompt builder jako jednu ze svých akcí.
• Kalkulace flex kreditů je složitější, než vypadá. Spotřeba kreditů v build fázi (indexování dokumentů, opakované přestavování objektů kvůli omezeným možnostem editace) může být větší než v run fázi. Inteligent Context na PDF dokumentech je výkonný, ale kreditově velmi nákladný.
• Integrace s dalšími systémy jsou klíčový driver hodnoty. Zatímco dřív bylo propojení Salesforce s ERP nebo jinými systémy “hezká věc do UX”, s AI se to dramaticky mění – agent, který vidí do více systémů najednou, může dávat výrazně hodnotnější odpovědi a doporučení. Proto mohou projekty stát víc, ale přidaná hodnota je tomu adekvátní.
• Agentforce vyžaduje hlubší porozumění byznys procesu než klasická implementace. Instrukce, popisy a pravidla agentů jsou životně důležité. Konzultant musí fakt rozumět názvosloví klienta a byznys logice – nestačí vědět, “které políčko se jmenuje jak.” A současně je možné použít LLM aby celého agenta vygenerovalo, Agent Script je v tomto případě skvělý (Trick or Trailhead badge to krásně ukazuje v praxi).
• Skills v Claude a jejich sdílení napříč firmou jsou velká nevyřešená výzva. Je snadné napsat skill, těžší napsat robustní skill (např. timesheet skill musí brát všechny lidi na projektu, ne konkrétní jména). Ještě těžší je sdílení a governance skillů napříč týmem – nutí firmu k dohodám, které dosud nepotřebovala. A pořád je dobré otevřít i skill, který si Claude vygeneroval a zkontrolovat, jak je napsaný.
• Dvě velká témata pro příštích 12 měsíců: UI rozhraní a týmoví agenti. Budoucnost není jen chatové rozhraní – hlas (testováno při řízení/běhání) bude dalším rovnocenným kanálem. A zásadní skok nastane, až agenti přestanou být nástrojem osobní produktivity a stanou se plnohodnotnými členy projektových týmů se sdíleným kontextem.
• Ranní audio brief jako inspirativní use case. Příklad Filipa Molčana: agent každé ráno vygeneruje 5–6minutový zvukový souhrn, který nekombinuje jen zprávy, ale kříží kalendář, Slack a emaily – upozorní třeba na konflikt mezi schůzkou a nedodrženým slibem z minulého měsíce. Klíčové: kontext rozšířený o 20% může přinést násobně vyšší nárůst kvality výstupu.
• Sledování trendů přes automatizaci + komunitu. Adam má skill, který mu jednou týdně přečte novinky z Agentforce a LLM světa a pošle mu shrnutí mailem. Druhý pilíř je komunita – v prostředí, kde Agentforce vydává update každý týden (na rozdíl od Salesforce 3× ročně), je to jediný způsob, jak držet krok.

What a great book, which Lars wrote even before the AI hit stage. I’m saying that because while the book is really good, it could be also blog post only, so I really admire how Lars have been able to extend the text and repeat it in several different ways that it doesn’t really look like a repetition

Jokes aside, the book is extremely important as it shows the patterns you might consider to be ok-ish and don’t foresee their whole impact.

Anti-pattern is a pattern that occurs in unsuccessful sofrware systems or projects that can look superficially like a good solution but in practice gets you into trouble.

I really loved a lot of them:

• Heroes don’t scale
• Be careful about suggesting big bang delivery approaches as it very frequently occurs where the digital transformation lacks strong leadership, so it will all fail at the end – spectacularly
• Just Do It!
• Stovepipe – respect the organization and as it is currently siloed and do nothing about it
• Intense coupling which results on waiting time for the other system(s)
• (Ungoverned) Org Proliferation where multiple partners implement their own small part of your overall instance. Great question on the CTA board, which probably never goes properly in depth
• Data export for further processing and ultimately their loss – you should aim to use compliance as a tool to become more secure and more security-aware, not as a way to get security out of the way because you’ve ticket all the boxes
• Declarative Is Always Safe! Still it might not mean that it is safe solution. I didn’t know for example that if user has access to All Flows list (and now with the Automation App it is way more common than before) they can run any of them – are you ready for that? Check great (and long) article by Aaron Costello on this topic
• Spaghetti Sharing Model – sharing can get super complicated in big orgs and I would say you really need to use Roles (or Territory Management) to help you with setting the security not in a way how the company works internally
• Use Custom Objects when possible – wrong! Overuse „Hero objects“ (the oldest of oldest such as Account, Contact, Lead, Opportunity) might be wrong as well
• Ignoring ecosystem and building where buying would be better – personally seen in and saved a lot of money to customer when I proposed the document generation solution instead of hardcoding tens or hundreds of VisualForce pages. Also building only for you means no additional development unless you will pay for it and come with the ideas
• License-based solutioning, shadow objects, etc – still there sometimes, the price push is being stronger and stronger with every price increase. But it is also about using external sites and pushing data across when it would be better to just use Experience Cloud
• Assumption-driven customization where you don’t have access to the „right“ stakeholders and depends on just part of them
• Golden Hammer (love the name!) – saw it way too often especially with junior admins who learnt something and then used it again and again for all use-cases. Also are you looking for problems you can solve with your tech stack or you start with the problem and then try to find the solution?
• Don’t depend on POCs as they are easy to get right but they are typically very limited and hard to switch for real business use case
• MINO (Middleware In Name Only) where you basically map APIs 1:1. I would say the whole integration anti-patterns are lighter in their better approach than the rest of the book and I really wonder how some of the example solve in a better way
• Enormous interface which basically can do everything but is hard to extend due to its size and complexity
• Chatty Integration which just triggers so often the other system is not able to handle it. I really love the idea of proactively asking the other system about its performance and intentionally add delay on SF side to not overload it
• Integration pattern monomania is one of the patterns where I would love to see more details about better solution. I know all the different integration patterns, but seeing it applied to the example in the book would be just awesome
• Groundhog day anti-pattern is when you just repeat yourself a lot because you don’t really try to find the underlying reason of the question. And you might not have the right communication strategy for the right audience – highly visual and engaging material might be great for workshop with general audience but for technical audience you need to have the precise and technically correct materials in a format they understand and typically use

Don’t postpone decisions beyond the latest point it makes sense to take them, even if making a decision is hard.

Two great links with additional anti-patterns – C2 and DevIQ.

While highly repetitive it is great at the same time as it shines the light on the topics from different angles and I would highly recommend the book for your library (and reading) just to be aware of all those moments when it felt like a good decision but long term probably isn’t that great.

Winter will hit (my customers‘ instances) during this weekend and if you are in similar situation you can still be prepared for that.

1100+ pages but at the end if feels like all the important things have been pushed to production during summer (passkeys, report exports needs to be confirmed by 2FA and a few more) and the regular release is about a lot of things in flow but otherwise mainly about some smaller features.

My top 3

• Make Inline Editing in List Views More Flexible
• Preview Records from Lightning Reports Without Losing Context
• Filter Collections Without Loop Elements

And here is the rest of interesting things (to me):

• Search Google Workspace in Real Time with Federated Search in Agentforce Coworker
• easier deployment of agents with new (simplified) metadata structure – when I saw AiAgentDefinitionVersion I had to smile as I recalled FlowVersion which has been discountinued after being used for some time
• Builder Central (Beta) – if all the code generated by LLMs isn’t enough and you don’t want to stop with Agentforce Vibes, you can use this new functionality to generate your app based on a prompt. Also new skills for Claude Code
• send emails from Scratch orgs with unverified email addresses – just add EmailAuthorizationSettings.enableSubstituteFromAddress to your scratch org definition file
• Hyperforce Is Coming to Google Cloud Platform (GCP) – US only
• Data 360 No Longer Required for Setup with Agentforce – I probably wonder why it was need in the beginning and what it means for the future
• Manage Multiple Users at Once in Setup with Agentforce – exactly the use-case I had back then and rather used Claude to do it, glad now I can use it natively in SF
• Explore 124 More Objects in Setup with Agentforce or Explore 190+ More Objects in Setup with Agentforce or Explore Over 100 Additional Objects in Setup with Agentforce – not sure but I love numbers so this catched my attention. Still wonder why it cannot support everything right away
• Track Where Your Tableau Next Dashboards Are Embedded
• Loyalty Management – Optimize Storage with Just-in-Time Member Currency Record Creation – I remember the surprise when I found during our user group about the Loyalty Management that you need to create these records in all possible currencies even though they might not be ever used
• Find Slack and Tableau Solutions in AgentExchange

Flow

• Build Flows Faster with Auto-Generated Element Labels – feels cheap that the name will be auto generated and somehow auto generation of description feels more useful
• Group Elements to Organize and Simplify Flows – looks like complex flows will be easier to oversee
• Filter Collections Without Loop Elements – again I hit it today that the filter doesn’t return collection but I need to somehow filter over it. Now we have this new resource type we can use

• Monitor Flow Performance Right on the Canvas – need to be enabled in Process Automation Settings but doesn’t need Data 360 anymore – feels like the Data 360 goes slowly away or what?
• Reduce Flow Failures Caused by Record Lock Contention – somehow had a feeling it was new in last release, but probably not
• Process Multiple Records with Screen Flows from List Views and Related Lists – it was possible also before but now it is more admin friendly
• Test Flows in Isolation with Mock Outputs for Action and Subflow Elements (Beta) – while Apex goes with @IntegrationTest which calls the endpoint during test instead of using mocks (as we needed so far), flow goes in the other direction

Data 360

• Ingest Microsoft OneNote Content into Data 360
• Connect Data 360 to Databricks on Azure with a Salesforce-Managed Private Network Route
• Data 360 Engagement Timeline – migrate from previous component (Data Cloud Profile Engagements widget)
• Activate Audiences to Reddit – didn’t realize this site is so crucial that even Salesforce will support it

Field Service

• so many things got fixed over last months but I’m not sure I’m seeing the same information for other clouds, which is a bit sad
• Seamlessly Book and Schedule Multiday Service Appointments – it was pain historically as the multi day appointments were hard to schedule but seems like finally they found a way how to handle them better
• Improve Productivity and Efficiency by Optimizing Multiday Service Appointments
• Orchestrate Complex Work Chains Seamlessly in the Scheduling Console

Education Cloud

• Share Billing Details with Your Students – Revenue Cloud Advanced is needed, but seems that the Educational Institutions have a lot of potential to improve their processes with Salesforce
• Spread Tuition Payments with Flexible Payment Plans
• Resolve Student Absences with the Attendance Management Agent including Slack integration
• Automate Faculty Access to Course Data with a Standardized and Secure Model – meaning also that access to course will be automatically withdraw from the tutor at the end of the semester
• Plan Your Academic Calendar with AI Tools, Build Your Course Catalog with AI Tools – those two or three usecases for AI are amazing to see, the data preparation for these things was super time consuming

Marketing Cloud

• Choose the Best Image with Recommenders – no more guessing by the marketer, leave this work to AI
• Route Outbound Emails Through Your Own Mail Servers instead of using Salesforce’s ones
• View an Email as a Web Page – probably never realized it isn’t there and I use it a lot especially for some newsletters
• Define Content Requirements for Distributed Marketing and Alerts – we can allow Sales people to use our templates and still control whether they included mandatory phrases in the email (this is not an investment recommendation for example)
• Personalize and Send Distributed Marketing Messages at Scale
• Show or Hide Dependent Form Fields Based on User Input
• Connect Forms and Landing Pages to More Data Sources – looks like now we can connect it directly to Salesforce instead of pushing everything into Data 360
• Automatically Update Consent Data in Record-Triggered Flows – they didn’t work before and we had to use event-triggered ones
• Skip the Wait When Sending Emails to Contact and Lead Lists – no more need for waiting for segment refresh and everything else what Data 360 has to do before send
• Extend Marketing Cloud Next Access to Platform Plus Users – the Campaign object was always the reason to go with Sales (or Service) Cloud license, now we can use the cheaper one. Still they won’t provide it to only the regular Platform license which is the cheapest

Developers

• Handle Larger Datasets with Increased Apex Heap Limits – 6->10, 12->25 – this is probably bigger than it sounds
• Avoid Workflow Disruptions by Enabling Elastic Limits for Batch Jobs (Beta)
• Test External Services and HTTP Callouts in Apex Integration Tests (Developer Preview) – no more needs for mocks? See Bob’s article
• Get Compiler Warnings for Apex API Versions 9.0 Through 19.0
• Assign Use Any API Auth Permission for SOAP login() (Release Update)
• Simplify REST API Version Management – finally we can put the „latest“ in the URL instead of specifying concrete version and then tell the other party they should update it for the new one
• Compare Values Between Fields in SOQL (Beta) – no more need for formula field?
• Web Console instead of Developer Console, which can be still enabled
• Send Site Emails from a Verified Address with Email Domain Substitution – for Experience Cloud it wasn’t required so far, now we have it here as well
• Send Sensitive Emails Securely with a Secondary Sender Email Address – this one is interesting as it can send sensitive emails (like Forgot password emails) directly from Salesforce servers rather than utilizing your relay server which can save the email somewhere

Admins

• Make Inline Editing in List Views More Flexible – any field (even those which are not on page layout) and record type limitation removed – need to be enabled in setup and while I love the former I don’t like the first one, but the enablement is divided between those two so all good
• Build Reusable Quick Action Experiences with Page-Based Quick Actions (Beta) – we will be able to create a „pallet“ of quick actions we want to use across Lightning Pages and then easily add everywhere. Taking into account it will support visibility rules this might be really handy!
• Filter joined reports with Common Rows Only (Beta) to show only the records that actually match
• Preview Records from Lightning Reports Without Losing Context (Beta) – feature which needs to be enabled in setup, but wow, no more opening of records in new tabs!

• Accelerate Meeting Follow-Ups with AI Suggested Actions
• Leverage Hybrid Cloud and On-Device AI Audio Processing
• Capture Post-Meeting Insights with Voice Notes
• Use Call Coaching on Video Calls to Drive Seller Success
• Keep Manual Shares When Transferring Records – before the manual shares have been removed when record owner has been changed, now they can stay. Setting which needs to be enabled in Setup
• Import Authorized Email Domains into a Sandbox – they didn’t transfer before and have to be added after each sandbox refresh
• Fine-Tune Which Emails and Events to Exclude from Einstein Activity Capture
• Connect Partner Portal Users‘ Calendars with Einstein Activity Capture
• Manage Stakeholder Details and Connections in Relationship Maps

Service

• Agentforce IT Service – while ServiceNow is moving into the CRM sphere Salesforce goes the other way. I didn’t have time yet to dive deeper into the IT Service module but it seems more powerful release by release
• Generate Enhanced Case Summaries in Five More Languages in Czech
• Easily View Original Case Attachments Inline in Case Details – they aren’t stored in separate files anymore but visible right at the original email (needs to be enabled)
• Reduce Storage Bloat and Keep Records Clear by Deleting Outdated Case Milestones – previously they were not removed from closed cases
• Reuse Modular Content Across Articles with Knowledge Blocks
• Prevent Duplicate Articles with Knowledge Similarity

Slack

• Sell Smarter in Slack: Agentforce Sales and the New Go Page
• Search, Summarize, and Take Action with Slackbot in Salesforce – I still have to find out how to explain to users when it is better to use what

What Others Found

• Jennifer W. Lee
• SalesforceBen – 12 features to share with your team + more articles on other clouds
• ApexHours
• Ceili
• Salesforce Time
• JM on Revenue Cloud features
• ForceNotes – what an awesome site to stay up-to-date or use MCP to tell you what is crucial for your instance
• Release Navigator which can also automatically generate for you a user story

The relevant trailmix on Trailhead is good but I would say far from comprehensive enough for the certification. Compared to the other marketing certifications/products there is one HUGE benefit – you can play with the actual product and really put your hands on it.

Much better was the practice exam prepared by Nobuyuki and Rodrigo. After passing the test I got a feeling that the exam will be mainly about Data360 and not really about the MCN (or whatever is the agreed acronym).

But the best learning at the end I’ve got from Nobuyuki’s blog. Basically every single question from the exam has an article on his blog where he describes in details how it works, what it can do, how to configure it.

Compared to the other marketing certifications this one is probably the most complex and it shows what will be needed from the marketers of future. It isn’t just about the Marketing Cloud, you also have to have pretty deep understanding of Data360 and some basics of Sales Cloud at least around the consent management. Also it includes all the things we didn’t really have to worry about and distinguish between so far – there are like 5 different types of flows (I know, should be easy job for me to distinguish between them) where each of them can be used in different situation. On top of that, if I got it right, some of them has been renamed in the meantime so the old articles call them differently. On-Demand, Broadcast, Audience, Segment, … and if that’s not enough you also need to distinguish between Marketing Cloud flows, Data360 flows and regular platform flows. Uff, not an easy job to absorb all of that.

And I completely forgot to speak about the AI which is included and you need to know what is the name and capabilities of each agent or how to configure Conversational Marketing which actually start with the core platform configuration.

Anyway, one failure later I can claim myself certified in this new product and really looking forward to see it on a real project and how easily the marketers will absorb all the knowledge and will be able to fully use what the platform offers.

Zápisky:

• Chybějící projektový manažer na straně klienta byl největší chybou, interní lidé (prorek­tor + kvestor) museli projekt vést popř. vedle svých hlavních rolí, hromadily se resty a projekt se brzdil.
• Dvě předchozí implementace skončily fiaskem.
• Oddělení předimplementační analýzy od samotné implementace se vyplatilo.
• Education Cloud byl v době implementace ještě „dítě,“ řada funkcionalit, které sliboval marketing, buď neexistovala, nebo nefungovala dostatečně. Klíčové moduly (registrace předmětů, studijní plány) musely být naprogramovány znovu na míru.
• Anglo-American University je česká škola s americkým systémem studia – žádné zkouškové období, jen malé semináře do 25 lidí, průběžné hodnocení, dvojí kreditový systém (americké + ECTS). Právě proto jim nevyhovovaly české studijní IS a sáhli po Salesforce.
• „Advising“ – osobní poradenství pro každého studenta – je klíčová přidaná hodnota školy a nesmí být nahrazen čistě automatizací. Každý semestr jde každý student za svým poradcem, který zná jeho historii a doporučí mu předměty. Tohle AI a systém plně nahradit nemůže.
• Buy-in týmu byl přirozený, protože všichni věděli, že papírový systém už není udržitelný, klíčový tým 8–10 lidí z různých agend dostával za přesčasovou práci na projektu odměnu – bez toho by to nešlo a zároveň to výrazně pomohlo adopci systému.
• Salesforce administrátor č. 1 selhal ne kvůli odbornosti, ale kvůli kulturnímu nesouladu.
• Velký potenciál vidí v AI analýze dat o studentech pro dřívější identifikaci těch, kteří jsou ohroženi neúspěchem.

Začátek vypadá skvěle a veze se na vlně AI, které k nám vtrhlo jak velká voda a vypadá, že s námi zůstane. Za mě naštěstí už na konci první stránky – byť první kapitola je vlastně celá o ní – se AI vytrácí a zůstávají strategické návyky pro lepší rozhodnutí – všechny ty věci, o kterých Honza posílá newslettery, já je sleduji zpovzdálí a zatím jsem moc nechápal. Tady jsou skvěle shrnuté a to je pro mě mega přidaná hodnota.

Strategické cykly a rozhodnutí (test, abyste si řekli opak strategického rozhodnutí a pokud je to zjevně hloupost, tak nejde o strategické rozhodnutí, mi přijde fantastický a jednoduchý), tři délky cyklů pro které je třeba plánovat, rozdíl mezi plánováním z budoucnosti a adaptací z přítomnosti.

Nastavování cílů a v jakých hladinách je plánovat – on je totiž rozdíl mezi výstupy, výsledky a dopady. Výstup zvládne každý, u výsledků musíte přemýšlet jak se k nim dostat, dopady už je mega výzva.

Zákaznické výzkumy. Opravdu je děláte nebo si jenom povídáte s lidmi?

Warleyho mapy Honza používá rád, nikdy jsem je nepochopil, až teď. Kecám, asi jsem je pořád plně nepochopil, ale konečně mi začaly dávat smysl, důležitost horizontální osy jsem totiž neznal a ta dělá celý ten rozdíl!

Principy budování organizace, kterých je „směšných“ 40 a jsou rozdělené do 4 fází – nemá smysl zavádět ty, na které nejste připravení. Jednoduchá aplikace vám je pomůže zmapovat a pak vzhůru na ně!

Obrana před konkurencí, řešení (a hledání) toho důležitého, rozhodování podle situace (ano, podle typu situace byste se měli rozhodovat jinak), ověřování nápadů a kdy si to zjednodušit a kdy zkomplikovat a to celé s praktickými příklady jak to dělají v House of Řezáč případně na vymyšlené palačinkárně. Za mě skvělá kniha na otevření očí, na další nápady, na věci, které hrají spolu dohromady a mohou váš byznys někam posunout. Spousta odkazů na další zdroje, takže přečtení knihy samotné není konec, ale opravdu jenom začátek cesty. Vydejte se na ní!

Předobjednat si knihu můžete na jeho webu.

Zápisky:

• stačí si o věcích číst nebo je musíte zažít?
• rituály, dýchání, výzvy
• sdílení, kde věci cítíte a odkud o nich mluvíte a do jaké hloubky jdete
• rozvoj není konzumace obsahu, ale prožívání a trávení věcí
• můžeš zapomenout? Nebo musíš ty situace vyřešit a doprožít?
• rychlost nebo pomalost? Lepší je mít čas věci nechat uležet a prožít je
• stačí být slyšen, ne dostávat rady
• jaký máte vztah s rodiči? A jak moc vás to ovlivňuje i když si třeba říkáte že ne?
• seriál Já jinak, pokud chcete přemýšlet o něčem co nemůže fungovat ale dost možná funguje
• vision quest – 4 dny sám v lese bez jídla, jak moc vás to může změnit a kam vás to posune?
• přechodové rituály jako ztracený nástroj společnosti – vědomý přechod z jedné životní fáze do druhé. Cesta na zkušenou bývala úplně normální
• muži emoce mají – jen se nenaučili o nich mluvit
• Je potřeba žít život, nechodit jenom na semináře – integrace do každodenního života je důležitější než hromadění zážitků z výcviků

Co dál je otázka, která mi zůstává. Marcel je na tom lépe, ví že chce pokračovat se Síla duše, já částečně doufám, že Jozef vymyslí pokračování a do toho se zkouším rozhlížet kolem, jak si tyhle věci udržet, kým se obklopit.

But now I found the time to check every single presentation (they are all on our website) from the day and learnt the following. Actually before I did my manual work I asked AI (Google NotebookLM specifically) to summarize it for me – and I learnt nothing from that output, obviously I’m still person who needs to invest own time and energy to have a feeling of achievement.

Intro keynote about DevOps was great – while I introed John with a story where I wasn’t 100% confident about inviting him, it worked out greatly. 820 metadata types deployable via Metadata API, every team has to do something to allow their metadata to be deployed (and some done do so, but they are constantly try to close the gap). We heard some stories from the background and learnt about StupidApexWorkAround class, about object Id which has to be changed just before going to production, about migration from managed package to platform native solution, which has been built in 6 months (to Pilot) thanks to AI help. Take-away: DevOps 2.0 is completely different product, I need to check it again.

Marketers

Olga and Timo made me excited about Marketing Cloud Next, additional channels and the whole platform unification topic. I would argue about respectful timing on Saturday at 10am, but I might happily ignore that WhatsApp message without being too annoyed. But scaling by using WhatsApp, automated qualification, RAG search (it is here again!) looks too good to be true. Lessons learnt and implementation reality is even more surprising and humbling – start small, one tweak at a time, don’t panic from first tests (takes a while to settle down), 4 – 6 weeks for basic implementation (including testing and iteration!).

Hanna and her „small“ tips for future success, valid not only for Marketing Cloud – naming conventions, description fields, monitoring, data diet (have only what you need, not 500 fields just in case), remove what is not needed anymore (and also have a plan from beginning when you can remove every single thing) and least privilige approach. With 2 things to do this week if you don’t have time. Awesome!

David’s talk was most likely a nice add-on to Hanna – a lot of great things how to look at what the system is doing, how to spot journeys which doesn’t run as expected (well, that actually means you can define the KPIs) and all the other monitorings you can do in Marketing Cloud. Not much to gain based on the slide to someone who don’t know (me) as a marketer definitely eye opening to what I should be doing.

Eva and emailing in scale – surprisingly it wasn’t that much about the technical part (how to avoid being marked as spam) but rather the organization behind – with 2M monthly emails and 2000 journey across 100 users I’m not surprised. One email template with referenced content blocks to your survival, integration with Figma if just by using the same name for relevant parts and … approvals!

Vicki covered Data360 nicely, but when I saw the picture above I had to wink – why the hell? But following through the presentation it probably makes sense, Data360 gives you the possibility to calculate additional metrics, segmentation can be driven by clicks not code (I hated this part of MCE), more types of segments, and much more. Obivously – especially in bigger orgs – you will need to understand all the technologies and its impact on your bill – when to sync, when to leverage what just to save your credits. Or maybe we won’t even worry about it anymore and just pay.

David followed with security in Data360 – maybe not the low level security as it isn’t really a storage, rather data in motion. More about the „perceived“ security we just talk at one customer as well. When you over ingest (we already mentioned it above) because it feels it makes sense rather than later extend the sync, when you segment (ideally super cleverly) and this segmentation reveals data to which the people would not originally have access/thought about and finally you activate/push the data to other system and suddenly everyone can see this indication, which was originally just a small internal label but now it says something very specific about the profile. And that’s the moment – way way downstream – where you don’t want to get, but because a lot of things have to happen together you cannot really foresee it

Ekat and Marketing Cloud on Core, should we care? It is actually scary as admins are getting more and more work it looks like with this they will gain even more – security, shared data with marketing (kind of 100% shared), Data360, flows instead of journey builder (so admin can do it, right, no need to pay marketer). So while I see the career expansion opportunity I’m scared for them as well. Luckily (?) MCE is here to stay at the moment, so let’s see how quick the transition will be.

Filip and BlockSDK with AI – no idea, this topic is over my head, but there is a link to public app to play with that!

AI

Robert – the most handsome speaker of CzechDreamin (official title) – generated his presentation with AI and had a full room of excited people. He shared My Org Butler, a tool which showcase what is possible. And the presentation is full of tips about less if often more, about finding balance, hybrid search which beats SOQL, how RAG on documents helps with finding answers, that Data Cloud Foundations is free and we should start now because it will be just more complex later, that LLM are trained on old data but fresh data are just one API call away, how persistent memory is crucial, or how headless is the future where we want to go. Take-away: try the My Org Butler

Crawl, walk, run approach for AI adoption by Yosra and Jim, the need to start simple (again this approach!), you the right technology for the right task, have clear business requirements and quality data, concise instructions which aren’t over complicated/constaining (reliability dropped past 8 intructions in production for Yosra), 20+ iteration cycles on master prompt as small wording can shift the behaviour – this would kill me! Edge cases and intents you didn’t foresee to come and need to constantly monitor for. Take-away: deploy AI agents will not be quick job and prompt writing is obviously a still key job.

Pei and her AI says yes but … thinking about it one more time AI is so much similar to us – it doesn’t know what it doesn’t know, it has been trained on patterns not context (every client is different but they are all the same), and it can sound very authoritative (it is correct because it is nicely looking). It reminded me so much about job in consulting And the mirror you should look at it is crucial – what assumptions you made, do you have honest answer from where the things came, can you defend every element, what might be wrong/incomplete with your answers, is it easy to maintain (otherwise it is technical debt even though you are so proud about it), use client’s terminology.

Lillie and her case for AI in Experience Cloud – don’t throw it on top of your problems, it will only amplify them. Deflection is earned by good design, not bought with an agent. If you have just unstructured data the AI-generated summaries won’t be the best, have good structured knowledgebase first. If you personalize on iferred attributes it is just creepy or presumptive, get your data correct first. Don’t deploy AI on emotionally-loaded topics (billing disputes, compaints), the empathy should stay with people.

Developers

Nicolas covered sfdx-hardis which looks better and better every time I see it. And while it does basically what a good CI/CD pipeline does, this is – in my view – focused more on the regular admin who don’t really understand those things. Also covered SFDMU and External Connected App – one reason I didn’t pay much effort into their migration so far is, that I didn’t know that all the credentials will stay the same! Take-away: look deeper into sfdx-hardis and really use it on a project. The documentation it generated on one of them was really good.

Igor about mega-orgs – actually when I heard at ArchitectDreamin about an org with 250 millions of contacts, that’s something I can hardly imagine (because I just don’t know country with so many people). Anyway, he walked us through the key limits (30 millions of ContentDocuments only, really?), how to use Grafana for DYI monitoring and costs optimization. Take-away: on top of Nebula Logger and sfdx-hardis try to find time to look at Grafana as well.

Michal and LWC architecture – thing I never felt good enough. While going through the presentation it looks simpler now (and way harder at the same time) – clear boundaries need to be set. The presentation contains a link to LWC toolkit with a decision tree to get you on the best path for your project.

Keir and Prompt Templates, because they aren’t just for agents and can be used directly from Apex. Why? Because Apex is not great at getting meaning, insights or context from text or in generating text with the right tone and language, which summarize some key data. I’ve never really thought about it but it can be super powerful and the examples are really simple code to achieve big things.

Ever saw a bad code? Houssam and Fátima claims that 99% of junior developers didn’t, which surprised me. Seeing the slides I would love to run a pannel with them and Piotr next time as they have opposite opinions (hard-code messages or not?), but besides that a lot of known anti-patterns (DML in loops), SOQL injections, Platform Cache (never saw it live), switch and „when else“ clause which should be always added (no clue why, but they probably said it), triggers and much more. I have to wonder how they define „junior“ because half of the presentation feel even to me like the absolut norm aligned with the best practices how to survive on the platform.

Todd to whom Lukas would be willing to listen even if speaking about toilet paper (actually a few people picked on introduction Lukas did of them in his video). Well, I didn’t know about the document.designMode = „on“ which allows you just simply type on any webpage, always did it via the Console. Tons of videos in the presentation so you’ll miss the talk but not the action. How to make the console log look better. That you don’t need to deploy a component to change it for testing. Take-away: rewatch this presentation!

I saw Michal’s presentation about developer who wasn’t there at Prague User Group and wanted it here as well. Demo is the main part, so you won’t find much in the presentation plus the presentation is probably too heavy even for regular developer. Based on that I realized how much the train left me and how AI will really change the delivery world. We even recorded a podcast episode about this (in Czech, sorry).

Beech had a super heavy presentation and while it is hard just based on the presentation restore the whole speach, some elements are clear – do NOT store secrets in your code repository, there are better ways how to inject them when needed. Anypoint Platform API Visualizer looks great, think twice where you can survive with Fire & Forget pattern, OpenAPI approach, DataWeave – still didn’t find energy to play with that.

Business & Admins

Marin and his being Agile – first of all I have no clue how he could deliver 118 slides in allocated time, but they are just great, similar style to Pei. If you are already scared from opening it don’t be, it is very good comics which reminds you that being Agile doesn’t mean daily stadups, reviews, tracking velocity, etc. but the 12 principles behind the manifesto are pretty much different. And if 12 is too much you should start with 4 – make sure that it satisfy the customer (understand personas, business model and value proposition), T-profile people might be better and working product is the crucial one – and if it isn’t delivered it doesn’t exist.

Aaron and fault path was mostly demo, but from those a few slides – store the errors in custom object (Nebula Logger?), create dashboard, think about retention policy and open all the relevant questions – do we need more user training, is that task too complex for flow, are we even using the right flow type?

I just love Lukasz intro picture. And sadly I saw automation hell where one change triggers something completely else which will …. Governor limits which politely inform you that your design sucks and should not be overcome by going asyns. The graveyard of old fields on overloaded object and finally that sharing is architecture as it drives performance and everything. Must have been great talk!

Maria and Justyna and their take on organizational changes – I never knew there are so many frameworks to drive the change, obviously discipline on its own. Also after seeing that – I’m not surprised that majority of projects fail in it, because people rarely see the complexity behind.

Matt’s session was another often mentioned, with the AI around the average time-to-exploit is down to 20 hours (and if that feels ok, you should know it used to be 2,3 years), so it is just a matter of time when it happens to you and you should be ready to act. Just open the presentation it has all the steps you should take and questions to ask. Golden!

Jasmine and decisions which will cost you later nicely add to Hanna, Lukasz and others, the presentation includes 5 (easy) things to do now. But we are back to proper object modelling (and no-one said the SF one is the best for everyone), automation sprawl and order of execution (that surprise so many people), hard coded IDs (well, wait for Piotr), naming conventions and governor limits. Easy to scroll through but it might open so many questions in your head.

Milan’s presentation about flows open a lot to imagination, would be definitely worth hearing the talk. But even from those screenshots you fantasy can start with what might be possible and how it might improve use experience. And then you go the route to DRY principle and how to tackle the actual flow creation and composition. Really nice one.

Paul and Roger and ADHD – not a standing room as at London’s Calling but still a handful of people attended and I realized why I should not trust the event coordinator that anyone can manage the room without microphone. A lot of excercises but to me the most crucial slide of the presentation is Roger’s „about me slide“ (#24) – instead of all the general info no-one really cares about it lists what works for him and why he migh behave during the meeting differently than you would expect. That’s something I should put together as well.

Rich and great roadmaps – there was probably way to many great things hidden in the talk, which I now miss Fantastic pictures so potentially a really funny presentation which I need to watch somewhere. A process how to make roadmap, reasons why to make it. Tools which will help.

So much of the value in a roadmap IS the process!

I simply love Andre’s presentation about data quality being a leadership problem. They typically don’t want to hear it, but if data is a strategic assets they should treat it that way, right? Governance should not be about more documents, admin work or meetings, but about clarity – who owns, what is the standard, which fields are the most crucial and who checks them. Salesforce admin should be a facilitator not janitor – spot patterns, make issues visible, build dashboards and advice on controls. The managers should explain why data is important and ensure the team follows the process. They also needs to know who creates the data and which decision depends on them and what happen wheny they are wrong.

Leanne and Liz, another first-time presenters at CzechDreamin (actually we had about 50% of speakers here for the first time, really suprised us such number) spoke about surviving global rollout. The feedback from audience was mainly about great team play during the presentation and the presentation is full of golden nuggets – weak governance, last minute changes, too many stakeholders, treating UAT as theatre (been there, saw that). Repeated what we heard during the day already – small bets, smart adjustments, why we are doing it? If something is straighforward it is usually a warning sign. That technology is rarely the hardest part, humans are! The closer to go-live the smaller decision group should with clear ownership. Work with timezones, don’t fight them. Commit to one system! Involve users early. And that hypercare is the moment where trust is won or lost. This was awesome even on slides only!

Melissa spoke about tracking ROI of your automation and that it should be just about financial savings and ignoring maintenance & training. You should also look for qualitative gains, user satisfaction, hours of work saved. Custom object, some simple triggers to fill it with data (lead assignment time, response time, conversion rate, etc) and then you can report also how many new deals you got and everything. I just never did the measurement before as typically my customers don’t know them, so never got a great looking numbers how we improved the system

Chandan spoke about the new UI improvements in flow, how we should choose the smallest pattern that solves the UX problem and then reuse it with Custom Labels everywhere. That these days there might not be a need for custom LWC as flow with a bit of styling, sections and thought can be enough.

Good old times when clients were happy with the standard UI are gone.

I saw Louise presenting on User Access Policies at IrishDreamin and while I never implemented it yet (either have clients to small to benefit from it, I know, wrong feeling) or someone else was responsible for it, it really feels like a powerful feature, which is surprisingly included for free everywhere. Such a time saver to an admin after implementation as it will automatically (de-)provision the right licenses, permission set (groups) and much more. All of that included with a high-level view how to approach the whole topic of profiles, permission sets and permission sets groups.

Consultants

I actually sit in Kedar’s session for a while as I’m constantly thinking whether to dig deeper into OmniScript or don’t bother anymore as it will be going away (I heard, but who knows). It is really interesting how similar it is to flows and while we play a few scenarios to make the best decision at the end it was (and probably is in reality as well) pretty schematic. OmniScript used to be better on UI but with the latest advancements of flow probably not that much different anymore. API calls, data raptors and all these things are potentially good enough in flows as well and what stay for OmniScript is the high effort of customization – yes, configure the thing was always hard and need a lot of knowledge and clicks so the final takeaway – start with flow by default is what stayed with me (as there is no universal winner).

CPQ or Agentforce Revenue Management by Oleg & George is fabulous. People complain about this new product not being on parity so how could Salesforce stop selling CPQ, but just going through the presentation I just like ARM much more. More end-to-end process support (not just quoting), product catalog which probably makes more sense (as I can sell one product in multiple ways, there is no reason to clone it), transaction editor easily extendable with flows (everything is flow basically in ARM), pricing engine which feels so easy to read compared to the old mix of Pricing Rules, Summary Variables and everything else, document generation which can be used for anything not just quotes. Yes, the migration is not lift and shift, that would kill you quickly, but with the right approach it feels like a product which have been thought through.

Speaking about products we typically don’t cover at CzechDreamin, Prag came to Prague with his Field Service talk. I like how he covers the non-typical capabilities, what is not covered in the presentation is sadly all the gotchas – crews look great but you need to constantly define them, complex work is awesome but has impact in scheduling and there is not templating for that. Maybe it has been said, maybe not, still great to have one more contact in the ecosystem with whom I can share my experience and ask for help.

Slack, had we ever have it before? Piyusha covered how to run your first Slack project successfully, because there are (surprisingly) companies who just don’t take their credit card and register the whole team, but want more structured approach (speak with me, please). And it goes again back to adoption and what it requires, changing ways people work, whom to involve in the project, differences between editions, and what to do after launch or what metrics to track.

Jason spoke about Industry/ies Clouds and how they different to the „core“ – different (higher) pricing, functionalities aligned to the industry, additional objects, OmniScript, etc. The key decision is at the beginning, check whether Salesforce covers your industry and whether the processes align with your processes and then (maybe) go for it. Be ready that it’ll limit the pool of people whom will be able to help you with the implementation and support, but it still might be worth it.

I just spoke about this picture with a client last week – they don’t want to develop, they want to click, based on experience from their old system. But it might not be the best approach long term and Tomas nicely covered 6 other myth as well. Because all of the out of the box features are great, only if they fit you. It might boost your productivity but it is still just a tool, it won’t fix everything magically on its own. It has robust instrastructure but it doesn’t mean you can use it for everything.

Evan’s presentation has been mentioned the most at the feedback we received. And while the presentation alone is pretty dry and requires a lot of your imagination, in the notes on the very last slide you have a link to video of what he achieved. Interesting idea to step out of dashboard and create lightning page showing reports charts, some flow to control refresh and a few other things to store the configuration. Not as user friendly to configure probably, but you can fit way more reports than you can to dashboard and also more filters. It might be solution for some use-cases, especially if you don’t want to go to Tableau or anything else.

Piotr and breaking best practices, topic I covered at ArchitectDreamin as well and we had great debate around it. Do you really need to be able to configure everything? What is the impact on complexity, understandability? Are hard-coded values really bad? Is duplication of code ok? Do I need a constant for everything? It resonated so well with me!

Aníbal and the „new“ approval processes – again I’m missing the demo but looks like flows are almost on par with the old-good approval process which was pretty easy to setup. I’m doing this thing so rarely that I didn’t bother with it yet.

Michal spoke about junior architects and how we still don’t know how to build them (while we know how to restore dinosaur). Presentation full of funny pictures where was probably great voice over, but this slide covers the most crucial things I would say.

Closing notes

And then Martina and her burn out topic which resonated with the audience even better than I predicted. Because the quality of our NO gives value to our YES!

Swag, main prize, food, drinks, talks – another great year. I still have no clue what I’ve been doing during the day that I didn’t have time to watch any session, but it flew by and I enjoyed it anyway.

Hope to catch you next year!

Todo’s for you:

• check the presentations
• check the photos

Todo’s for me: check the following in more depth

• Todd’s presentation
• Nebula Logger
• sfdx-hardis
• Grafana
• My Org Butler

After reading all 1078 pages of the latest release notes I realized the truth – there is happening way to much to keep up with everything. A while ago I still had a feeling I more or less knows the whole platform or at least have a clue of the different clouds. With the latest release I realized there are tons of new products I haven’t even heard about – Agentforce IT Services, HR Services and tons of other. Also it looks like three releases a year isn’t enough anymore and a lot of products switched/introduced a monthly releases as well, with the AI topic is being updated on weekly basis. Uff, I don’t really have energy to keep up with that.

Anyway, still a lot of interesting things to digest from the release notes:

• Chatter is off by default in new orgs, at the same time Slack is automatically provisioned including Slack Channels being enabled for the key objects and lovely Slack pannel added to Lightning Pages – I have to admin it looks really great. At the same time, if it is auto enabled how to handle clients who already have slack?
• Chat transcript is being moved to AWS while a lot of other things are migrated from AWS to Salesforce – not sure about the direction here
• Chat in Agentforce available in Slovak language, while Agentforce Voice in Czech
• Prompt Template deployable via metadata
• Report and dashboard brand palette
• Batch size can be specified for scheduled flows
• Email template reference by name not id which should result in easier deployment
• Hiding flow path to gain more screen space
• Date operators in decision logic in flows!
• Data table show readable record name, not id only
• Radio button groups to vizualize radio buttons horizontally
• Formula can be typed directly in actions input, no need to create a variable for it, same for transform & apex-defined variables in flows
• Timeout path for async paths to handle errors – it never occured to me so far!
• Flow version comparisons tools
• Group approval where all needs to approve – so far the flow approval process allowed only one from group to approve
• Excel Agent for auto-fill excel files (no need to export report and manipulate) (part of Agentforce Operations product – one of the new products I haven’t heard about)
• Sharing with queue member superior can be switched off – yes!
• Manage Shared List Views & Shared list view editing so you don’t have to give users the right to manage all public groups, but only those shared with their role/group, which might slightly limit their rights
• Setup with Agentforce generally available, each org can enjoy 500 free monthly actions (contractual limit, so shouldn’t pay anything above)
• Field service scheduling console looks really nice

• Embedding of existing React/Angular/Vue/JS apps in SF (developer preview) including data exchange
• Apex database operations run in user mode by default (breaking change in API 67), WITH SECURITY_ENFORCED is removed, also WITH SHARING is set by default (while apex triggers run with WITHOUT SHARING always)
• Elastic limits for queueable and future can be enabled in Apex settings and will schedule jobs over limit in throttled rate – cool, we spoke about the challenges around these jobs at ArchitectDreamin and this might be very handy feature
• Apex Anonymous Code Execution from managed packages is blocked – I know about some, which used this handy feature
• Multiline strings in Apex utilizing triple apostrophes to start/end the text – this is absolutely awesome
• API version lower than 40 is being retired (and SOAP login call all the way to version 64)
• Data Mask available for all editions? That would be great
• 10GB size limit for files uploaded to SF + malicious files detection out-of-the-box
• Get Scheduling Recommendations with Appointment Insights alias why we are getting so little slots answers

• Guide Students to Conflict-Free Course Schedules
• Elevate In-Person Meetings with Mobile AI Transcription – hard to figure out whether this is free for everyone or not, but looks pretty cool
• Log In to the Salesforce Mobile App with Email by Default, no need to enter password
• Keep Approvals Moving in Slack for advanced approvals or flow approval processes – at first glance it looks like a feature in Revenue Cloud only, but maybe it is also for the flow approvals
• Login with username first only (password/passkey as a next step)
• Find Case Experts Instantly with Agentforce Actions
• Illustrate Complex Customer Issues with Rich Text Case Descriptions (Beta)
• See Deal Engagement at a Glance in Pipeline Inspection

Looks like another busy release, with a lot of happening in flows, first release I can recall which has breaking changes in Apex and some interesting features across the product.

What others found interesting

• Salesforce Ben
• iTechCloud
• Ascend Technologies
• sigma Innovations Unlimited
• Salesforce Dictionary
• Maintask
• Salesforce Release In a Box
• Salesforce Developers Blog

A long time the <packt> publishing offered all of their books for really good price. I bought them all but didn’t really have time to read them for a long time, but finally I started one by one.

The End-to-End implementation somehow made it on top of the list and I really enjoyed the book. Kristian has really similar approach to implementations and the book resonated very well with me.

14 chapters, each with intro and summary, covering the whole process. Which activities, whom to include, what to take care about. I feel it is almost aimed at the companies implementing internally, to people without Salesforce experience. Some of the steps/tasks/chapters are so obvious, at the same time I feel they can bring a real value to someone at the beginning of their journey.

• overview of current business capabilities – I always hated this diagram so much yet understand it can bring an immense value. The tricky part for me is, that every single one of us can have a different view on the situation, can group and name the capabilities differently and it was always hard for me to come with something I would be happy with, something which won’t be obvious to everyone since beginning but would bring some new insights – but that’s probably not needed at all;
• list of delivery methodologies – I still struggle with the subtle differences between Agile, Scrum and Kanban and probably like some bits from each of them. Obviously I won’t be a great project manager;
• change managements frameworks – important part of every project which is being ignored on every single project I’ve been part of and some simplified into „management will send an email“ (in its best form). Seeing three frameworks listed in the book I want to learn more and while there is this module on Trailhead I don’t feel it gave me enough;
• KPIs or how we will spot successful implementation – very often I have to wonder how the implementation itself might improve those KPIs -> I do understand lowering processing time, but generate more leads?
• I’ve never heard of Conway’s law which says that companies do mostly lift and shift into new system, unless provided external input -> strong case (according to Kristian) to involve an implementation partner. Sadly I remember the implementations where the analyst just asked how the processes work now and didn’t care to suggest any possible improvements;
• a user story should be linked to business objectives, should have a purpose bigger than moving the process into its next step, they shouldn’t describe the solution but rather the need, problem and outcome (YES!). And another book I should prioritize – Salesforce Business Analyst Handbook;

Oftentimes, experienced functional consultants are asked to act as business analysts to run workshops, illicit requirements, and challenge the organization’s assumptions and old way of working. However, solid business analyst skills are distinct from declarative development on the Salesforce platform. While some functional consultants are great business analysts, not all are.

• deployment plan should include not just the pre/post deployment steps (still can of weird we need them these days when automated pipelines should handle everything) BUT also stakeholder communication plan – back to change management and the whole „project awareness“ topic which is hard to see in the wild. And I spoke with Ceska Sporitelna (in Czech) it is super hard as well as people don’t have really time to grasp any extra communication and are very often surprised later on that some features already exist and they don’t have a clue;
• speaking about communication, learning and documentation that’s one of the hardest topic I ever faced – as I always acted on the partner side, this was the typical area the customer didn’t want to pay for and rather do it themselves (but never had capacity to do so). Seeing what „training“ might/should include as everyone has different affinity to different learning methods gives me so many ideas, which would make the training the most expensive part of the delivery – workshops, videos, cheat sheets, one-pagers, FAQ, in-app guidance and all of that grouped by different personas and constantly updated. I probably know why at IrishDreamin the ClickLearn application won the demojam;
• when to transfer from hypercare to ongoing production support? As a partner we push into as soon as possible, seeing these four questions (have you aligned your processes, is the team trained and onboarded, are you reaching adoption targets, are you begin to achieve the business results you laid out) it should take way longer than what we typically aim for. But it is back to the KPIs you want to achieve, some of them are usually pretty long term I would say. And Kristian says kind of the same in the summary of the chapter, speaking about 1 – 12 months to begin achieving the results, not sure we should wait with go-live for that long;

Shield the development team from the Steering Committee meeting

• the continuous improvement phase after go-live and consideration to modify the partner model – different partner (due to different knowledge/experience), in-house combined with partner (and where is the line), full in-house or anything completely different;
• how to translate new feature requests into existing capabilities of your implementation and how to handle (limit/promote) the fact that as people start using the platform and learn more about the possibilities (out of the box, configuration, development) they will utilize the platform more;

All in all such a great book to learn how to deliver product into a company (yours or someone else). While there are references to Salesforce I don’t feel it is related only to SF, can be rather used by anyone.