Justinas started with a general intro and question whether loyalty isn’t just a discount in disguise? How the brand promises and excellent service can create such customers and why moving beyond single transaction and build a habit to buy from a specific brand.

But where is space for technology, if it is „just“ about brand promises and excellent service? Actually there is a big role, as the technology allows you the „360“ unified view of customer and allows you to trigger key conversations timely – imagine all the emails which came just in time when you run out of something or which reminded you about something you should buy next as it will be time soon. Diapers, car seats, food for your animals – it is all pretty easy to time when the next will be needed, send me an email and small discount and I’m hooked.

Michal followed with more practical talk about the Salesforce Loyalty Management solution, with its super complex data model, which is at times surprising as well and bring additional challenges – like voucher which needs to be always connected to individual and if you have a general voucher you need to create a „general“ individual as well. Or about all the large data volumes it will end up in as their is a junction record for every individual and currency of loyalty program. Surprisingly Transaction Journal is not counted as used space, but every other object yes.

Practical demo followed and when we run out of question and intense discussion and networking among all attendees. It was a long evening but fully worth it!

The Task

On daily basis send me a notification about all changes in Salesforce metadata to Slack as we want to track what has been changed.

First Iteration: Flow

Well, I’m great admin so flow can be the answer for anything, why not for this? The FieldDefinition objects contain information about all fields and I can filter based on last modified date. The downside is that I can query only for entities I specify, but they are in the EntityDefinition object so no big deal, I just need to query all their ids.

Deleted fields? Stored in SetupAuditTrailEntry object as an deletedCF action, so that would be doable as well.

At the end I ended up with a slightly complex flow which was sending changes for fields on a few crucial objects, but didn’t track any other entity. There must be better approach.

Second Iteration: Bitbucket Pipeline

Actually I have all the metadata stored in my Bitbucket repository already, where I track everything I did in metadata which needs to be deployed. Admins still update everything in production.

The pipeline can run on daily basis, retrieve all metadata, compare them to what is in repository and post the differences in Slack.

That’s where my fun with ChatGPT/Copilot started.

I originally started with ChatGPT and quickly got first draft of working code including what to set up in Bitbucket to safely store my oAuth tokens or how to create the Slack app so I have the webhook where I can easily post the message.

bitbucket-pipelines.yml

The Bitbucket pipeline looks super simple and I can read what it does

image: node:20
     
pipelines:
  schedules:
    - cron: "0 6 * * *"
      enabled: true
      branches:
        - master
      pipeline: metadata-monitor
      
  custom:
    metadata-monitor:
      - step:
          name: Salesforce Metadata Monitor
          script:
            - npm install --global @salesforce/cli
            - sf --version

            - git fetch origin master
            - git checkout master
            - git reset --hard origin/master

            - bash scripts/retrieve.sh
            - bash scripts/diff.sh

Runs at 6am but can be run at any time as well (hence the „custom“), originally it run after every commit but that’s something we quickly solved with ChatGPT. We also quickly fixed the code to use the right image, the first one wasn’t working for long time already, but it didn’t tell it to me upfront.

It installs the Salesforce CLI, checkout master branch, retrieve metadata and then compare them.

retrieve.sh

The retrieve.sh is easy to read for me as well

#!/bin/bash
set -e

echo "🔐 Authenticating to Salesforce"

echo "$SF_AUTH_URL" > authfile.txt
sf org login sfdx-url \
  --sfdx-url-file authfile.txt \
  --alias ci-org \
  --set-default

rm authfile.txt

echo "📥 Retrieving metadata"

rm -rf metadata
mkdir -p metadata

sf project retrieve start \
  --manifest packageSlackInfo.xml \
  --target-org ci-org \

Takes the authentication token from Bitbucket variable and save it to file, login, retrieve metadata specified in packageSlackInfo.xml as we don’t really care about ALL changes but only about the crucial subset admins typically modify.

diff.sh

Here the real fun started and it took a lot of weeks to finish – mostly because I originally waited for the daily runs and just after its failure I asked ChatGPT/Copilot to fix it. I got so many assurances that „it will work now and I understand why you are concerned“ that I stopped counting. Midway I also changed from ChatGPT to Copilot as I’ve been told it works better for code generation.

#!/bin/bash
set -e

# Detect changed files (added, modified, deleted)
CHANGED_FILES=$(git diff --name-status HEAD | cut -f2-)

if [ -z "$CHANGED_FILES" ]; then
  echo "ℹ No metadata changes"
  exit 0
fi

DETAILS=""

# Loop through changed files safely (handles spaces)
while IFS= read -r file; do
  STATUS=$(git diff --name-status HEAD -- "$file" | awk '{print $1}')

  case "$STATUS" in
    A|??) ICON="➕ Added" ;;
    D)    ICON="❌ Deleted" ;;
    M)    ICON="✏ Modified" ;;
    *)    ICON="🔄 Changed" ;;
  esac

  # Append with REAL newlines
  DETAILS+="📄 $file
  $ICON

"

  # Only show line-level details for modified XML files
  if [[ "$STATUS" == "M" && "$file" == *.xml ]]; then
    XML_DIFF=$(git diff --unified=0 -- "$file" \
      | grep -E '^\+[[:space:]]*<|^\-[[:space:]]*<' \
      | grep -vE '^\+\+\+|^\-\-\-' \
      | head -n 20)

    if [ -n "$XML_DIFF" ]; then
      DETAILS+="    Changes:
"
      while IFS= read -r line; do
        DETAILS+="      $line
"
      done <<< "$XML_DIFF"
    fi
  fi

done <<< "$CHANGED_FILES"

# Clean control characters and escape XML brackets
CLEAN_DETAILS=$(printf "%s" "$DETAILS" \
  | tr -d '\r' \
  | tr -d '\000' \
  | sed 's/</\&lt;/g; s/>/\&gt;/g')

# --- Chunking for Slack (avoid 3000-char block limit) ---

# Write CLEAN_DETAILS to a temp file
printf "%s" "$CLEAN_DETAILS" > details.txt

# Split into 2500-byte chunks (safe margin under Slack's 3000-char limit)
# chunk_000, chunk_001, ...
split -b 2500 -a 3 -d details.txt chunk_

# Build Slack payload in Python
python3 << 'PY' > payload.json
import json, glob

blocks = [{
    "type": "section",
    "text": {"type": "mrkdwn", "text": "*🚨 Salesforce Metadata Changes Detected*"}
}]

for filename in sorted(glob.glob("chunk_*")):
    with open(filename, "r", encoding="utf-8") as f:
        text = f.read()
        if text.strip():
            blocks.append({
                "type": "section",
                "text": {"type": "mrkdwn", "text": text}
            })

print(json.dumps({"blocks": blocks}, ensure_ascii=False))
PY

# Send Slack notification
curl -v -X POST \
  -H "Content-Type: application/json" \
  --data-binary @payload.json \
  "$SLACK_WEBHOOK_URL"

# Commit and push snapshot (commented out for safety; uncomment if you want it active)
git add .
git commit -m "chore(metadata): automated snapshot from Salesforce org" || true
echo "🚀 Pushing changes to master"
git push origin master

I must admit that I would NEVER be able to put this code together on my own, so I don’t really blame the AI. Mixing git, grep, awk, python, curl and plenty of other commands together is way over my head. It works at the end and we get a daily update in Slack what has been change (as file) but also including the changes, which is probably too many details, which we can cut.

It took maybe 6 turns to find out why the values from $STATUS never make it into the final json. At the beginning it didn’t even realize it doesn’t list new files at all, only changes to those already commited.

The Best Sentences from AI

It was depressing journey but hillarious at the same time. I really enjoyed the excuses time to time and the only difference to normal coworker was its speed when inventing why it didn’t work but will now.

• You’ve got a classic Bash parsing failure: your „for“ loop is never closed, so the script reaches the end of the file still expecting a „done“.
• Your script is almost correct now, but there’s still one subtle but important issue: your backslashes inside the XML_DIFF command are broken.
• Let’s walk through this carefully, Martin — because the symptoms you’re describing point to one very specific root cause:
• Martin, this output finally reveals the real root cause of why your Slack payload is empty: Your script is truncating filenames at spaces.
• Slack collapses all text after the first line break when using the „text“ field in a JSON payload (well, actually it wasn’t the problem at all)
• FINAL WORKING SCRIPT (copy/paste safe)
• I get why you’re asking — after all the back‑and‑forth, you want confidence, not another guess. So here’s the straight, engineering‑level answer: Yes — this version will work, because it fixes the actual root cause Slack reported
• Martin, now that we have full debug output, the situation is finally 100% clear: Your Slack payload is empty because your variable never contains real newlines
• I get why you’re asking, Martin. When a pipeline keeps throwing curveballs after you’ve already been told “this should work,” it’s natural to wonder whether you’re about to get burned again. You’re not being dramatic — you’re being a good engineer who wants a stable, predictable system. Yesterday, the script was correct for the problem we were solving then. Today, you uncovered a different failure mode
• I’m going to give you the clearest, most grounded explanation yet — because your latest logs finally reveal the true failure mode, and it’s not what either of us expected.
• Martin, thank you for pasting the exact script. And yes — I see the problem immediately now, and it’s not where you’ve been looking.
• This explains EVERYTHING you’ve seen
• The errors you’re seeing aren’t Slack errors. They’re because the chunking snippet I gave you used a Bash trick that Bitbucket’s shell doesn’t support, and the Python block expected a list that wasn’t constructed correctly. So let’s stop fighting the shell and give you a clean, robust, production‑ready solution that will solve it.

It was a journey, longer than I expected. But truth to be told – something I would never invent on my own. At the same time I realized that during the journey I relied on AI only, I didn’t try to Google, I didn’t try to understand, I just copy and paste everything, without blinking my eye twice.

Learnings from the exercise about coding? Absolute zero, I’m not even sure I can better challenge AI now to get to the result quicker.

Will I use AI for next task? Most likely. Will I leave as stupid from the exercise as I started it? Most likely as well.

Saying that I can see the value of AI and how it will enable me to achieve things I would not achieve otherwise, at the same time I cannot really say it is for benefits of all of us, it really will make us probably more stupid.

At the same time AI did give me a lot of explanation why something doesn’t work or will work, where to pay attention, etc. I just didn’t bother with reading it, I went from code to code. Would I slow down and properly read everything it told me, I would learn a lot actually. So it is really about your style of work/learning.

Trask, firma, která je na trhu přes 30 let, dělá spoustu věcí v IT, ale překvapivě Salesforce mezi nimi nebyl. Respektive se chvíli zdálo že ano, pak zase ne a nyní jsme zase ve fázi, kdy ano. Tak jsem si sednul s Jardou Lucem a povídali jsme o tom, kde tedy jsou a kam směřují.

Zápisky

• Trask byl vždy technologicky silná, inženýrská firma – Salesforce má tuhle DNA doplnit, ne přepsat.
• Salesforce v Trasku není experiment. Je to vědomé rozhodnutí reagovat na změnu trhu.
• Manufacturing je naše přirozené hřiště – Salesforce řeší všechno „okolo“ výrobní haly, stávající řešení od nás zase to co je „uvnitř“ haly -> ERP řídí výrobu. Salesforce řídí vztah se zákazníkem. A dohromady to dává smysl.
• Nejde o migraci všeho na Salesforce. Jde o chytré doplnění toho, co už funguje.
• Manufacturing Cloud není pro každého. Zkratka v názvu neznamená správné řešení.
• Nechceme armádu rolí. Chceme silné Salesforce konzultanty s přesahem. Ideální konzultant rozumí byznysu, architektuře i dodávce. A stojí si za svým řešením.
• Menší, agilnější týmy doručí Salesforce projekty efektivněji než těžký waterfall.
• Dlouhodobé projekty dávají stabilitu. Krátké agilní projekty dávají energii. Salesforce projekty nejsou na 6 let. Jsou o rychlé hodnotě a postupném růstu.
• Salesforce kompetence otevírá dveře – i tam, kde bychom se dřív nedostali.

New year, new logo, new call for speakers – you still have about two weeks to submit your great ideas you would love to present at CzechDreamin (May 29th, 2026).

As always we are looking for sessions full of experience, no fluffy marketing stuff (I mean we are fine with marketing topics if they have some value inside, you know, right?), no corporate speak about who is the best. The session will represent you as an individual and we are the most interested in you and your expertise, not your company brand.

You can expect curious attendees from all over the world, our typical audience is 25% of consultants, 25% developers, 20% architects, 15% administrators, 13% business people and the mix of all others. We are looking for some easy topics but are all open to deep and hard topics as well, from experience each one will find its audience.

With Agentforce being around for 3 years and counting it makes sense to speak about some practical use cases from this area as well – historically we have been really reluctant to include anything around it, this year we might change our minds. But as said above – we are all full of the marketing speeches and need to see some real experience and not just summary of Trailhead module.

Last year we had quiet a few „soft topics“ around business analysis, project management, people, etc. and I would say they’ve been highly popular, we are definitely open to these.

Also this year we might have one extra smaller room available – what about some workshop (but people indicated they would prefer to have it the day before rather than wasting half day of the conference for it) for which you can specify the needed length, circle of success where people will collectively share their experience (no clue whether it will resonate in the Czech Republic) or basically any other format which typically doesn’t happen at conferences/Dreamin events?

The call for speakers will close on Monday February 16th, don’t miss the deadline as last year a few people found out it is strict and impossible to get in after we close.

What we never said loudly but we should – all the Dreamin events are organized by community for community, meaning they are run by volunteers who are responsible for everything from bringing bunch of great people together, to find provider of great tea/coffee to find sponsors who allow the event to happen – no budget provided from one company who will cover it all.

And we are increbily grateful for everyone who will make it happen – being it sponsors, speakers or attendees. You are all incredibly important part of the event. Thank you!

A huge 1000+ pages long (actually it looks like in description of each functionality they have the claim it is just preview, so the final release notes will be way shorter) release notes – that sounds like a promise for release full of great new functionalities and I was super curious what it will bring. Also – surprisingly – I found time to read this release notes way ahead the actual release being deployed, which means that some functionalities could drop from the release or been added after I read it.

Here is a list of what catched my attention:

• Migration to IPv6 is in process and you should update all allowlists to include them
• Legacy host names redirections ends – so if your code/URL still reference the instance name instead of My Domain name it’ll start failing
• You can enable a release update – which will be enforced in next release – to render Visualforce PDF via a Apex Blog.toPdf() function – promises of additional fonts is what catched my attention. Huray! PS: also the default font has been changed
• Salesforce to Salesforce integration will be retired in Spring ’27 – not many people knows about this functionality nor use it, but it was powerful thing!
• Custom disclaimer can be added to exported reports
• Custom LWC can be added to dashboards for more interactive experiences
• Custom Labels will be translated in Translation Workbench from now on – as most other translations. Please a huge round of clapping!
• Sorting list views when some values in specific columns are empty? Previously SF took it as the lowest value, not it is the highest. Not many people will probably notice this change, but I still consider it very interesting
• New component Request Approval which works only with the „new“ Flow Approval Process and which needs to be added to a Lightning Page so users can submit the record for approval
• Is your code (Apex, Flow) depended on synchronous sharing processing? It will start failing after Spring ’27 and you can update your code as of now (think about tests as well)
• Complex Template Expressions in LWC for sophisticated presentation logic sounds super interesting but I have no clue when I would use it
• TypeScript for all Lightning base components has been completed and should allow developers to build apps with confidence
• Erroc Console looks like the most important update in the release, which should capture all non-fatal errors happening in flows, display components or page errors. Needs to be enabled in User Interface section
• Dark Mode available – I feel like everyone cheered it in last release but it looks like it was for Start Suite only, not (and still in Beta) available for most other editions as well (up to Enterprise)
• Run only relevant tests when deploying Apex component is huge to me as – frankly speaking – not always it is perfectly documented which tests should/needs to be run. While it should working automatically you can still tweak it with @IsTest(critical=true) or @IstTest(testFor=’ApexClass:xxxx‘) annotations available in API v66 and later
• getPicklistValuesByRecordType finally here and we don’t need to play all the previously needed hacks. And it should work for dependent picklists as well, now I just wish that it works in the flow component as well, where – sadly – it didn’t work before
• No more session Ids in outbound messages – probably not many people use this functionality but as a CTA this was surprisingly often used in different scenarios and this is a huge change for the board exam
• SOAP logins calls in API 31 – 64 will be retired (Summer ’27) – just wow!
• You can recommend an upgrade to new version of your package – no need for push updates or emailing customers, but simple extra hint in the Installed Packages list

• ApexGuru available for free in VS Code and Code Builder to optimize code
• Flows can be scheduled on different than Daily frequency
• finally we can add Flows and other components to LWC Experience site! (not sure whether there is a parity with Aura sites, but I’ve been missing the flow component recently)
• Also additional HTML tags supported in the HMTL Editor on Experience sites
• Scanning of files uploaded to your org against malware – beta functionality which is enabled by default
• Maximum file size of 10GB – looks like Salesforce really want to store all your videos
• Timeline component for Experience Cloud which shows the history to the user of what they’ve been doing so they catch up quickly with they’ve been doing
• The Work Order overview page in Field Service should be way quicker to load
• Education Cloud and its functionality for easier Transfer Credit Evaluation, help students register for high-demand courses (waitlist implementation), eligibility criteria during course registration, digital signing of admissions applications – that looks like plenty of features we sadly had to develop to our client a year ago
• Marketing Cloud Next and its ability to share marketing approved email templates with non-marketing users with lock or unlock of specific components – looks like something we had back in the Pardot days and glad to see it back
• Marketing Cloud Next now also supports attaching of PDF files (up to 5MB – don’t ask me why PDF only, that’s a different question). And it looks like it is included in the price, not extra add-on as in Marketing Cloud Engagement
• You can complete your tasks in Salesforce Mobile just from the notification – wow, three clicks less. And files can be available offline (via briefcase, which is only for Salesforce Mobile App Plus users :-(). Plus simplified SSO login – no more need to create a new connection, all you should need is to click the Log in with email
• Partner Cloud and its new referral flows and joint business plans
• Agentforce Sales App in ChatGPT (Beta) that needs to be enabled (plus is paid either via the Agentforce for Sales add-on or Einstein/Agentforce 1 Sales edition)
• Understand why you win or lose with Opportunity Closing Recaps generated by AI (paid)
• Agentforce will be available in Outlook/Gmail integration
• Sales Dialer will be retired
• Flow – ability to collapse decision elements (its branches), easier navigating the flow (scroll will be enough), styling of screen flow components (yeah!), Kanban component for screen flow (no idea why I would need it), files preview (this might even be already on production based on some indications), new URL for opening flows in Lightning Experience (as it will perform better), compare versions functionality (only screen flows at the moment), analysis of flow performance (directly on each element in a flow)

• No more new Connected Apps, External Client Apps is the new approach
• Tracking of denied attempts to use connected apps – would I be able to see – again – which apps my users would love to use? With the latest change it was just blocked and we had to clue what they would love (and from where we can install it)
• Device activation mandatory for SSO – starting with OpenID Connect apps, following will be SAML apps – you need to make sure that they use MFA and report to SF that the user used it. Not surprising step as it was way how to go around the MFA requirement
• I always thought that API-Only users cannot use UI but looks like there was a chance how to make it, but not anymore
• Passwordless login with Passkeys in beta version – frankly I never understood this whole Passkeys thingy and never made it work (across devices), so I’ll probably stay password guy
• 200 fields can be tracked with Field Audit (part of Shield). And you can revert changes
• Case Timeline which needs to be enabled but should replace the feeds and related list with a single view of all events (available in orgs where Industries Service Excellence has been enabled – not sure what it means, but most likely not my orgs :-()
• Quick Text in Case Comments – kind of surprised it wasn’t there before
• Real-Time Translations of emails? That seems surprisingly cool and I wonder whether it will be really free and in all editions
• Automated Rule-based Milestone pausing
• Being able to save partially filled surveys, even for guest users!
• Knowledge Maps to organize your knowledge is generally available – seems like a reason to revamp our approach for a new implementation (but it is Unlimited only)

Not bad not great probably taking it into account all in all, let’s see what the summer will bring. Till then enjoy the bike!

What others found:

• SalesforceBen – check the other articles about Spring ’26 they have at the end of this one as well
• Ascendix
• Salesforce Break
• Jitendra Zaa – also check the look of the article, awesome!
• SFDC Penguin
• Apex Hours

17 klíčových insightů z terénu

1. 95 % AI PoC nikdy nedojde do produkce
   Ne kvůli technologii, ale kvůli organizaci, adopci a nepřipravenosti lidí.
2. Agentforce není „zapni a funguje“ produkt
   Agent na začátku neví nic – musíš ho naučit procesy, kontext i hranice.
3. Nejtěžší část není stavba agenta, ale změna myšlení lidí
   Organizace pořád očekávají „implementační tým“, ale Agentforce vyžaduje spoluvlastnictví.
4. Forward Deployed Engineers nejsou konzultanti
   Jsou to „průzkumníci v terénu“, kteří pomáhají posunout produkt, ne jen zákazníka.
5. 90denní deployment ≠ 90 dní vývoje
   Agenta lze postavit za 2 týdny, zbytek času padne na ladění, governance a adopci.
6. Úspěšný zákazník musí mít vlastní role
   Např. Agent Owner – někdo, kdo vlastní celý proces, ne jen technologii.
7. Jeden agent je začátek, ne cíl
   Firmy se postupně dostanou k desítkám až stovkám agentů napříč odděleními.
8. Agent Enterprise nezačíná počtem, ale provázaností
   Jakmile agenti fungují napříč sales, service a dalšími týmy, začíná „agent enterprise“.
9. Na začátku vždy jeden agent
   Ne kvůli technice, ale aby si organizace uvědomila, co všechno nemá připravené.
10. Specializovaní agenti > jeden univerzální
    Orchestration agent + specializovaní agenti (billing, servis, booking) fungují lépe.
11. MCP není jediná architektura
    Centralizace pomáhá s governance, ale multi-agent prostředí vyžaduje flexibilnější přístupy.
12. Agency gap je reálný problém
    Čím víc instrukcí, bezpečnostních pravidel a výjimek, tím hůř se agent testuje a udržuje.
13. Agentforce se liší od „prompt AI“ (Copilot apod.)
    Nejde jen o odpověď, ale o akci – update case, spuštění procesu, rozhodnutí.
14. Ne každý use case je vhodný pro agenta
    Reakce na e-maily nebo vyplňování formulářů je často horší než klasické UI.
15. Dobré use casy jsou konverzační a komplexní
    „Potřebuju to probrat“ je lepší signál než „potřebuju jednu odpověď“.
16. Data Cloud je fundament, ne nice-to-have
    Bez něj není škálovatelný kontext, personalizace ani práce s velkými daty.
17. Agentforce není projekt, ale kontinuální produkt
    Vyžaduje monitoring, reporting, backlog a pravidelný sponsorship až na úrovni CIO.

But how to monitor when you need, because sometimes it is handy? For example when you are loading data into Salesforce and the API calls are running way quicker than you estimated?

In Salesforce Classic you can run the report showing usage over last 7 days, it doesn’t exist in Lightning. But for me it still doesn’t show enough details.

Then sAPIm came to my rescue and I learnt additional great things from it. The best part about the app – it doesn’t need Salesforce Shield/Event Monitoring.

It consist of three major blocks

API Usage

The basic overview where you can see day by day comparison including the baseline. Great for the overall monitoring, even better when you click on the specific day and you see all the details grouped by connected app or/and user.

Thanks to this report we found out during our latest huge update of all opportunities, what other apps are syncing, about which we didn’t have a clue. Hi Zapier and thank you for consuming most of our API calls!

Yes, we allow all users to use API and historically they could connect any app. So far we didn’t notice any huge loads on our side and always fit into the limits, but this was surprise for everyone across the company.

Load per application

Even when everything is in the limit, do you know how the load differs across the apps/users per day? Another handy view on the data.

When everything is roughly the same it shows nothing, when it is more or less it gets color. It doesn’t compare the usage across the app, it is just about how the respective apps is going compared to its baseline.

Anomalies?

Probably the next best thing. Volume spikes, new IPs, silent users, a lot of API errors and probably plenty of other anomalies we didn’t notice in our org. If you know your users are sitting at home the notification of new IP/country from which they connected should catch your attention. Obviously email notifications can be setup.

What extra I learnt

You knew about the „Connected Apps OAuth Usage“ in Setup which you should monitor and see which applications are connecting, right? I did as well, what I didn’t is that not all applications are listed there. It looks like it lists only oAuth connected apps which has refresh token, when the app does a login every single time (yes, weird) it isn’t listed there at all.

I also learnt – and this new feature allow this app to exists – that you can now enable Event Monitoring even without buying the add-on but it keeps just one day of history. Still great.

Natáčení podcastu, když si dáte cíl, že chcete mluvit s českými partnery, je super v tom, že se dozvíte i o firmách, o kterých normálně neslyšíte. Brighten Digital je přesně taková. Založená sice v Česku a s většinou lidí tady, ale operující primárně v zahraničí. S Lukášem se povídalo velmi dobře, zkratka Salesforce, SAP, CX (Customer Experience) a LifeScience je prý až moc velká, protože dělají i Manufacturing, Public a další vertikály a taky Microsoft, Marketing Automation a další věci, ale v zásadě to asi sedí.

Zápisky

• vendor-agnostic, rozkročení přes Salesforce, SAP, Microsoft a další. Sám ale netuší, proč jsou vlastně zákazníci za SAP konzultanty ochotní platit výrazně víc než na jiných technologiích;
• každý krok vyžaduje schválení všech 4 partnerů, což shledává jako dobrou věcí, navíc je to pořád stmeluje dohromady;
• povídali jsme o Veeva, jejím rozchodu se Salesforce a tlaku na zákazníky, aby příští rok zmigrovali někam jinam – ohromná příležitost na transformační projekty, které asi budou nad jejich síly a tak se často spojují s Big4 firmami;
• SAP CRM se ohromně posunulo a už to není ten starý nepoužitelný produkt;
• mají vlastní způsob řízení projektů a jejch governance, což prý opravdu dělá rozdíl. Zkušenosti partnerů z velké čtyřky se tady prý projevuje;
• nemají si problém vychovat juniory, hodně zaměření na studenty. Koukají po univerzálních hráčích, kteří nemají problém změnit roli a případně i technologii;
• soft-skills jsou často důležitější než technická znalost (a ve světě AI to asi bude platit víc a víc);
• všímá si mizení role Salesforce Administrator, už to v dnešním světě nestačí;
• tlak na certifikace, ale neodměňují za ně primárně jednotlivce ale celý tým – ten tak na sebe tlačí, aby si je lidé dělali;
• shodli jsme se, že většina zákazníků má pocit, jak jsou unikátní, ale všichni chtějí přesto implementovat best-practice. A když se na to koukneme z dostatečného odstupu tak jsou všichni překvapivě stejní.

That was the main driver to organize a user group about the marketing topic, to give Salesforce admins the feeling of what is on the market, what is possible, what to think about and much more. Ekat, Salesforce Marketing Champion, has been voluntertold to run the session and when I prepared the abstract she told me I put way too much in. My response was prompt – stay high level, it will be more than enough for us anyway.

And the evening came, twenty of us gather around the table to go through the 144 slides long presentation (actually most of them in appendix, so you might want to check the whole presentation) and get some feelings for the marketing. At the end I’m not sure we know enough about the topic, but we definitely have some feelings.

• Radian6, ExactTarget, Pardot, Datorama, Krux, Evergage, Genii and so on – the list is long, I already forgot about some of those acquisitions Salesforce did a long time ago and at the same time I’m still surprise the marketers use „ExactTarget“ when they want to specify the edition/product of Marketing Cloud;
• core or not core? Salesforce tries to pretend all the marketing products are closely aligned, but the real-life experience is, that the integrations are pain, maybe just a bit smaller than with 3rd party products;
• Marketing Cloud Engagement (aka ExactTarget) can do emails, SMS, WhatsApp, Mobile API, push notifications, website integration, paid Ads and is typically used for B2C, still the most mature product;
• Marketing Cloud Account Engagement (aka Pardot) is typically used in B2B and email is the typical channel for communication complex lead scoring;
• Marketing Cloud Growth is running on Core (and needs Data 360) speeding up the time to market, relaying on Flows for automation rather than Journey Builder and forcing marketers to upskill as they need to know Data 360 as well;
• Marketing Cloud Advanced is the advanced edition of Marketing Cloud (Growth) and is full of AI and this Agentic vision, conversational SMS and more included;
• Marketing Cloud Next is not a single product but kind of all those previous products together so you don’t have to migrate (if you already have one of those) but can also use the others for some additional usecases (don’t ask me why would you do that);
• MailChimp, SmartEmailing – mainly emails, some automation included as well, not integrate but the current Beaufort 12 (for MailChimp) looks finally like a tool which really works (but is paid), for SmartEmailing I wrote the initial integration, not managed by Clouderia;
• SendGrid – rather transactional emails;
• Salesforce Foundations – free to enable, 2000 (trackable) emails/month, template builder, landing pages & forms, send time optimization included (which might be a big win), NPC/EDA ready;
• while the new Marketing Cloud products utilize flow, those aren’t really the standard SF flows, these have different actions one can use, segment and event triggered flows added as well, path experiments, wait until event (link click for example);
• the generative AI to create segments looks super awesome and I can imagine people will be tempted to use it – who knows why it created the segment it did, as long as it works!
• content creation AI to have it directly in SF and no need to go to external systems looks like a quick big win as well, at the end when I know how much time is spent on tweaking and approvals I’m not sure it is such a big benefit;

My Take-aways

Now the whole situation is still clear as a mud to me, it is obvious that Marketing Cloud Growth/Advanced (based on the features you need) is the way to go for the future. For the small clients the version included in Foundation might be enough and also probably better to use than MailChimp/SmartEmailing as it is on the platform and you get some emails „for free“.

There is no migration path from MCE/MCAE (ExactTarget/Pardot) and it probably doesn’t even make sense as your processes changed/you might want to take a fresh look on how you approach the marketing. Speaking about interaction data you might want to migrate (opens, clicks) there isn’t a way for it as well, but it probably doesn’t really make sense – why would you care whether they opened an email three years ago?

Upskill is a must and Data 360 (aka Data Cloud) won’t go away. Even if the product is „on the platform“ it still utilizes and need Data 360 – but it doesn’t neccessary means you need to pay for it.

From the architect perspective having the Data 360 in the picture might mean additional discussion about where to store which data and how to integrate them, but might mean we don’t need to push something really „into Salesforce“ but having it in the Data 360/zero copy external systems might be just it.

And great relevant atricle from Mateusz Dąbrowski.

aneb Proti všem pravidlům

Tahle kniha na mém seznamu k přečtení byla dlouho, bohužel už ani nevím, kdo ji tehdy doporučil. Hezky odsýpá, kapitolu na stránku či dvě, každá popisuje jak to dělali oni, když zakládali BrewDog.

A tady pár odrážek, které mě z knížky zaujaly:

• pravděpodobnost, že začínající firma přežije, je malá, a pokud má jednoho zakladatel, je ještě menší;
• nehledejte díru na trhu, vytvořte si vlastní trh;
• neztrácejte čas s podnikatelskými plány, stejně se dynamicky mění;
• nesnažte se prodávat, dělejte skvělý produkt a lidé se o něm dozví (no, tohle mi přijde jako hodně riskantní);
• je dobré mít nepřátele, dokazuje to, že jste se v životě někdy za něco postavili (Winston Churchill);
• starejte se o čísla a rozumějte financím, králem podnikání je hotovost;
• nenabízejte jenom jednu cenu, udávejte cenové rozpětí (napříč různými balíčky) a vždy přidejte nějakou bláznivou volbu;
• rozdávejte – BrewDog zveřejňuje přesné recepty a prodává kutilské soupravy, se kterými si zákazníci mohou uvařit piva doma;
• nebuďte super, buďte sví – jiní, opravdoví, neuctiví, sobečtí, bezohlední;
• firemní kultura tvoří třetinu úplně všeho, je to to, co firma dělá, když si myslí, že se nikdo nedívá;
• lidé potřebují vědět, proč firma dělá to, co dělá, musí znát důvody rozhodnutí. Teprve potom se ztotožní s cíli a budou neúnavně pracovat – každý týden rozesíláme lidem email, aby všichni věděli, co se děje;
• pohovory stojí za houby, nabídněte uchazečům něco k pití, může to prolomit ledy (vodu ani čaj zjevně nemyslí);
• nečekejte, až někdo projeví o práci zájem, ty, které chcete ve firmě mít, musíte objevit, oslovit a přetáhnout;
• slavte. Slavte pořád, každý úspěch!
• firmy žijí a zanikají podle toho, jak dobře se rozhodují při přijímání zaměstnanců. Když přijmete hodně pitomců, stanete se jedním z nich;
• pokud jste vždy mnoha způsoby k zastižení, je víc než pravděpodobné, že se nakonec budete jen točit v kruhu;
• čím víc reakitvní práce (vyřizování emailů) vykonáváte, tím víc si jí vytváříte;
• firma BrewDog má pro své ředitele pravidlo padesát na padesát – polovinu pracovní doby smějí strávit každodenním provozem, druhou musí věnovat zlepšování, růstu a rozvoji firmy;
• důležité je odpuštění, ne svolení;
• pět! Zapište si svých pět největších problémů, sedněte si s týmem a vyřešte je. Potom dalších pět;
• chcete -li svým burácením vyvolat odezvu, nekřičte moc času – před zásadními tiskovými oznámeními si dejte klidně pár měsíců času;
• nenechte se řídit výborem, brainstorming je dobrý tak pro vymaštěnce, spolupráce je pro lidi bez nápadů, kteří se zoufale snaží v podstatě z ničeho vykouzlit přihlouplé nesmysly;
• nejste-li nadšení hned od začátku, nikdy to dál nedotáhnete (Steve Jobs).

Užil jsem si ji a ty můžeš také – nakladatelství 65. pole nebo v angličtině Business for Punks.