Salesforce

Agreed. And the shape of work is changing too. Six months ago people were using AI to write a function, now we're describing a whole experience for an agent to assemble. And as the coding part gets faster and easier, it's becoming more apparent that the new bottleneck is what the agent codes against: data, workflows, permissions, etc.

It's mind-blowing how fast agentic coding has progressed in the past 6 month. It's a completely different world now.

See what happens when AI goes off-script, and learn how to map your brand values directly to agent behavior: sforce.co/4w8aJLu

Customers are abandoning AI agents that feel unpredictable A clever chatbot persona isn't enough to drive adoption—brands need reliable AI that acts like a trusted employee Here are 3 ways to build agents customers actually trust: Define core company values upfront to dictate agent behavior before development begins Rigorously test edge cases and build plain-language fallbacks for seamless human handoffs Measure qualitative user satisfaction instead of just relying on closed support tickets Agentforce builds these guardrails directly into your agents using Agentforce Builder and Testing Center, ensuring every interaction stays secure, reliable, and perfectly on-brand.

@matei_zaharia The tasks that actually matter to each company also sit inside their unique data, workflows, and policies. So, every company needing its own loop also means every company needs its own eval set built from real work.

One reason we built custom coding and data agent benchmarks internally at Databricks (e.g. databricks.com/blog/benchmark…). Academic benchmarks are great and people will build better ones, but you also care about YOUR tasks, which are often different. Each company needs its own "loop".

Want to dive deeper? Here's more on how smart companies are winning with agentic commerce: sforce.co/3Rrx87w

39% of consumers now let AI do the product discovery Shopping behavior has officially shifted, and agentic commerce changes how brands get discovered Here are 3 ways to stay visible to LLMs: → Clean up product data with structured details and natural search terms → Feed catalogs directly into AI platforms instead of relying on web scraping → Drive third-party reviews on social platforms to signal trust to AI models Salesforce B2C Commerce automatically syncs product catalogs to OpenAI and Google through new direct feed protocols, ensuring inventory sits right in front of the agents making the purchase decisions.

Build your perfect schedule: salesforce.com/dreamforce/

Your Dreamforce forecast: A perfect 3-days to transform every part of your business.

Slackbot can now do anything @Salesforce can. All you have to do is ask. New Salesforce MCP servers connect your CRM, Data 360, @MuleSoft, @Tableau, and AI agents directly to Slackbot in Slack. Everything you need to move work forward, all in one place. 🙌

⏰ sforce.co/44VDoHH

Don’t sleep on it. Register for Dreamforce by July 16 to save $800.

🗳️ Poll alert! Which character should star in the official Salesforce Winter ’27 Release logo? Vote by Friday, July 10.

🎉 Congratulations to the Salesforce MVP Class of 2026. Thank you for leading with expertise, generosity, and heart — and for helping the Trailblazer Community succeed. 💙

Great question! Continuous compliance in agentic loops requires two things: a certified foundation and real-time guardrails. First, Agentforce runs entirely within our trusted infrastructure, which continuously meets strict global regulatory standards—tracked live on our Salesforce Compliance Portal. Second, during active loops, the Einstein Trust Layer enforces real-time governance (like PII masking and zero-data retention) before any action is executed.

@salesforce @AndrewYNg But how do you continuously ensure ongoing compliance across these different loops in the context of enterprise agent development or applications as they operate in regulated context ?

“Loop engineering” is a hot buzzphrase after mentions of it by Boris Cherny (Claude Code’s creator) and Peter Steinberger (OpenClaw's creator) went viral on social media. Loops are now a key part of how we get AI agents to iterate at length to build software. In this letter, I’d like to share my 3 key loops, shown in the image below, for building 0-to-1 products. These loops guide not just how I build software, but also how I decide what software to build. Agentic coding loop: Given a product specification and optionally a set of evals (that is, a dataset against which to measure performance), we can have an AI agent write code, test its work, and keep iterating until the code is bug-free and meets its specification. This idea of closing the loop took off around the end of last year, and it has been a game changer in enabling coding agents to work longer productively without human intervention. For example, over the weekend, I was building an app for my daughter to practice typing, and my coding agent could easily work for around an hour, using a web browser to check what it had built multiple times before getting back to me, without needing my intervention. The engineering loop executes quickly. Every few minutes, the coding agent might build and test a new version of the software. I hear frequently from developers who are finding new ways to engineer more effective engineering loops. This is an active area of invention! Developer feedback loop: In this loop, a developer examines the current product and steers the coding agent to improve it. Last year, a lot of developers (including me) were acting as the QA (quality assurance) function for our coding agents, manually finding bugs and then asking the agent to fix them. But with coding agents much more able to test their own code, the amount of time we need to spend on this function has decreased significantly. This allows us to make higher-level product decisions, such as what key features to offer, where the UI needs improvement, and so on. The developer-feedback loop operates over time intervals between tens of minutes and hours — that's how frequently a developer might review a product and give feedback. In the case of the typing app, I changed my mind a few times about the visual design, what cat costumes she can unlock as she learns (she loves cats), and the user flow for a grown-up to log in and steer the child's learning experience. When a developer has a clear vision for what to build, it is still a lot of work to translate that vision into a specification for a coding agent to implement. Further, after the developer has seen an implementation, they might update (or perhaps clarify) the spec to steer it toward what they want. If you find that the system repeatedly runs into certain problems, building a set of evals for the agent becomes useful. AI-native teams are increasingly using AI to help shape product direction, for example, automating the gathering and analysis of usage data, summarizing written and verbal customer feedback, or carrying out competitive analysis. However, for pretty much all the products I’m involved in, I see humans as having a significant context advantage over current AI systems — we know a lot more than the AI system about the users and the context the product has to operate in — and thus humans play a critical role. Many people describe this human contribution as “taste,” but I prefer to think of it as humans having a context advantage, since that gives us a clearer path to helping AI systems get better. This also speaks to why this step can’t be automated: So long as the human knows something the AI does not, human-in-the-loop is needed to to inject that knowledge into the system. External feedback loop: This includes a wide range of tactics like asking a few friends for feedback, launching to alpha testers, or putting the code into production with A/B testing. These tactics are usually slow, rarely taking less than hours and sometimes taking days or even weeks. This data informs the developer vision, which in turn continues to drive the detailed product spec, which in turn drives the coding agent. With coding agents speeding up software development, more engineers are starting to play a partial product management role. For many engineers who are growing into this role, the hardest part is shaping the product vision and striking a balance between building (bridging the gap between vision and spec) and getting user feedback to evolve the vision. It is important to do both! I will write more about how to do this in future posts, but for now, I find it encouraging that engineers are playing an expanded role (just as product managers and designers now do more engineering). [Original text: The Batch]

Sales teams: what if an AI agent could research, prioritize, and engage the right prospects — helping reps book meetings and move pipeline forward? That’s Hunter, your 🆕 always-on Prospecting Agent in Agentforce Sales. Coming in our Summer ’26 Release.

Dear Claude from Finance, Your @mentions are about to go way up. We’re so sorry!