StackAI

StackAI just hit 500+ integrations 🎉 That means your AI agents can work with the systems your teams already use, like Google Drive, Notion, Slack, Asana, Microsoft 365, Jira and AWS. The team has been working toward this for a while, and we're excited to finally share it. See every integration 👇 https://lnkd.in/emm6Z5Uc

"AGI, for the purpose of enterprise automation, arrived in Feb 2026..." - Bernard Aceituno, co-founder of StackAI (now part of the Asana team). Reason being, he says, is that agents crossed the line of human-level reliability in five main ways: Understanding unstructured data, querying unstructured data, orchestrating tools and actions in a non-deterministic way, interacting with visual interfaces and, synthesizing information across documents and tools. (Also.. admiring the MTS Live team for the fast, direct approach to handing out the news on AI.) https://lnkd.in/gBay7mTF

StackAI's document indexing errors dropped from ~20% to below 0.1% after moving to Temporal Technologies. Before an agent can use a customer's documents, the StackAI pipeline has to parse and index every file. On the old setup, when one step failed, the retry started over from the beginning, including paid steps that had already worked. So StackAI's engineering team moved the pipeline to Temporal piece by piece. Now each stage remembers where it left off, and a retry only re-runs the step that failed. Parsing costs are down to about a tenth of what they were. And customer complaints about indexing have stopped. Read the full story here 👇 https://lnkd.in/ecWcP9hD

Complex AI use cases don’t fail at the build stage. They fail at integration, security and deployment. Most platforms hand you a builder and leave the rest to your team. StackAI pairs every customer with dedicated experts: → An AI strategist who finds use cases where agents pay off and tracks the ROI → A forward-deployed engineer who builds custom integrations, deploys on-premise and trains your team → Support in Slack, Teams or email, plus live calls when you need them It starts with a structured proof of value: three use cases in production on the StackAI platform, running on your data and systems. Learn more on our blog → https://lnkd.in/eWQtgJCV #EnterpriseAI #AIAgents #AgenticAI

StackAI cut its indexing failure rate from about 20% to below 0.1%, and daily customer complaints about indexing stopped. In this case study, Frank Hidalgo, PhD, CTO of StackAI, shares how Temporal helps the team retry only failed steps, trace failures more easily, and scale different parts of the indexing pipeline independently. Read more: https://lnkd.in/dS3F2-wr

Every company has one system nobody is allowed to touch. Mike set it up in 2009. Only he knows how it works. Every AI plan runs into it. A platform alone won't fix that. Someone has to go deep on Mike's server and build the connection. Most enterprises need both to get AI into production. That's what StackAI was built for. The platform: → A no-code builder, so your own teams can build and maintain agents → Connects to the systems you already use, in the cloud or on-prem (Mike's server too) → Humans approve key actions before agents act The team behind it: → An AI strategist who finds where agents pay off and tracks the ROI → A forward-deployed engineer who builds custom integrations and trains your team It starts with a structured 3–6 month deployment: three use cases live in production on StackAI, running on your own data. From there, your team keeps building. Mike finally gets a vacation. 👉 Try it here: https://lnkd.in/g_HNXs_6 What's the oldest system your AI has to talk to? #AIAgents

Our co-founder Bernard Aceituno took the stage at Asana's Work Innovation Summit in New York today, joined by the CRO of XYMOGEN, one of our customers. He talked about how StackAI by Asana gives enterprises teams of AI agents that connect to 500+ systems, use the context of Asana’s Work Graph, and take on complex workflows end to end. The rest of the StackAI team was on the program too, with a presentation and a hands-on workshop on how companies use AI agents for the document-heavy back-office work that eats hours every week, like contract review, intake processing and compliance checks. Thank you to Asana for the stage, and to everyone who stopped by! #AgenticAI #EnterpriseAI

What if research and optimization could keep running while your team sleeps? At StackAI, we used OpenAI's latest models in Codex to optimize our browser agent—with minimal hands-on time. Asana's Command tracked every run and turned the results into updates that shipped to StackAI. 𝗧𝗵𝗲 𝗿𝗲𝘀𝘂𝗹𝘁: 76× cheaper and 5× faster in our week-long experiment. Every night our agents aren't running feels like a wasted night. Full story here: ordnl.link/jA7DRpp #AgenticAI #AIResearch

Every time Ducker Carlisle's AI team deployed one agent, ten more requests came in. The team had become the bottleneck. So they flipped the model. Through a citizen developer program built on StackAI, business users now build about 90% of their own AI agents. A central team of experts handles the other 10%, including complex integrations, security and governance review, and tuning for production. Here's where they are today. → 100+ non-technical employees building agents → 50+ agents deployed across dozens of use cases → $1M in projected annual savings "You don't have to be a nerd. You just have to be curious." - Fabien CROS, Chief Data and AI Officer, Ducker Carlisle Read the full story → https://lnkd.in/ghjgm-Qk #EnterpriseAI #AIAgents #CitizenDevelopers