ScoutOS Changelog

A lot of the work we've been doing at Scout lately is foundational infrastructure—the kind of under-the-hood work that might not look flashy at first, but unlocks powerful new capabilities. This update is all about making your agents smarter, more reliable, and easier to organize.

🗂️ Introducing Drive: Your Central Hub for Agent Knowledge

The biggest addition to Scout is Drive—a unified workspace where all the knowledge your agents can access lives in one organized place.

What's in Drive:

• Tables - Structured data your agents can reference
• Workflows - The automations powering your agents
• Crawls - Streamlined web scraping (appears as tables but with a cleaner setup process)

Think of Drive as mission control for your agent's knowledge base. Instead of scattered data sources, everything is organized, connected, and accessible from one place.

Drive is now available for everyone in Scout. For current users, you’ll still see Databases and Workflows in the side navigation in your Scout workspace for the next couple of months. We want to make the transition as smooth as possible.

Coming Soon: File support is in fast-follow development, so you'll soon be able to upload and organize documents directly in Drive for your agents to reference.

⚡ Dynamic Mode: Never Let Downtime Slow You Down

If you've used AI agents long enough, you've experienced the frustration: OpenAI goes down, your workflow grinds to a halt.

Dynamic Mode solves this by automatically routing requests to the best-available model based on your task—and we have access to all the major models (GPT, Claude, Gemini).

The benefit? Seamless failover. If OpenAI has an outage, Scout automatically switches to Claude or Gemini without you lifting a finger. This is one of the key advantages of using a third-party platform like Scout instead of going direct to ChatGPT.

Plus, you’ll automatically maximize speed and token usage by leveraging faster, cheaper models for simpler tasks and only leaning on the heavy-duty models for the hardest work.

🧠 Recall: Giving Agents Memory

Here's where things get interesting. We're working on Recall—a capability that will be available to every agent in Scout.

How it works: When you expose a file to an agent, Scout will automatically index it. Your agent can then recall that information in future conversations, creating a form of persistent memory without overwhelming the context window.

This is just the first piece of our broader vision for agentic memory. We're building the infrastructure that lets agents learn from past interactions while staying focused and performant—it's harder than it sounds, but we believe this is how we create the next leap forward in AI utility.

🔧 Other Improvements

• Compaction: Agents can now dynamically compress their context, keeping conversations efficient without losing important information
• JSON Mode: Perfect for developers—agents can now respond exclusively in JSON format for programmatic integrations (great for hooking into APIs like HubSpot)

What's Next?

Much of our recent work has been infrastructure that doesn't show immediate UI changes but enables powerful features down the road. Files in Drive, enhanced Recall capabilities, and more turnkey ways to expose your data to agents are all on the horizon.

As always, we're building Scout to be the platform where your agents don't just respond—they remember, adapt, and stay reliable when it matters most.

Sales teams are stuck in a productivity trap. You're spending more time on admin work than actually selling - researching prospects, filling out questionnaires, waiting for engineers to answer technical questions, and keeping CRM data current. Meanwhile, your pipeline suffers and deals stall.

The problem is… automating sales workflows has always required months of dev time that your engineering team doesn't have. So you're left choosing between expensive, rigid solutions that solve one problem, or building something custom that may never get prioritized.

Scout’s new focus is helping sales teams automate their internal workflows without fighting for dev resources. We connect to your data, build AI agents, then launch them into the tools you already use. Choose presets or go custom, all with white-glove support.

This narrower focus means we can dial in exactly what sales teams need - faster setup, reliable automation, and immediate impact on your day-to-day workflows.

🕵🏻‍♂️ 5 new agents for sales teams

To help Sales teams get up-to-speed faster with Scout, we’ve launched 5 new out-of-the-box agents optimized for common sales workflows. Now it takes two clicks to start running competitor research, cleaning up your CRM, or drafting a response to your latest RFP.

Meeting prep agent

Pulls relevant notes, past interactions, and key data, so your team shows up ready to close.

RFP agent

Scout quickly and accurately drafts tailored RFP responses using your content.

AI Sales Engineer

Provides fast, on-demand support to solution and sales engineers.

Competitive intel agent

Pulls real-time insights on the competition from internal and external sources.

Security questionnaire agent

Accurately autofills your high-stakes questionnaires using your existing docs.

🧠 Smarter, more collaborative, and faster to test

We've also supercharged our AI agent capabilities to give you more power and flexibility.

• Multi-Agent Chats: You can now mention multiple agents in a single chat. This allows you to bringin different expertise for more complex tasks and conversations.
• Agent Sandbox: Rapidly iterate on agent instructions and conversation starters with the in-page agent sandbox.
• Google Gemini Support: We're excited to announce the integration of Google's Gemini 2.5 models. You can now choose from Flash Lite, Flash, and Pro models when creating your agents.

🦸🏻‍♂️ Table superpowers

We've made significant enhancements to how you manage your data in Scout. The feature formerly known as "Collections" has been renamed to "Tables" across the platform for clarity. And you can now view your Tables as Kanban boards which unlocks all sorts of agent management workflows.

• New Kanban View: View documents in a table as a Kanban board and easily drag and drop between columns. Use this view to track progress on tasks and manage agents the way you manage tasks with your human teammates.
• New Column Types: You can now use Select and Multi-Select columns, allowing for more structured data entry. We've also introduced a Relation column type, which lets you link tables together, creating powerfullational databases. For quick binary choices, a new Checkbox column is now available.
• Enhanced Options: For 'Select' and 'Multi-Select' columns, you can now color-code your options for better visual organization and easily delete options you no longer need.
• Improved User Experience: We've added a number of quality-of-life improvements, including the ability to export tables, a redesigned table footer with a "New Row" button and more information at a glance, and sticky headers in the studio so you always know where you are. We've also fixed a bug that caused the search bar to disappear when no results were found.
• Simplified Data Management: You can now delete individual rows and entire tables, giving you more control over your data.

Other improvements

• More Powerful Search: We've enabled stemming by default in our search, which means you'll get more relevant results (e.g., searching for "run" will also find "running"). We've also introduced powerful vector and text search capabilities for deeper, more contextual searches within your tables.
• Gmail Drafting: A new Gmail drafting tool allows you to create, edit, and send emails directly from Scout.
• Streamlined Onboarding: We've removed the guided onboarding flow to give you a more direct and faster path to getting started with Scout.
• Tuning the Engine: We've also made a number of backend improvements to enhance performance and reliability, including a new and improved web crawler and a re-introduction of embedding chunking for more efficient data processing.

Today, we’re thrilled to launch Scheduled Runs for Workflows—a major step toward making your AI automation truly hands-off and always-on.

Schedule your workflows with precision

• New “Schedule” tab in Workflows: Find the new Schedule tab in the left panel of any workflow. No more hunting for automation settings—everything you need is now in one place!
• Create multiple cron or time-based triggers: Set up as many scheduled triggers as you need. Run your AI workflows daily, weekly, or on any custom cron schedule—no coding required.
• Custom inputs for each scheduled run: Define unique input values for every scheduled trigger. Perfect for workflows that need different parameters at different times.
• Easy management: View, edit, and disable schedules directly from the Schedule tab for full control.

Why does it matter?

Until now, automating workflow runs meant relying on manual starts or external integrations. With built-in scheduling, you can ensure your agents and automations run exactly when you want—whether that’s every morning, on Mondays at noon, or any pattern you can imagine.

What’s new?

• Hands-off, reliable workflow automation
• Multiple schedules per workflow
• Direct input configuration for each schedule
• Centralized schedule management

Ready to get started? Head to the Workflows area and open the Schedule tab to set up your first automated run. Thank you for building with ScoutOS!

Say goodbye to brittle automation and hello to a smarter way of working! Today, we’re thrilled to introduce AI Agents to the Scout platform—intelligent assistants that adapt, learn, and get your toughest jobs done.

What’s new?

AI Agents: Adaptable, autonomous, always on

• Flexible goal execution: Give agents a plain-English goal—like “Find all customers who haven’t ordered in 90 days and send them a re-engagement email”—and let them figure out the steps.
• Automatic tool integration: Agents connect with your favorite tools (Slack, Google Workspace, CRMs, databases, and more) in just one click. No manual API wrangling required.
• Custom tools in minutes: Build any logic visually in the workflow builder, save it as a tool, and your agent can use it instantly.
• Built-in resilience: Agents handle edge cases gracefully, adapt to unexpected data, and recover from errors—so you don’t have to babysit your automations.
• Personalized behavior: Configure everything from language model to response style, step limits, and visibility. Make each agent fit your team’s exact needs.

Why does it matter?

• Less guesswork, more building: Agents eliminate rigid “if this, then that” flows. Just describe the outcome you want—your agent handles the rest.
• Works everywhere you do: Chat with your agent in the Scout dashboard, embed it in your app (Copilot Beta), add to Slack, or access via API.
• Collaborative by design: Assign specialized agents for research, support, sales, and more. They can even hand off tasks to each other.

Ready to get started?
Build your first agent at studio.scoutos.com/agents/new or check out our quick start guide.

Next up on our roadmap:

• Expanded agent analytics and monitoring
• More integration options
• Smarter self-improving agents

Thank you for being part of the Scout community!

🚀 Introducing Workflow Analytics for Scout

Power users need clarity, not guesswork. Today, we’re launching Workflow Analytics: real-time visibility into your workflows - finally, all in one place.

Are my AI workflows actually successful? Is my RAG context relevant? Why are my costs spiking? Where is latency hurting UX? Scout Workflow Analytics gives you these answers instantly.

What’s New?

• Usage & Health: Track how often a workflow is running, and how many times the workflow is failing.

• Collection Strength: See at-a-glance how well your semantic search is performing and whether your context is actually relevant.

• Latency Metrics: Identify bottlenecks and optimize for speed. See where and why latency jumps, before it hits your end users.

• Cost Controls: Understand which blocks drive cost spikes.

Why does it matter?

Until now, our most advanced users were flying blind - it was difficult to know which workflows are being used, how much they're being used, if they're actually delivering value, where context is breaking, or what’s driving up spend. Workflow Analytics changes that.

Less guessing. More building.