Kanvas is the operating intelligence your business runs on — a managed AI operations service that connects your tools, teams, capital, and AI agents around the goals that matter, so the work moves in the same direction.

How does Kanvas work with my existing tools?

Kanvas connects to the tools you already use. We map where work is getting stuck, set up the AI workers and guardrails, and run it for you — no rip-and-replace and nothing for you to build.

Do I have to build anything?

No. Kanvas is a managed service. We handle diagnosis, configuration, go-live, and continuous operation. You stay in charge of the business while we do the building and running.

How is Kanvas priced?

Kanvas is custom-built to each business. We scope every engagement to your operations and goals across three layers — setting up the intelligence layer (unifying your knowledge base, connecting tools, and establishing the operational framework), building the capacity layer (deploying AI agents that drive your key processes), and running the outcome layer (measuring that the intended results are delivered while surfacing improvement and expansion opportunities each iteration). Pricing is tailored to that scope — no per-seat or per-task metering.

Jun 4, 2026Blog4 min read

Kanvas Update — May 2026

kaiokenEngineering & operations

May was about taking the next step toward our vision for Kanvas. Over the last few years, we've built the foundation: APIs, workflows, CRM, inventory,...

In this article

May was about taking the next step toward our vision for Kanvas.

Over the last few years, we've built the foundation: APIs, workflows, CRM, inventory, messaging, integrations, and the operational building blocks that power real businesses.

This month, we focused on strengthening the Nervous System.

Not by building another agent.

But by making Kanvas the layer that connects all of them.

The Nervous System Gets More Flexible

One of the biggest milestones this month was expanding the Kanvas agent architecture.

Our vision has never been to build around a single agent framework. The AI ecosystem is evolving too quickly for businesses to be locked into one platform.

Instead, Kanvas acts as the operational layer underneath your agents — managing business data, workflows, permissions, communications, and execution.

This month we expanded support for multiple agent runtimes and architectures.

Today Kanvas can coordinate agents across:

Native Kanvas Agents
OpenClaw
Hermes
External AI Providers
Custom Agent Implementations

The goal is simple:

Businesses shouldn't have to rebuild their operations every time a new agent platform appears.

Your workflows stay the same. Your data stays connected. Your operations continue running.

That's what we mean when we say Kanvas is becoming the operational nervous system for modern businesses.

Better Visibility Into Agent Activity

As more work gets delegated to agents, understanding what happened becomes increasingly important.

This month we expanded the Nervous System event architecture to provide deeper visibility across:

Conversations
Agent actions
Workflow executions
Skills and tools
Errors and system events

This gives teams a clearer understanding of how humans, agents, and systems interact across the platform.

Agent Learning & Memory Improvements

We continued investing in how agents retain context and organize work.

Agents can now better manage tasks, learn from activity, and maintain context across workflows.

While much of this work happens behind the scenes, it lays the foundation for more capable operational agents that can work continuously instead of reacting to a single prompt.

Agent Vision

Agents need more than text to operate effectively.

This month we added support for image processing across the Kanvas ecosystem, allowing agents to work with screenshots, photos, documents, and visual information as part of their workflows.

Sally Goes to Work

We continue to dogfood Kanvas internally.

This month we expanded Sally, our internal sales agent, and began using her throughout our own sales process.

We're also building accounting and invoicing agents that will eventually become part of the broader Kanvas ecosystem.

Using these agents ourselves helps us validate workflows, uncover bottlenecks, and improve the platform before customers ever see the features.

Preparing for Public Launch

A major focus this month was reducing the effort required to get started with Kanvas.

Social Login

We completed the groundwork for Google and GitHub authentication as part of our upcoming public onboarding experience.

One-Click Company Setup

We're also building automatic company provisioning.

Our goal is simple:

Create a company and have Kanvas automatically configure the foundational services required to operate:

Email
Voice
SMS
WhatsApp
Agent infrastructure
Core integrations

What used to take hours of setup will eventually take only a few minutes.

Platform Improvements

Alongside the larger initiatives, we shipped several ecosystem improvements:

Continued progress on Acumatica integration work
INTRAS integration moving closer to production rollout
Vehicle Charge support for automotive and mobility use cases
Stripe and payment infrastructure improvements
Upgrades to core AI services and platform monitoring
Improved health monitoring and operational visibility

Looking Ahead

June is focused on opening more of Kanvas to the public.

We're continuing work on kanvas.dev, simplifying onboarding, and refining the operational modules that power modern businesses.

The vision remains unchanged:

Kanvas is the operational nervous system that connects your data, workflows, humans, and agents into a single system.

Not another dashboard.

Not another AI tool.

The system where operations actually run.

See you next month.