Krea Bots Opens Beta With 9 AI Agents Running Full Creative Campaigns

Krea's new beta hatches specialist AI agents with persistent memory that collaborate over chat, with teams getting $1,000 in credits to try it.

·
·
·
  • Krea opened the beta for Krea Bots, named AI agents that each own one creative craft.
  • A director bot called North plans projects and briefs specialists for images, video, motion, sound, 3D and social.
  • Bots collaborate in chat via @mentions and hand work to each other automatically.
  • Three memory layers persist: craft lessons, project notes and workspace-wide house style rules.
  • Each bot connects to Slack, Meta Ads, Figma, a browser and Krea's generation tools.
  • Accepted beta teams receive $1,000 in credits; no public pricing or GA date yet.

Krea has opened the beta for Krea Bots, a system of named AI agents that handle specific creative tasks, retain approved preferences across projects, and pass work through a shared chat. Accepted teams receive $1,000 in credits to test the full feature set.

The interface resembles a team chat: users assign work by mentioning a specialist with @, and the bots coordinate subsequent steps. Krea describes each bot as an AI teammate with a role, identity, memory, tools, and isolated compute. The company says it produced its recent marketing output with the system.

A nine-bot production line

Each bot carries a defined role within the workflow. North, the creative director, reads the brief, plans the work, and routes tasks to the appropriate specialists. A mentioned bot completes its assignment and hands the next step to the relevant role.

  • North: plans projects and briefs the other bots
  • Lumen: generates images and product shots
  • Doodle: creates storyboard sketches
  • Voxel: builds 3D models
  • Glide: produces motion graphics and animated loops
  • Snip: edits videos and creates cutdowns
  • Bloop: designs and mixes sound
  • Ping: writes captions, schedules posts, and manages social channels
  • Serif: checks brand compliance and logo use

Krea’s landing page illustrates the workflow with a product launch. North proposes three directions, Lumen generates 20 stills on travertine, Voxel models the product, Glide creates a seamless rotation, Bloop mixes room tone, Snip cuts a 15-second spot, and Ping publishes it across four channels. Krea estimates 43 hours of bot work and seven minutes of human input for the example, though it does not provide a benchmarking methodology.

What runs inside each bot

Each bot combines a reasoning model, a persistent brief, sandboxed compute, a visual review loop, and connected tools. Sandboxed compute gives the agent an isolated environment for its work, while the visual loop inspects images and references before the bot responds.

Krea lists Slack for requests and updates, Meta Ads for campaign launches, Figma for layouts, a browser for research, and its own image, editing, motion, sound, and 3D generators. Tool access allows a bot to move beyond generating an asset and perform parts of the surrounding production workflow.

Memory with clear boundaries

A three-layer memory model determines what each bot knows before starting a task:

Memory layer What it stores Where it applies
Craft Approved lessons from feedback, such as keeping breakfast captions short The individual specialist
Project Pinned instructions and context, such as shooting at golden hour Every bot in the current chat
Workspace House rules, including logo placement and brand conventions All bots and projects in the workspace

Lessons proposed by teammates require user approval before they enter persistent memory. That approval step gives teams a way to prevent temporary feedback or mistaken instructions from becoming standing rules.

How Krea assembled the stack

Bots consolidates capabilities Krea introduced across several earlier releases:

  1. August, Slack integration: Krea brought its creative tools into Slack through an adaptive agent that learns team preferences.
  2. September, Krea Agents: The company introduced orchestration across more than 60 models, including Flux, Veo 3.1, Kling, Runway, Luma, and Krea 2. Large language models from providers including Anthropic handle planning, while Krea and third-party systems perform generation.
  3. October, Krea 3: Krea released its image editor at $0.03 for a 1K image and $0.06 for a 2K image.

The shared chat packages those model-routing and generation capabilities into named roles with separate responsibilities and memories. Teams can assign ownership of each production step while retaining project-wide instructions and workspace rules.

The market for AI creative crews

Adobe’s Firefly agents, Canva’s Magic Studio, and Runway’s workflow tools are expanding across the same campaign pipeline, from asset generation through editing and distribution. These products aim to coordinate multiple models and tasks within a single creative environment.

Krea differentiates Bots through its team-chat interface and scoped memory. The structure mirrors common agency and in-house workflows, where creative direction, image production, motion, sound, editing, and distribution belong to distinct roles.

Beta access and open questions

Teams can apply through the beta waitlist. Krea says accepted applicants will receive $1,000 in credits and access to the full feature set.

Bots-specific pricing and a general availability date remain unpublished. The practical value of the credit grant will depend on how Krea meters model calls, compute, storage, and connected-tool actions.

Production evaluations should examine several operational details:

  • permission boundaries for Slack, Figma, Meta Ads, and browser access
  • controls for viewing, editing, approving, and deleting stored memories
  • handoff behavior when a bot fails or produces an unusable result
  • usage logs, approval records, and cost attribution by bot or project
  • API access, asset export, and integration with existing production systems
  • data retention, model-provider routing, and workspace isolation

The beta gives existing Krea users a structured layer over the company’s model orchestration and creative tools. For new teams, the credits provide room to test whether role-based agents can complete a campaign while preserving brand rules, human approvals, and predictable costs.

Trending
  • No trending articles

Comments

avatar

Next Reads