A Generalist Agent vs Durable

Gato is the generalist agent DeepMind introduced in its May 2022 research post "A Generalist Agent." One transformer policy with shared weights handles chat, image captioning, Atari games, and real robot arm block stacking from the same model. The post describes it as a multi-modal, multi-task, multi-embodiment policy that picks whether to emit text, joint torques, button presses, or other tokens based on context.

Most tools in this space train a separate model per task domain. Gato instead serializes every modality and environment into a flat token sequence and runs it through a transformer shaped like a large language model. That means one pretrained checkpoint moves between dialogue, vision, and control without swapping architectures.

During training, data from simulated and real environments mixes with natural language and image datasets, with loss masked so Gato predicts only action and text targets. At deployment, a prompt tokenizes first, each new observation appends to the sequence, and the model samples an action vector one token at a time inside a 1024-token context window. The blog includes domain-grouped charts of tasks where the pretrained model clears expert score thresholds.

The writeup targets AI and robotics researchers more than everyday software buyers. You read and cite the research on deepmind.google; there is no public signup flow, API tier, or download button on the pages reviewed here.

Durable turns business problems described in plain English into production-ready automations that your team can deploy and maintain without writing code. You describe a workflow issue, Durable investigates connected systems like Salesforce or Snowflake, and produces reviewable requirements before writing real code. Deployments happen with one click, and Durable monitors automations afterward, fixing API breaks and submitting updates for approval.

Unlike agent-first platforms that chain LLM calls into brittle workflows, Durable writes deterministic production code and uses AI only where judgment is needed, such as classifying documents or mapping custom fields. Requirements stay in plain English as the source of truth, so edits propagate to code without filing tickets or waiting on engineering sprints.

Operations teams at mid-market and enterprise companies use Durable for CRM syncs, invoice processing, lead routing, and customer onboarding. Integrations cover 44 systems including Salesforce, Slack, HubSpot, Jira, and Snowflake, with SOC 2 Type II and a 99.9% uptime SLA for production workloads.