Tool · Build

Workbench

The Workbench is where developers build with coding agents on real projects, on your own infrastructure. It turns a ticket into a plan, runs agents in isolated workspaces, and keeps a person in control of every result.

Coming soon

The ESACA Context Builder: the Coding step, with the requirements-to-review workflow and a subtask dependency graph. — The Context Builder: from requirements to review, with subtasks and their dependencies.

Capabilities

From a ticket to reviewed, working code

Plan from a ticket

Turn a ticket or an intent into an implementation plan and break it down into concrete subtasks before any code is written.

Multi-agent orchestration

Run several coding agents in defined workflows, each handling part of the work, instead of one agent doing everything at once.

Pluggable agents

Works with OpenCode, Claude Code, Aider and CLI-based agents, so teams are not locked into a single agent runtime.

Multi-repo, pinned state

Work across several repositories at known, pinned commits, so a task is well defined and the result is reproducible.

Isolated execution

Each agent works inside an isolated, sandboxed workspace rather than loose on the host, so it only touches what it is meant to.

Human-in-the-loop, binding

A person stays in control. Agents can propose and mark work done, but the human keeps the override and the review stays binding.

Fits your development flow

Designed to sit alongside your existing Bitbucket and GitLab workflow, with an audit trail of every agent action.

Bring your chosen model

Use the model you selected in the Benchmark. Switch models without rewriting endpoints, on self-hosted or cloud compute.

How it looks

A loop, not a one-shot

Ticket

Start from a ticket or an idea.

Plan

Plan and decompose it into subtasks.

Agents

Agents work in isolated workspaces.

Review

Review the result, with a full audit trail.

Handover

Hand over to your normal review and merge.

What it gives you

Agentic speed, without giving up control

Developers stay on real projects instead of throwaway sandboxes.

Code and context stay on your own infrastructure.

Every agent action is logged for review and audit.

It is part of the development flow, not an isolated one-shot.

Security & sovereignty

The Workbench runs on your own GPUs and infrastructure, with optional cloud burst. Agent execution is being moved into isolated sandbox containers, access is governed by roles, and single sign-on is on the roadmap. As an early build, isolation and access control are being hardened before wider release.

In active development

The Workbench is part of an informational preview. A login to use it in the browser is planned.

Coming soon Back to the tools