4.0 Control

Budgets you set, not bills you discover.

Every task has a budget, every loop has a cap, and every person and agent has a role. When work reaches a limit, it stops and asks a person. Nothing goes past a limit without someone saying yes.

AGENT TURNS BUDGET REACHED YOU ANSWER CHECKS SPENT $0 $5.00 BUDGET $5.40 RAISED TO $8.00 STOPS AND ASKS YOU RAISE BUDGET · REPLAN · CANCEL WORK IS KEPT PASS MAIN ALSO CAPPED: RETRIES · REVIEW ROUNDS · AGENTS RUNNING AT ONCE · TIME PER STEP

4.1 Budgets

Spending stops where you set it

Each task has a budget, and each project has a ceiling. You get a warning at 80%. At the cap, the next agent turn does not start: the task stops and asks a person to raise the budget, replan or cancel. The work done so far is kept.

A finished design task merged into main through the merge gate: its total cost, the agents that worked on it and its active time, every run with its own cost, and two thirds of the budget used.

4.2 Retries and time

Every retry has a cap and every step a time limit

Every repeat has a cap you set, and every step has a time limit. When a task runs out of rounds, it stops and asks a person, with the evidence, instead of trying the same thing again.

A task’s timeline: its steps and agent turns, waits for a free full-test-suite slot, holds while the limit on work in flight was full, and a repair fixed and verified; a side panel shows one event’s properties and artifacts.
  • New plans per task
  • Review fix rounds
  • Repair rounds
  • Refused merges
  • Automatic reruns
  • Retries per step
  • Time per step
  • Time per sandbox

4.3 Concurrency

You decide how much runs at once

Cap the tasks in flight, the agents running, the full test suites, the depth of the merge queue and the workspaces on each machine. When a cap is full, new work waits for a free slot, so a busy day does not swamp your machines or your CI.

TASKS IN FLIGHT 12 OF 12 NEW WORK WAITS FOR A FREE SLOT AGENTS RUNNING 6 OF 8 FULL TEST SUITES 1 OF 2 MERGE QUEUE 5 OF 6 MAIN ALSO CAPPED: WORKSPACES PER MACHINE · PARALLEL MERGES · CHAT SESSIONS · CPU CORES

4.4 Where agents run

Agents work on machines you choose

Each task runs in its own sandbox: a Docker container on your own machines, Kubernetes, AWS or Cloudflare, or a cloud sandbox from E2B or Daytona. The factory reaches a Docker host in your network over SSH. Each step names its environment: the image, the memory, the command that verifies the work and the side services it needs.

YOUR NETWORK OVER SSH DOCKER HOST ON YOUR MACHINES EACH TASK IN ITS OWN SANDBOX E2B CLOUD SANDBOXES THE FACTORY RUNS YOUR WORKFLOWS OR KUBERNETES · AWS · CLOUDFLARE · DAYTONA

4.5 Security and access

One set of rules for people and agents

Every request meets the same roles and the same project access, whether it comes through the web, the API or MCP, the open protocol agents use to call tools. Access to a project is denied until someone grants it.

  • four roles: Viewer, Operator, Organization admin and Platform admin;
  • single sign-on through your identity provider: Google, GitHub, GitLab, any OIDC provider, or Cloudflare Access;
  • OAuth for MCP clients, with consent and revocation;
  • personal API keys that are hashed, scoped and expiring;
  • secrets never pass through chat or MCP;
  • integration installs, revocations and disconnects are audited.
Run the factory from your own agent →
PEOPLE SINGLE SIGN-ON YOUR AGENTS OAUTH, WITH CONSENT SCRIPTS AND SERVICES SCOPED, EXPIRING KEYS ONE ACCESS CHECK YOUR ROLE · PROJECT ACCESS WEB API MCP NO PROJECT ACCESS: REFUSED

4.6 Audit trail

Every run leaves a record

Each step stores what it produced, and nothing it stored can be changed once published. Every task also keeps a timeline of every event, from the moment it arrived to the moment it merged or stopped.

A task’s artifacts: its plan, agent transcripts, test summaries and a person’s review, and one agent review run opened with its cost, tokens and model, and a shell command the agent ran with its output.
Stored for every run
  • Plan
  • Review
  • Test summary
  • Build summary
  • Diff summary
  • Agent result
  • Log bundle
  • Diagnostic snapshot
  • Document
  • Transcript
  • CI merge judgement

Keep your process.
Add the agents.