Executions

An execution is a single AI agent run. You provide a prompt, and the agent writes code, runs commands, and builds your project in an isolated Docker container.

Execution Lifecycle#

Pending → Running → Completed Queued ↗ ↓ → Failed Awaiting → Cancelled (manual) Approval

1. Pending — Container is starting up
2. Queued — Waiting for another execution on the same project to finish (one at a time per project)
3. Running — Agent is actively working
4. Awaiting Approval — Agent is requesting user approval before continuing (e.g., for destructive actions)
5. Completed — Agent finished successfully
6. Failed — Agent encountered an error (can be retried)
7. Cancelled — Manually stopped by a user

Starting an Execution#

From the Command Center, type a prompt and click Run. You can optionally select:

• Provider — Select a different AI provider
• Model — Override the default Claude model

Permission required: execution:create

Workflow Phases#

Each execution runs through a 4-phase orchestrated workflow:

Plan → Code → Test → Review

1. Plan — The planner agent analyzes the prompt and creates a detailed implementation plan
2. Code — The coder agent implements the plan, writing and modifying files
3. Test — The tester agent writes and runs tests for the changes
4. Review — The reviewer agent evaluates code quality, correctness, and completeness

Between phases, an automated decision service evaluates the output and determines whether to proceed, retry, or fail:

• Proceed — Move to the next phase
• Retry — Re-run the previous phase with specific feedback (e.g., review finds bugs → code phase retries with the feedback)
• Fail — Stop the workflow (e.g., after exceeding max retries)

Each phase appears as a tab in the execution view, showing the agent's streaming output in real time.

Plan Files#

The planner's output is saved to a .redstickai/ directory in the project workspace. Downstream agents (coder, tester, reviewer) reference this file directly, avoiding context truncation for large plans. For planning sessions, a master deliverable.md file aggregates all requirements and feature specifications.

Real-Time Streaming#

While running, the execution streams in real-time:

• Text responses — The agent's reasoning and explanations
• Extended thinking — The agent's internal reasoning process (collapsible)
• Tool calls — File operations, terminal commands, and other actions
• Status updates — Container lifecycle events

Tool Call Display#

Tool calls are grouped by type and show:

• File writes/edits — Inline +N/-M line count stats in the header, with an expandable unified diff view (green for additions, red for removals)
• Terminal commands — Command and output display
• File reads — Collapsible file content
• Search results — Glob and Grep results with context

Subagent Attribution#

When the agent spawns subagents for parallel tasks, each message shows a badge indicating which agent produced it.

Turn-Based Chat#

Executions support multi-turn conversations:

1. Start with an initial prompt
2. After the agent completes a turn, send a follow-up message to continue
3. Each turn is visually separated with dividers
4. Full conversation context is preserved across turns

Use Continue to send a follow-up message to a completed execution.

Execution Controls#

Cost Tracking#

Each execution tracks:

• Input tokens — Tokens sent to the model
• Output tokens — Tokens generated by the model
• Cost (USD) — Estimated cost per turn and total

Token counts and costs are displayed per turn and summarized at the execution level.

Results Tab#

After completion, the Results tab shows an aggregated view of all file changes made during the execution. Each changed file displays:

• File path
• Lines added/removed (+N/-M)
• Expandable unified diff

This provides a quick overview of everything the agent modified across all workflow phases.

Execution Summary#

After completion, each execution shows:

• Duration — Total wall-clock time
• Turn count — Number of conversation turns
• Tool call count — Total tool invocations
• Token usage — Input/output token counts
• Cost — Total estimated cost in USD

Agent Timeline#

A visual timeline shows agent activity over the execution's duration, helpful for understanding when the agent was actively working versus waiting.

Searching Executions#

Use the global search to find executions across all projects by prompt text.

Comments#

Add comments to executions for team communication. Comments are separate from the agent conversation and visible to all team members. See Comments.