Skip to main content
The dotbot web dashboard gives your team a live view into every aspect of an AI-assisted development project. It runs as a pure PowerShell HTTP server paired with a vanilla JS frontend — no Node.js, no Docker, no external dependencies — and is launched directly from the .bot/ directory that lives inside your project repository.

​
Launching the dashboard

Start the dashboard from your project root: 
.bot\go.ps1
The server starts on port 8686 by default. If that port is already in use, it auto-selects the next available port. To specify a port explicitly, pass the -Port flag: 
.bot\go.ps1 -Port 9000
Once running, open http://localhost:8686 (or your chosen port) in any browser to access the dashboard.

​
Dashboard tabs

The dashboard is organized into seven tabs, each providing a focused view of a different layer of your project.

​
Overview

Workflow cards with progress pills showing task counts per lifecycle stage, plus per-workflow run and stop controls. This is your primary operational view — you can start and stop individual workflows directly from here without dropping to the command line.

​
Product

Product documents generated during kickstart: mission statement, tech stack description, and entity model. These documents are produced by the guided interview flow and serve as the ground truth for the AI during subsequent pipeline runs.

​
Roadmap

A visual task roadmap view showing effort estimates, priorities, and dependencies across the entire backlog. Use this tab to assess scope and sequencing before starting a workflow run.

​
Processes

Real-time monitoring of running AI processes — provider, model, task, and elapsed time for each active slot. If you have multiple parallel workers running, this tab shows you what each one is doing at any given moment.

​
Decisions

Browse the decision log: architectural and design decisions with their status, rationale, and supersession chain. When the AI makes a structural choice during a session, it records a decision entry here so you can review and challenge it later.

​
Workflow

Pipeline-phase view of all tasks with filtering by workflow, phase, and category. Use this tab to drill into a specific workflow’s queue and verify task distribution across phases.

​
Settings

Provider configuration, model selection per phase (analysis and execution), and permission mode controls. This is also where provider detection results are displayed — see Provider detection below.

​
Manifest-driven kickstart dialog

The kickstart dialog is driven by the workflow.yaml manifest installed in your project. Depending on the workflow, the dialog renders different form modes controlled by visibility flags:
  • Prompt mode — free-text description of the feature or change to build. Use this for quick, well-understood tasks where you can describe the requirement in a sentence or two.
  • File upload mode — attach a requirements document or specification file. dotbot reads the document and uses it as the primary context for task generation.
  • Interview mode — a guided requirements-gathering flow that produces product documents and a task roadmap. This mode asks structured questions and uses the answers to populate the Product and Roadmap tabs before generating tasks.
  • Auto-workflow mode — skips the dialog entirely and runs the pipeline from preconfigured inputs. Use this for repeatable automation scenarios where the inputs are already defined.
The specific fields and modes available depend on which workflow is installed. For example, the kickstart-via-jira workflow adds Jira project and sprint selectors to the dialog.

​
Provider detection

The Settings tab shows every AI provider that dotbot detects on your system. For each detected provider, the dashboard displays:
  • Installed CLI version — the version of the provider’s CLI currently on your PATH
  • Authentication status — whether the CLI is currently authenticated or requires a login
  • Available permission modes — the permission levels supported by that provider (for example, Claude supports bypass and auto; Codex supports bypass and full-auto; Gemini supports yolo and auto-edit)
The dashboard only shows providers whose CLI is present on your PATH. Install at least one of Claude CLI, Codex CLI, or Gemini CLI before launching the dashboard, or the Settings tab will show no providers.
You can switch the active provider and model from the Settings tab at any time. Changes take effect on the next workflow run.