TicketFlow Help

Overview

TicketFlow is a demo platform for testing AI agent integrations via MCP (Model Context Protocol). It includes a ticket management system as a built-in use case — agents can create, search, and update tickets — but the primary purpose is to evaluate how different MCP servers, models, and prompts perform on real tasks.

The agent uses Anthropic models (Claude) and runs on a shared corporate API key — no personal API key is needed.

Quick start

1. Go to MCP Profiles and add your MCP server connection. Any MCP-compatible server works — for example, Albato or Composio.
2. Go to Agents and create an agent. Attach the MCP profile you just created.
3. Open Chats, select your agent and start a conversation.
4. Optionally, go to Testing to compare two agents side by side.

Tickets

The core of TicketFlow. Each ticket has a title, description (Markdown), status, and visibility.

Statuses

• Backlog — not started
• Open — in queue
• In Progress — being worked on
• Done — completed

Visibility

• Private — visible only to you.
• Public — visible to you and the administrator.

Views

Switch between List and Kanban board using the toggle in the top-right corner of the Tickets page.

Filtering & search

Filter by status and ownership (All / Mine). Use the search field to find tickets by title or description.

MCP Profiles

MCP (Model Context Protocol) profiles connect the agent to external services — CRMs, messengers, databases, and more. Each profile is a URL + token pair pointing to an MCP-compatible server.

Adding a profile

1. Go to MCP Profiles in the sidebar.
2. Click Add profile.
3. Enter a name, the MCP server URL, and your token.
4. Save. The profile is now available to attach to agents.

Built-in profile

Every account has the TicketFlow profile pre-connected. It gives the agent access to native ticket management tools (create, list, update, delete tickets).

Agents

An agent is a configured AI assistant. You can create multiple agents with different models, system prompts, and connected MCP profiles.

Configuration options

• Name — display name for the agent.
• Model — Anthropic model to use (Haiku, Sonnet, Opus). Only Anthropic models are currently supported.
• System prompt — instructions that define the agent's behavior and persona.
• MCP Profiles — one or more profiles that give the agent access to external tools.
• Max iterations — maximum number of model calls per request. Increase if the agent hits the limit on complex tasks (recommended: 15–20 for multi-step MCP tasks).
• Temperature — controls randomness. Lower values make responses more predictable.

Chats

Each agent can be used in a persistent chat. Conversation history is saved — you can close the browser and continue later.

How it works

• Open Chats in the sidebar and click New chat.
• Select an agent to use for this conversation.
• Type your message and press Enter.
• The agent streams its response in real time, showing which tools it calls along the way.

Tool visibility

During a response, you can see each tool the agent invoked and its result. This helps you understand exactly what actions were taken on external services.

Agent Comparison

The Testing section lets you compare up to 4 agents simultaneously on the same set of tasks — useful for evaluating different models, prompts, or MCP configurations.

Concepts

• Suite — a named collection of test cases.
• Case — a single user message sent to all sides.
• Side — one agent slot in the comparison. Add up to 4 sides using the + Add side button.

Running a test

1. Create a suite and add test cases.
2. Add one or more sides and assign an agent to each.
3. Click Run. All sides execute each case in parallel.
4. Review results: token usage, cost ($), duration, and full tool call trace for each run.
5. An AI summary is generated highlighting key differences.

Example: comparing MCP providers

You can use the same agent on both sides but with different MCP profiles attached — for example, to compare Albato vs Composio on the same task:

1. Create two agents with identical model and system prompt.
2. Attach the Albato MCP profile to one, Composio to the other.
3. Run the same test cases on both sides.
4. Compare token usage, cost, duration, and response quality.

Cost display

Cost is calculated automatically from token counts using current Anthropic pricing. Hover over a bar in the chart to see the per-case breakdown (input vs output tokens and their rates).

Statistics Admin

Available to administrators. Shows a log of all agent sessions across all users.

What's tracked

• User message and agent response
• Token usage (input, output, cache)
• Duration and model response time
• Tool calls with inputs, outputs, and timing
• MCP profile used
• Errors, if any

Sessions can be filtered by user, date, tool name, and error status. Individual sessions can be hidden from the list or annotated with a note.

Users Admin

Administrators can manage all user accounts in the Users section.

User statuses

• Pending — registered but awaiting approval. Cannot use the app.
• Active — full access.
• Blocked — access revoked.

New registrations default to Pending. An admin must approve them before they can log in.

Actions

Approve, block, or delete users. Enable or disable agent access per user. Admins cannot modify their own status or delete themselves.

Administrators can also delete any ticket, including tickets created by other users.

Settings

AI

Anthropic API Key — optionally set your own API key. If not set, the platform uses the shared corporate key. Useful if you want to track your personal usage separately.

Always confirm connection — when enabled, the agent will always ask you to choose a connection before performing any action, even if only one is available. Useful for demos where you want to make the flow visible step by step.

Custom instructions Admin — text appended to the system prompt for all agents and all users. Use it to set the default tone, restrict certain behaviors, or add shared domain context.

Appearance

Customize the app for your workspace: set a name, pick an accent color, and upload a logo. Changes apply immediately and are visible only to your account.

Security

Change your password. Passwords must be at least 8 characters and include an uppercase letter, a number, and a special character.

Release Notes

July 1, 2026

MCP Profiles

Each user can now connect their own MCP server under Settings → MCP Profiles. Any MCP-compatible provider is supported (Albato, Composio, and others). Tokens are encrypted before storage.

A built-in TicketFlow profile with native ticket management tools is automatically added to every account.

Agents

The Agents section lets you create custom AI agents with their own system prompt, model selection (Sonnet, Haiku, Opus), MCP profile bindings, iteration limit, and temperature. The platform uses a shared corporate Anthropic API key — no additional setup required.

Chats

Each agent is accessible via persistent chat with full history. The chat streams responses and shows tool calls and their results inline.

Agent Comparison

The Testing section lets you compare agents on identical tasks — side by side, with metrics on tokens, cost, and time. An AI-generated summary highlights the key differences. Each run includes a detailed breakdown of tool calls and responses.

Cost is calculated automatically using current Anthropic pricing, with per-case breakdowns of input/output tokens.

Earlier features

• Tickets — create, edit, filter, search; list and kanban views; markdown support
• Public / private ticket visibility
• Agent statistics — run history, tokens, tools, timing (Admin only)
• Custom branding — app name, accent color, logo (Settings → Appearance)
• User management — approve, block, grant agent access (Admin only)
• Security — token encryption, httpOnly cookies, rate limiting, password change