Create specialized agents with custom roles, tools, and instructions. Your main agent manages everything.
When you start Pinchr, you're talking to your main agent. This is your primary assistant — it manages tasks, coordinates work, and decides when to create specialized sub-agents.
Your main agent is always visible in the Chat page. It orchestrates everything — you don't manually switch agents.
Your main agent automatically creates sub-agents for specialized tasks:
Searches the web, reads docs, and gathers information. Returns findings to the main agent.
Handles coding tasks, refactoring, testing, and debugging. Works in the background.
Drafts emails, reports, documentation, and creative content with your tone and style.
Analyzes spreadsheets, runs queries, and generates visualizations and reports.
You don't manually create or switch to sub-agents. Your main agent handles this automatically based on the task. Sub-agents work in the background and report back when done.
You can create your own specialized agents with custom instructions, tools, and roles. Go to Settings → Agents and click New Agent:
Your main agent will delegate to this custom agent when appropriate. You can also manually trigger it by mentioning its name: @Customer Support Agent
Different agents can use different models. Here's what we recommend:
Best for main agents and complex reasoning. Excels at task management, multi-step workflows, and computer control.
Great all-rounder. Fast, capable, and reliable for sub-agents handling research, writing, or data tasks.
Good for lightweight sub-agents. Faster and cheaper, still very capable for most tasks.
Avoid smaller models for your main agent. Models like Haiku, GPT-4o-mini, or local models lack the reasoning ability for task management and tool orchestration.
Agents can use extended thinking for complex reasoning. This feature uses the model's internal reasoning tokens before responding:
Fast responses. Good for simple tasks and quick questions.
Balanced reasoning. Main agent default for most workflows.
Deep reasoning. For complex strategy, planning, or debugging.
Configure thinking levels per agent in Settings → Agents. Your main agent can dynamically adjust thinking levels based on task complexity.
Each agent maintains its own context and memory:
Sub-agents report back to the main agent with their findings. The main agent decides what to do next.
Here's how agents work together on a typical task:
All of this happens automatically. You see progress updates in real-time and can step in anytime.
For advanced users, you can define custom agent behaviors with an AGENTS.md file in your workspace root:
This is optional. Most users manage agents through the Settings UI.