> ## Documentation Index > Fetch the complete documentation index at: https://docs.swarms.ai/llms.txt > Use this file to discover all available pages before exploring further. > Collaborative discussion swarm where multiple agents engage in group conversation, building on each other's ideas for brainstorming and cross-functional planning # Group chat **Swarm Type**: `GroupChat` ## Overview The GroupChat swarm type facilitates collaborative discussion between multiple specialist agents. Unlike workflows where agents operate independently, GroupChat enables agents to engage in a shared conversation where each participant can build on, challenge, and refine ideas from others. This architecture is ideal for brainstorming, cross-functional planning, and problems that benefit from interactive dialogue. Key features: * **Collaborative Discussion**: Agents engage in shared conversation rather than working in isolation * **Cross-Functional Input**: Combine perspectives from different domains in a single discussion * **Idea Building**: Each agent can react to and build on contributions from other participants * **Convergent Outcomes**: Discussion naturally converges toward actionable conclusions ## Use Cases * Product strategy brainstorming sessions * Cross-functional planning and alignment * Architectural design discussions * Risk assessment with multiple stakeholders * Creative ideation requiring diverse perspectives ## API Usage ### Basic GroupChat Example ```bash theme={null} curl -X POST "https://api.swarms.world/v1/swarm/completions" \ -H "x-api-key: $SWARMS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "name": "Product Launch Strategy", "description": "Cross-functional product launch discussion", "swarm_type": "GroupChat", "task": "Discuss and develop a go-to-market strategy for an AI-powered project management tool targeting remote engineering teams of 5-30 people. The MVP is built with 12 beta users. Budget is $50K with an 8-week timeline to public launch.", "agents": [ { "agent_name": "Product Manager", "description": "Drives product vision, roadmap, and prioritization", "system_prompt": "You are a Senior Product Manager. Define the core value proposition and target personas. Prioritize features for the launch MVP. Identify key metrics and success criteria. Be concise and action-oriented. Build on what other participants say.", "model_name": "gpt-4.1", "role": "worker", "max_loops": 1, "temperature": 0.5 }, { "agent_name": "Growth Marketer", "description": "Designs acquisition channels and launch campaigns", "system_prompt": "You are a Growth Marketing Lead. Propose acquisition channels ranked by expected ROI. Design the launch campaign strategy. Suggest pricing and positioning tactics. Be data-driven and specific with numbers.", "model_name": "gpt-4.1", "role": "worker", "max_loops": 1, "temperature": 0.5 }, { "agent_name": "Engineering Lead", "description": "Assesses technical feasibility and delivery timelines", "system_prompt": "You are an Engineering Lead. Evaluate technical feasibility of proposed features. Flag complexity risks and dependencies. Propose a realistic MVP scope and timeline. Be pragmatic and push back on scope creep.", "model_name": "gpt-4.1", "role": "worker", "max_loops": 1, "temperature": 0.4 }, { "agent_name": "Customer Success Lead", "description": "Represents the customer voice and retention strategy", "system_prompt": "You are a Customer Success Lead. Advocate for the end-user experience. Identify onboarding friction points. Propose retention and engagement hooks. Ground the discussion in real customer needs.", "model_name": "gpt-4.1", "role": "worker", "max_loops": 1, "temperature": 0.5 } ], "max_loops": 1 }' ``` ```python theme={null} import requests import json API_BASE_URL = "https://api.swarms.world" API_KEY = "your_api_key_here" headers = { "x-api-key": API_KEY, "Content-Type": "application/json" } swarm_config = { "name": "Product Launch Strategy", "description": "Cross-functional product launch discussion", "swarm_type": "GroupChat", "task": "Discuss and develop a go-to-market strategy for an AI-powered project management tool targeting remote engineering teams of 5-30 people. The MVP is built with 12 beta users. Budget is $50K with an 8-week timeline to public launch.", "agents": [ { "agent_name": "Product Manager", "description": "Drives product vision, roadmap, and prioritization", "system_prompt": "You are a Senior Product Manager. Define the core value proposition and target personas. Prioritize features for the launch MVP. Identify key metrics and success criteria. Be concise and action-oriented. Build on what other participants say.", "model_name": "gpt-4.1", "role": "worker", "max_loops": 1, "temperature": 0.5 }, { "agent_name": "Growth Marketer", "description": "Designs acquisition channels and launch campaigns", "system_prompt": "You are a Growth Marketing Lead. Propose acquisition channels ranked by expected ROI. Design the launch campaign strategy. Suggest pricing and positioning tactics. Be data-driven and specific with numbers.", "model_name": "gpt-4.1", "role": "worker", "max_loops": 1, "temperature": 0.5 }, { "agent_name": "Engineering Lead", "description": "Assesses technical feasibility and delivery timelines", "system_prompt": "You are an Engineering Lead. Evaluate technical feasibility of proposed features. Flag complexity risks and dependencies. Propose a realistic MVP scope and timeline. Be pragmatic and push back on scope creep.", "model_name": "gpt-4.1", "role": "worker", "max_loops": 1, "temperature": 0.4 }, { "agent_name": "Customer Success Lead", "description": "Represents the customer voice and retention strategy", "system_prompt": "You are a Customer Success Lead. Advocate for the end-user experience. Identify onboarding friction points. Propose retention and engagement hooks. Ground the discussion in real customer needs.", "model_name": "gpt-4.1", "role": "worker", "max_loops": 1, "temperature": 0.5 } ], "max_loops": 1 } response = requests.post( f"{API_BASE_URL}/v1/swarm/completions", headers=headers, json=swarm_config ) if response.status_code == 200: result = response.json() print("GroupChat swarm completed successfully!") for output in result.get("output", []): print(f"\n{output['role']}: {output['content'][:200]}...") else: print(f"Error: {response.status_code} - {response.text}") ``` ```javascript theme={null} const API_BASE_URL = "https://api.swarms.world"; const API_KEY = "your_api_key_here"; const headers = { "x-api-key": API_KEY, "Content-Type": "application/json" }; const swarmConfig = { name: "Product Launch Strategy", description: "Cross-functional product launch discussion", swarm_type: "GroupChat", task: "Discuss and develop a go-to-market strategy for an AI-powered project management tool targeting remote engineering teams of 5-30 people. The MVP is built with 12 beta users. Budget is $50K with an 8-week timeline to public launch.", agents: [ { agent_name: "Product Manager", description: "Drives product vision, roadmap, and prioritization", system_prompt: "You are a Senior Product Manager. Define the core value proposition and target personas. Prioritize features for the launch MVP. Identify key metrics and success criteria. Be concise and action-oriented. Build on what other participants say.", model_name: "gpt-4.1", role: "worker", max_loops: 1, temperature: 0.5 }, { agent_name: "Growth Marketer", description: "Designs acquisition channels and launch campaigns", system_prompt: "You are a Growth Marketing Lead. Propose acquisition channels ranked by expected ROI. Design the launch campaign strategy. Suggest pricing and positioning tactics. Be data-driven and specific with numbers.", model_name: "gpt-4.1", role: "worker", max_loops: 1, temperature: 0.5 }, { agent_name: "Engineering Lead", description: "Assesses technical feasibility and delivery timelines", system_prompt: "You are an Engineering Lead. Evaluate technical feasibility of proposed features. Flag complexity risks and dependencies. Propose a realistic MVP scope and timeline. Be pragmatic and push back on scope creep.", model_name: "gpt-4.1", role: "worker", max_loops: 1, temperature: 0.4 }, { agent_name: "Customer Success Lead", description: "Represents the customer voice and retention strategy", system_prompt: "You are a Customer Success Lead. Advocate for the end-user experience. Identify onboarding friction points. Propose retention and engagement hooks. Ground the discussion in real customer needs.", model_name: "gpt-4.1", role: "worker", max_loops: 1, temperature: 0.5 } ], max_loops: 1 }; fetch(`${API_BASE_URL}/v1/swarm/completions`, { method: "POST", headers: headers, body: JSON.stringify(swarmConfig) }) .then(response => response.json()) .then(result => { if (result.status === "success") { console.log("GroupChat swarm completed successfully!"); result.output.forEach(output => { console.log(`\n${output.role}: ${output.content}`); }); } }) .catch(error => console.error("Error:", error)); ``` ```go theme={null} package main import ( "bytes" "encoding/json" "fmt" "io/ioutil" "net/http" ) type Agent struct { AgentName string `json:"agent_name"` Description string `json:"description"` SystemPrompt string `json:"system_prompt"` ModelName string `json:"model_name"` Role string `json:"role"` MaxLoops int `json:"max_loops"` Temperature float64 `json:"temperature"` } type SwarmConfig struct { Name string `json:"name"` Description string `json:"description"` SwarmType string `json:"swarm_type"` Task string `json:"task"` Agents []Agent `json:"agents"` MaxLoops int `json:"max_loops"` } func main() { API_BASE_URL := "https://api.swarms.world" API_KEY := "your_api_key_here" swarmConfig := SwarmConfig{ Name: "Product Launch Strategy", Description: "Cross-functional product launch discussion", SwarmType: "GroupChat", Task: "Discuss and develop a go-to-market strategy for an AI-powered project management tool targeting remote engineering teams of 5-30 people. The MVP is built with 12 beta users. Budget is $50K with an 8-week timeline to public launch.", Agents: []Agent{ { AgentName: "Product Manager", Description: "Drives product vision, roadmap, and prioritization", SystemPrompt: "You are a Senior Product Manager. Define the core value proposition and target personas. Prioritize features for the launch MVP. Identify key metrics and success criteria. Be concise and action-oriented. Build on what other participants say.", ModelName: "gpt-4.1", Role: "worker", MaxLoops: 1, Temperature: 0.5, }, { AgentName: "Growth Marketer", Description: "Designs acquisition channels and launch campaigns", SystemPrompt: "You are a Growth Marketing Lead. Propose acquisition channels ranked by expected ROI. Design the launch campaign strategy. Suggest pricing and positioning tactics. Be data-driven and specific with numbers.", ModelName: "gpt-4.1", Role: "worker", MaxLoops: 1, Temperature: 0.5, }, { AgentName: "Engineering Lead", Description: "Assesses technical feasibility and delivery timelines", SystemPrompt: "You are an Engineering Lead. Evaluate technical feasibility of proposed features. Flag complexity risks and dependencies. Propose a realistic MVP scope and timeline. Be pragmatic and push back on scope creep.", ModelName: "gpt-4.1", Role: "worker", MaxLoops: 1, Temperature: 0.4, }, { AgentName: "Customer Success Lead", Description: "Represents the customer voice and retention strategy", SystemPrompt: "You are a Customer Success Lead. Advocate for the end-user experience. Identify onboarding friction points. Propose retention and engagement hooks. Ground the discussion in real customer needs.", ModelName: "gpt-4.1", Role: "worker", MaxLoops: 1, Temperature: 0.5, }, }, MaxLoops: 1, } jsonData, _ := json.Marshal(swarmConfig) req, _ := http.NewRequest("POST", API_BASE_URL+"/v1/swarm/completions", bytes.NewBuffer(jsonData)) req.Header.Set("x-api-key", API_KEY) req.Header.Set("Content-Type", "application/json") client := &http.Client{} resp, err := client.Do(req) if err != nil { fmt.Printf("Error: %v\n", err) return } defer resp.Body.Close() body, _ := ioutil.ReadAll(resp.Body) fmt.Printf("Response: %s\n", string(body)) } ``` ```rust theme={null} use reqwest::Client; use serde_json::{json, Value}; use std::error::Error; #[tokio::main] async fn main() -> Result<(), Box> { let api_base_url = "https://api.swarms.world"; let api_key = "your_api_key_here"; let swarm_config = json!({ "name": "Product Launch Strategy", "description": "Cross-functional product launch discussion", "swarm_type": "GroupChat", "task": "Discuss and develop a go-to-market strategy for an AI-powered project management tool targeting remote engineering teams of 5-30 people. The MVP is built with 12 beta users. Budget is $50K with an 8-week timeline to public launch.", "agents": [ { "agent_name": "Product Manager", "description": "Drives product vision, roadmap, and prioritization", "system_prompt": "You are a Senior Product Manager. Define the core value proposition and target personas. Prioritize features for the launch MVP. Identify key metrics and success criteria. Be concise and action-oriented. Build on what other participants say.", "model_name": "gpt-4.1", "role": "worker", "max_loops": 1, "temperature": 0.5 }, { "agent_name": "Growth Marketer", "description": "Designs acquisition channels and launch campaigns", "system_prompt": "You are a Growth Marketing Lead. Propose acquisition channels ranked by expected ROI. Design the launch campaign strategy. Suggest pricing and positioning tactics. Be data-driven and specific with numbers.", "model_name": "gpt-4.1", "role": "worker", "max_loops": 1, "temperature": 0.5 }, { "agent_name": "Engineering Lead", "description": "Assesses technical feasibility and delivery timelines", "system_prompt": "You are an Engineering Lead. Evaluate technical feasibility of proposed features. Flag complexity risks and dependencies. Propose a realistic MVP scope and timeline. Be pragmatic and push back on scope creep.", "model_name": "gpt-4.1", "role": "worker", "max_loops": 1, "temperature": 0.4 }, { "agent_name": "Customer Success Lead", "description": "Represents the customer voice and retention strategy", "system_prompt": "You are a Customer Success Lead. Advocate for the end-user experience. Identify onboarding friction points. Propose retention and engagement hooks. Ground the discussion in real customer needs.", "model_name": "gpt-4.1", "role": "worker", "max_loops": 1, "temperature": 0.5 } ], "max_loops": 1 }); let client = Client::new(); let response = client .post(&format!("{}/v1/swarm/completions", api_base_url)) .header("x-api-key", api_key) .header("Content-Type", "application/json") .json(&swarm_config) .send() .await?; if response.status().is_success() { let result: Value = response.json().await?; println!("GroupChat swarm completed successfully!"); println!("Response: {:?}", result); } else { println!("Error: {}", response.status()); } Ok(()) } ``` **Example Response**: ```json theme={null} { "job_id": "swarms-G17nZFDesmLHxCRoeyF3NVYvPaXk", "status": "success", "swarm_name": "Product Launch Strategy", "description": "Cross-functional product launch discussion", "swarm_type": "GroupChat", "output": [ { "role": "Product Manager", "content": "Here's my take on the launch strategy. Value proposition: 'Stop managing tasks — let AI manage them for you.' Target persona: engineering managers at remote-first startups who currently use Jira or Linear but struggle with sprint planning accuracy. MVP priority for launch: (1) AI task assignment — this is the core differentiator, (2) Slack integration — lowest friction adoption path, (3) standup summaries — immediate daily value. I'd defer Jira migration and delivery risk prediction post-launch. Success metrics: 50 teams onboarded in 8 weeks, 60% WAU after first month." }, { "role": "Growth Marketer", "content": "Love the positioning. Channel strategy for the $50K budget: Product Hunt launch ($2K, expected 500-1K signups), dev-focused content marketing ($15K), Slack community partnerships ($8K), LinkedIn ads targeting eng managers ($15K, est. CAC $35-50), and a beta user referral program ($10K). Pricing: free tier up to 5 users as growth loop, Pro at $12/user/month targeting ~$2,500 ACV, with a 40% launch discount on annual plans for the first 3 months." }, { "role": "Engineering Lead", "content": "Reality check on scope. Feasible in 8 weeks: AI task assignment (core algo exists, needs polish — 3 weeks), Slack integration (standard OAuth + webhooks — 2 weeks), standup summaries (v1 using activity logs — 1 week). Risks: GitHub integration adds 2-3 weeks for bidirectional sync, recommend starting with read-only status sync (1 week). AI assignment accuracy has a cold-start problem for new teams — suggest manual override plus learning mode. Timeline: 6 weeks eng + 2 weeks buffer, doable if we freeze scope now." }, { "role": "Customer Success Lead", "content": "From our 12 beta users, top onboarding friction: teams don't trust AI assignments on day one (need a suggestion mode before autonomous mode), Slack connection takes 3 clicks but users expect 1-click, and there's no clear aha moment in the first 5 minutes. Retention hooks I'd prioritize: daily standup digest in Slack (passive value), weekly time-saved report (quantifies ROI for the buyer), team leaderboard for sprint completion. Common objection: 'How is this different from Jira automation rules?' — we need a comparison page and a 2-minute demo video." } ], "number_of_agents": 4, "service_tier": "standard", "execution_time": 35.2, "usage": { "input_tokens": 45, "output_tokens": 2400, "total_tokens": 2445, "billing_info": { "cost_breakdown": { "agent_cost": 0.04, "input_token_cost": 0.000135, "output_token_cost": 0.036, "token_counts": { "total_input_tokens": 45, "total_output_tokens": 2400, "total_tokens": 2445 }, "num_agents": 4, "service_tier": "standard", "night_time_discount_applied": false }, "total_cost": 0.076135, "discount_active": false } } } ``` ## Best Practices * Design agents with complementary but distinct expertise to maximize discussion breadth * Use descriptive system prompts that instruct agents to build on and react to other participants' input * GroupChat works best with 3-6 agents — too few limits perspective diversity, too many dilutes focus * Ideal for brainstorming and planning tasks where interactive dialogue adds more value than independent analysis