Analysis Agent

curl -X POST https://api.relace.run/v1/repo/123e4567-e89b-12d3-a456-426614174000/agent \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_name": "code-analyzer",
    "agent_inputs": {
      "query": "Analyze user engagement data and create visualization plots",
      "system_prompt": "Generate comprehensive data analysis with matplotlib/plotly visualizations"
    },
    "overrides": {}
  }'

event: started
data: {"prompt_id": "prompt_123e4567-e89b-12d3-a456-426614174000"}

event: agent
data: {"content": "I'll analyze the user engagement data and create visualization plots.", "type": "reasoning"}

event: tool
data: {"tool_name": "data_analyzer", "content": "Loading dataset with 10,000 records", "status": "started"}

event: tool
data: {"tool_name": "data_analyzer", "content": "Analysis complete. Found key patterns in engagement data.", "status": "completed"}

event: agent
data: {"content": "Analysis shows 65% higher engagement on weekends with peak activity between 2-4 PM.", "type": "response"}

event: tool
data: {"tool_name": "plot_generator", "content": "Generating engagement trend visualization", "status": "started"}

event: committed
data: {"files": ["plots/engagement_trends.png", "analysis/engagement_report.md"], "message": "Add engagement analysis and visualization plots"}

event: build
data: {"event": "start", "output": "Building visualization components..."}

event: build
data: {"event": "pass", "output": "Build completed successfully"}

event: deployed
data: {"status": "success", "url": "https://app.relace.ai/repo/123e4567/viz"}

event: done
data: {"summary": "Successfully analyzed engagement data and generated 2 visualization plots"}

POST

repo

{repo_id}

agent

curl -X POST https://api.relace.run/v1/repo/123e4567-e89b-12d3-a456-426614174000/agent \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_name": "code-analyzer",
    "agent_inputs": {
      "query": "Analyze user engagement data and create visualization plots",
      "system_prompt": "Generate comprehensive data analysis with matplotlib/plotly visualizations"
    },
    "overrides": {}
  }'

event: started
data: {"prompt_id": "prompt_123e4567-e89b-12d3-a456-426614174000"}

event: agent
data: {"content": "I'll analyze the user engagement data and create visualization plots.", "type": "reasoning"}

event: tool
data: {"tool_name": "data_analyzer", "content": "Loading dataset with 10,000 records", "status": "started"}

event: tool
data: {"tool_name": "data_analyzer", "content": "Analysis complete. Found key patterns in engagement data.", "status": "completed"}

event: agent
data: {"content": "Analysis shows 65% higher engagement on weekends with peak activity between 2-4 PM.", "type": "response"}

event: tool
data: {"tool_name": "plot_generator", "content": "Generating engagement trend visualization", "status": "started"}

event: committed
data: {"files": ["plots/engagement_trends.png", "analysis/engagement_report.md"], "message": "Add engagement analysis and visualization plots"}

event: build
data: {"event": "start", "output": "Building visualization components..."}

event: build
data: {"event": "pass", "output": "Build completed successfully"}

event: deployed
data: {"status": "success", "url": "https://app.relace.ai/repo/123e4567/viz"}

event: done
data: {"summary": "Successfully analyzed engagement data and generated 2 visualization plots"}

Path Parameters

repo_id

string

required

Repo ID

Request Body

agent_name

string

required

Name of the predefined agent to run

agent_inputs

object

required

Input parameters for the agent

Show properties

query

string

required

The query or question to process with the agent

system_prompt

string

Custom system prompt to guide the agent’s behavior

Response

The agent returns a Server-Sent Events (SSE) stream with real-time updates from tool calls. The various event types indicate different stages of execution.

Event Types

started

event

Signals that the agent execution has begun

Show properties

prompt_id

string

Unique identifier for this agent execution session

agent

event

Contains agent reasoning, analysis, and text responses

Show properties

content

string

The agent’s response content or reasoning

type

string

Type of agent message (e.g., “reasoning”, “response”)

tool

event

Reports tool usage and execution results

Show properties

tool_name

string

Name of the tool being used

content

string

Tool execution details or results

status

string

Tool execution status (e.g., “started”, “completed”)

committed

event

Indicates code changes have been made to the repository

Show properties

files

array

List of files that were modified

message

string

Commit message describing the changes

build

event

Reports build process status and results

Show properties

event

string

Build event type: “start”, “pass”, or “fail”

output

string

Build output or error messages

test

event

Reports test execution status and results

Show properties

event

string

Test event type: “start”, “pass”, or “fail”

output

string

Test output or results

deployed

event

Signals that changes have been deployed/visualizations updated

Show properties

status

string

Deployment status

url

string

URL to view the deployed changes

prompt_error

event

Reports errors that occurred during agent execution

Show properties

error

string

Error message describing what went wrong

code

string

Error code for programmatic handling

done

event

Signals that the agent execution has completed successfully

Show properties

summary

string

Summary of what was accomplished

curl -X POST https://api.relace.run/v1/repo/123e4567-e89b-12d3-a456-426614174000/agent \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_name": "code-analyzer",
    "agent_inputs": {
      "query": "Analyze user engagement data and create visualization plots",
      "system_prompt": "Generate comprehensive data analysis with matplotlib/plotly visualizations"
    },
    "overrides": {}
  }'

event: started
data: {"prompt_id": "prompt_123e4567-e89b-12d3-a456-426614174000"}

event: agent
data: {"content": "I'll analyze the user engagement data and create visualization plots.", "type": "reasoning"}

event: tool
data: {"tool_name": "data_analyzer", "content": "Loading dataset with 10,000 records", "status": "started"}

event: tool
data: {"tool_name": "data_analyzer", "content": "Analysis complete. Found key patterns in engagement data.", "status": "completed"}

event: agent
data: {"content": "Analysis shows 65% higher engagement on weekends with peak activity between 2-4 PM.", "type": "response"}

event: tool
data: {"tool_name": "plot_generator", "content": "Generating engagement trend visualization", "status": "started"}

event: committed
data: {"files": ["plots/engagement_trends.png", "analysis/engagement_report.md"], "message": "Add engagement analysis and visualization plots"}

event: build
data: {"event": "start", "output": "Building visualization components..."}

event: build
data: {"event": "pass", "output": "Build completed successfully"}

event: deployed
data: {"status": "success", "url": "https://app.relace.ai/repo/123e4567/viz"}

event: done
data: {"summary": "Successfully analyzed engagement data and generated 2 visualization plots"}

⌘I

​Path Parameters

​Request Body

​Response

​Event Types

Path Parameters

Request Body

Response

Event Types