Using the Python SDK

Once you’ve installed Lucidic and connected it to the dashboard, you’re ready to start recording your agent’s behavior, step by step. This guide walks you through how to initialize a session, track steps and events, and optionally pull prompts from our Prompt DB.

Step 1: Create a Session

Theere are 4 things you need to provide to initialize a session:

session_name: A name for your session #Whatever you want to name it
lucidic_api_key: Your Lucidic API key #You should have this copied somewhere safe
agent_id: Your Lucidic Agent ID #You can get this from the dashboard
provider: The LLM provider you’re using #OpenAI, Anthropic, PydanticAI, or LangChain

Full version of init:

import lucidicai as lai
lai.init(
    session_name="search_wikipedia",
    lucidic_api_key="your-api-key",   # Or use env var: LUCIDIC_API_KEY
    agent_id="your-agent-id",         # Or use env var: LUCIDIC_AGENT_ID
    task="Search Wikipedia for Steve Jobs biography",
    providers=["openai"],                # "openai", "anthropic", "pydantic_ai", if "langchain" you can leave this blank checkout [LangChain Integration](/integrations/langchain)
    mass_sim_id="your-mass-sim-id",   # Optional
    rubrics=["default", "custom_score"]  # Optional
)

Shorter/more common version of init:

import lucidicai as lai
lai.init(
    session_name="search_wikipedia",
    providers = ["openai"],                
)

We reccomend moving the LUCIDIC_API_KEY and LUCIDIC_AGENT_ID to environment variables. The way to do this is create a .env file in the root of your project and add the following. Most of you will already have a .env (it is where you would keep any API key) and will just have to add a Lucidic API Key and a Lucidic Agent ID.

LUCIDIC_API_KEY=your-api-key
LUCIDIC_AGENT_ID=your-agent-id

OR You can set the environment variables in your terminal:

export LUCIDIC_API_KEY=your-api-key
export LUCIDIC_AGENT_ID=your-agent-id

Step 2: Create Steps

Use create_step() and end_step() around your step logic. Each step should represent a meaningful action or decision point.

lai.create_step(state="Home page", goal="Navigate to search")

# Your agent logic here...

lai.end_step(is_successful=True, action="Clicked search")

Only one step can be active at a time, so be sure to end a step before creating a new one.

Optional Fields You Can Attach to a Step

You can enrich any step with the following optional fields to improve debugging, evaluation, and traceability:

state – A short description of the current environment or UI (e.g., page title, visible content, or system state).
action – What the agent did in this step (e.g., “clicked submit”, “filled out form”).
goal – What the agent intended to accomplish (e.g., “navigate to checkout”, “extract user name”).
eval_score – A step-level rating (like "5" or "pass") to assess performance at that point.
eval_description – An explanation justifying the eval_score, useful for audits or structured reviews.
screenshot or screenshot_path – Visual context for this step, either as a base64-encoded image or a file path.

Step Updates

You can update steps mid-run or retroactively:

lai.update_step(action="Updated description")
lai.update_previous_step(index=-1, eval_score=0.5)

Step 3: Create Events

If your agent has tool calls or LLM usage, track them as events within each step.

If you only have LLM calls with a supported provider you don’t need to create events for them! Lucidic will automatically create events for you.

lai.create_event(description="OpenAI call")
# Do your LLM call...
lai.end_event(is_successful=True, result="Summary generated")

You can enrich any event with the following optional fields to improve debugging, evaluation, and traceability:

All of these are optional, but we recommend setting at least description and result.

description – A detailed explanation of the event (e.g., “clicked submit”, “completed form entry”), or any relevant input, context, or memory for your agent. This field is often used to capture user actions, LLM prompts, document processing inputs, or data retrieval details. Include any information you consider important for your agent.
is_successful – A boolean indicating whether the event was successful.
result – This is more of a result/output of the event. For example, if you are doing a document processing, this could be the result of the document processing. Or if you make an API call, this could be the result of the API call.
is_finished – A boolean indicating whether the event was finished. This will automatically be set to true when the event is ended.
model – A lot of people use events with LLMs so if you have a custom LLM call you can set the model name here.
cost – If you have a custom API call or LLM call you can set the cost here.

LLM calls from supported providers like OpenAI and Anthropic are automatically captured into events when you set the provider in init().

Step 4: (Optional) Pull Prompts from Prompt DB

Use Lucidic’s Prompt DB to version and serve prompts dynamically:

prompt = lai.get_prompt(
    prompt_name="summarize_webpage",
    variables={"page_text": "Stanford University is..."},
    label="production",
    cache_ttl=60
)

Here’s what each parameter does:

prompt_name: Prompt name
label: Label to fetch (defaults to production)
variables: Dictionary of string key/values to interpolate
cache_ttl:
- 0 = no cache
- -1 = cache forever
- n = cache for n seconds

Additional notes:

{{variable}} placeholders will be replaced using your dictionary
Missing keys will raise an error
Unreplaced variables will trigger a warning
Read more at Prompt DB

Step 5: End the Session

Your session will automatically end when the script exits (via an atexit handler), but you can also end it manually if you would like to add in evals:

lai.end_session(
    is_successful=True,
    is_successful_reason="Completed all steps",
    session_eval="5",
    session_eval_reason="Accurate and efficient"
)

All fields are optional — if you don’t provide them, Lucidic will automatically evaluate the session for you.

Custom Evaluation Rubrics

When ending a session, you can provide your own evaluation metrics to better assess your agent’s performance:

If you don’t provide evaluation metrics, Lucidic will automatically evaluate your session using default rubrics.
If you provide custom evaluation metrics, Lucidic will use your metrics instead of the default ones.

We recommend creating your own rubric for custom tasks to ensure the evaluation aligns with your specific requirements:

# When initializing your session, specify custom rubrics
lai.init(
    session_name="custom_task",
    providers=["openai"],
    rubrics=["default", "my_custom_rubric"]  # Include both default and custom rubrics
)

# When ending the session, provide your custom evaluation
lai.end_session(
    is_successful=True,
    session_eval="4.5",  # Your custom score which is not a rubric
    session_eval_reason="Agent completed primary objectives but took longer than expected"
)

Custom rubrics allow you to:

Define task-specific success criteria
Implement domain-specific evaluation metrics
Compare agent performance across different versions using consistent metrics
Track improvements over time with metrics tailored to your use case

Learn more about creating and using custom rubrics in the Evaluation Rubrics documentation.

Why Both `is_successful` and `session_eval`?

We support two types of evaluations so you can keep things simple or add more detail:

is_successful: A binary flag — did the agent complete the task?
session_eval: A more detailed score (e.g. 1–5) showing how well the agent did.

If you only want to pass in one value (like a numeric score), you can compute the other yourself:

score = 5
lai.end_session(
    is_successful=score >= 4,
    session_eval=str(score),
)

This gives you full control and lets you keep your logic consistent with your own success criteria.

Full Example

import lucidicai as lai

lai.init(
    session_name="wiki_search",
    agent_id="agent-123",
    providers=["openai"],
    task="Search for Stanford University",
    rubrics=["default"]
)

lai.create_step(state="Home", goal="Search for Stanford")

# (Your logic here)

lai.create_event(description="OpenAI call")
# (Your LLM call)
lai.end_event(is_successful=True, result="Found Stanford") #Optional 

lai.end_step(is_successful=True, action="Used search") #Required

lai.end_session(is_successful=True) #Optional

GetsStarted

Features

Integrations

Core Concepts

Python SDK Functions

Final Instructions [Creating Steps, Events, and Sessions]

Using the Python SDK

Step 1: Create a Session

Step 2: Create Steps

Optional Fields You Can Attach to a Step

Step Updates

Step 3: Create Events

Step 4: (Optional) Pull Prompts from Prompt DB

Step 5: End the Session

Custom Evaluation Rubrics

Why Both `is_successful` and `session_eval`?

Full Example

Next Steps

GetsStarted

Features

Integrations

Core Concepts

Python SDK Functions

​Using the Python SDK

​Step 1: Create a Session

​Step 2: Create Steps

​Optional Fields You Can Attach to a Step

​Step Updates

​Step 3: Create Events

​Step 4: (Optional) Pull Prompts from Prompt DB

​Step 5: End the Session

​Custom Evaluation Rubrics

​Why Both is_successful and session_eval?

​Full Example

​Next Steps

Using the Python SDK

Step 1: Create a Session

Step 2: Create Steps

Optional Fields You Can Attach to a Step

Step Updates

Step 3: Create Events

Step 4: (Optional) Pull Prompts from Prompt DB

Step 5: End the Session

Custom Evaluation Rubrics

Why Both `is_successful` and `session_eval`?

Full Example

Next Steps