Decision Log

The Decision Log Store records decisions made by agents with reasoning, context, and outcomes. Useful for auditing agent behavior, debugging unexpected outcomes, and building feedback loops.

Aspect	Value
Scope	Per agent
Persistence	Long-term
Default mode	Always (`DecisionLogConfig()`), Agentic (`decision_log=True`)
Supported modes	Always, Agentic

Basic Usage

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.learn import LearningMachine, DecisionLogConfig
from agno.models.openai import OpenAIResponses

agent = Agent(
    id="my-agent",
    model=OpenAIResponses(id="gpt-5.2"),
    db=PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai"),
    learning=LearningMachine(
        decision_log=DecisionLogConfig(),  # defaults to LearningMode.ALWAYS
    ),
    instructions=[
        "When you make a significant choice, use log_decision to record it.",
        "Include your reasoning and alternatives you considered.",
    ],
)

agent.print_response(
    "I need help choosing between Python and JavaScript for web scraping.",
    session_id="session_1",
)

# View logged decisions
lm = agent.learning_machine
lm.decision_log_store.print(agent_id="my-agent", limit=5)

Agentic Mode

The agent receives tools to explicitly log decisions.

from agno.learn import LearningMachine, LearningMode, DecisionLogConfig

agent = Agent(
    id="my-agent",
    model=OpenAIResponses(id="gpt-5.2"),
    db=db,
    learning=LearningMachine(
        decision_log=DecisionLogConfig(mode=LearningMode.AGENTIC),
    ),
)

Available tools: log_decision, record_outcome, search_decisions The agent decides when a decision is significant enough to log.

Always Mode

Tool calls are automatically logged as decisions.

from agno.learn import LearningMachine, LearningMode, DecisionLogConfig
from agno.tools.duckduckgo import DuckDuckGoTools

agent = Agent(
    id="my-agent",
    model=OpenAIResponses(id="gpt-5.2"),
    db=db,
    learning=LearningMachine(
        decision_log=DecisionLogConfig(mode=LearningMode.ALWAYS),
    ),
    tools=[DuckDuckGoTools()],
)

agent.print_response("What are the latest developments in AI agents?")
# Tool calls are automatically recorded as decisions

Extraction starts in the background before the model finishes generating its response, and only scans tool calls already present in the message snapshot at that point. On a single run, the current turn’s tool calls may not be captured; logging becomes reliable from the next run once those messages are part of the conversation history.

The tradeoff is that every tool call gets logged, which can add noise.

Data Model

Field	Description
`id`	Unique identifier (e.g., “dec_abc123”)
`decision`	What was decided
`reasoning`	Why this decision was made
`decision_type`	Category: tool_selection, response_style, clarification
`context`	The situation that required a decision
`alternatives`	Other options considered
`confidence`	How confident (0.0 to 1.0)
`outcome`	What happened as a result
`outcome_quality`	Was it good, bad, or neutral
`created_at`	When the decision was made

Recording Outcomes

Update decisions with what actually happened to build feedback loops:

lm = agent.learning_machine

# Via store directly
lm.decision_log_store.update_outcome(
    decision_id="dec_abc123",
    outcome="User was satisfied with Python recommendation",
    outcome_quality="good",
)

Or the agent can use the record_outcome tool during conversation.

Accessing Decisions

lm = agent.learning_machine

# Search decisions
decisions = lm.decision_log_store.search(
    agent_id="my-agent",
    decision_type="tool_selection",
    days=7,
    limit=10,
)

for d in decisions:
    print(f"{d.decision}: {d.reasoning}")

# Debug output
lm.decision_log_store.print(agent_id="my-agent", limit=5)

Context Injection

Recent decisions are injected into the system prompt:

<decision_log>
Recent decisions:

- **Recommended Python over JavaScript**
  Reasoning: Web scraping libraries are more mature in Python
  Outcome: User was satisfied

- **Used web search for current info**
  Reasoning: Question about recent developments requires fresh data
</decision_log>

Decision Types

Common categories for organizing decisions:

Type	When to use
`tool_selection`	Choosing which tool to call
`response_style`	Deciding how to format or phrase response
`clarification`	Choosing to ask for more info
`escalation`	Deciding to defer to human
`approach`	Choosing between solution strategies

Use Cases

Auditing: Review what decisions agents made and why
Debugging: Understand unexpected behavior by examining reasoning
Learning: Analyze outcome patterns to improve agent instructions
Feedback loops: Record outcomes to identify successful patterns

Get Started

Basics

Advanced

Production

Providers

Other

Additional Resources

Decision Log

Basic Usage

Agentic Mode

Always Mode

Data Model

Recording Outcomes

Accessing Decisions

Context Injection

Decision Types

Use Cases

​Basic Usage

​Agentic Mode

​Always Mode

​Data Model

​Recording Outcomes

​Accessing Decisions

​Context Injection

​Decision Types

​Use Cases

Basic Usage

Agentic Mode

Always Mode

Data Model

Recording Outcomes

Accessing Decisions

Context Injection

Decision Types

Use Cases