Structured deliverable

Return a typed decision with the call, conviction, allocation, rationale, and citations.

Make the final pipeline step return a typed decision that downstream code can validate and use. Define the call, conviction, allocation, rationale, and citations in a Pydantic schema, then pass it as the final agent’s output_schema.

from typing import List, Literal

from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from pydantic import BaseModel, Field


class Decision(BaseModel):
    call: Literal["BUY", "HOLD", "PASS"] = Field(..., description="The committee decision")
    conviction: Literal["low", "medium", "high"] = Field(..., description="Confidence in the call")
    allocation_usd: float = Field(..., description="Dollar allocation, 0 if not BUY")
    rationale: str = Field(..., description="Why, referencing the analyst inputs")
    citations: List[str] = Field(..., description="Sources and prior memos used")


chair = Agent(
    name="Committee Chair",
    model=OpenAIResponses(id="gpt-5.5"),
    output_schema=Decision,
    instructions=(
        "Synthesize the analyst inputs into a decision. Every BUY needs a "
        "dollar amount. Every decision must reference at least one risk."
    ),
)


def briefing(*analyst_outputs: str) -> str:
    return "Analyst inputs:\n\n" + "\n\n".join(analyst_outputs)


result = chair.run(briefing(market, fundamentals, technicals, risk)).content
# Decision(call='BUY', conviction='high', allocation_usd=2_000_000.0,
#          rationale='Momentum and fundamentals align; sized within the
#                      sector cap the Risk Officer set.',
#          citations=['memo:NVDA-2024Q3', 'research:semiconductors'])

Because output_schema=Decision, the run returns a validated Decision. Downstream code reads result.call and result.allocation_usd directly. If the model’s output fails validation, Agno logs a warning and content stays a string, so check the type before acting on it.

The chair weighs the specialists’ inputs and commits to a call. Its configuration omits tools so every conclusion comes from the supplied briefing.

Decision and memo

A research system usually produces both a machine-actionable decision and a human-readable memo.

Artifact	Form	Consumer
Decision	Typed object (output_schema)	Downstream automation, dashboards, audit
Memo	Markdown written to disk	Humans, the next review’s context

The memo is written by a dedicated agent with file tools and a fixed template, then archived. The next review reads it back as prior work. The decision is the row you store and act on.

Required decision fields

Field	Purpose
conviction	Lets you threshold: act on high, queue medium for review
rationale	Records the reasoning trail for review and audit
citations	Carries source identifiers for downstream verification

Require citations in the schema and instructions so each decision carries source identifiers for verification.

Add approval for consequential actions

When a decision triggers a real action, such as moving capital or publishing a number, add human approval before the action executes. See human approval.

Next steps

Task	Guide
Carry the memo into the next run	Grounding research
Make decisions improve over time	Institutional learning
Serve the decision to a surface	Serve and embed

Developer Resources

• Structured output
• Workflows cookbook
• Human approval