Skip to main content
engineering_briefing.py
"""
Engineering briefing: Slack + Workspace + Parallel Web
======================================================

Three sources, one agent.

  Slack      what the team is talking about right now
  Workspace  what this repo already knows about it
  Web        fallback context when the repo has no clear match

The main agent does synthesis. Each provider owns its own mess.

Requires:
    OPENAI_API_KEY
    PARALLEL_API_KEY   https://platform.parallel.ai/
    SLACK_BOT_TOKEN    scopes: channels:read, channels:history,
                       users:read, chat:write
    pip install parallel-web
"""

from __future__ import annotations

import asyncio
from pathlib import Path

from agno.agent import Agent
from agno.context.slack import SlackContextProvider
from agno.context.web import ParallelBackend, WebContextProvider
from agno.context.workspace import WorkspaceContextProvider
from agno.models.openai import OpenAIResponses

PROJECT_ROOT = Path(__file__).resolve().parents[2]

# Sub-agents do source-specific tool work with a smaller model.
provider_model = OpenAIResponses(id="gpt-5.4-mini")

slack = SlackContextProvider(model=provider_model)
codebase = WorkspaceContextProvider(id="agno", root=PROJECT_ROOT, model=provider_model)
web = WebContextProvider(backend=ParallelBackend(), model=provider_model)

agent = Agent(
    model=OpenAIResponses(id="gpt-5.4"),
    tools=[*slack.get_tools(), *codebase.get_tools(), *web.get_tools()],
    markdown=True,
)


if __name__ == "__main__":
    print(f"slack    = {slack.status()}")
    print(f"codebase = {codebase.status()}")
    print(f"web      = {web.status()}\n")

    prompt = (
        "First call query_slack to read the 10 most recent messages from #agents and pick "
        "2 active topics. Do not call query_agno until query_slack returns those topics. "
        "For each topic, then call query_agno to look for local codebase context. Only call "
        "query_web when query_agno has no clear local match for that topic; use web search "
        "to fill the missing context and say the local match was not found. Write a "
        "Slack-friendly numbered list, not a markdown table. For each topic include: Topic, "
        "Slack signal, Codebase context, External fallback if used, Sync question. Then post "
        "the list in #test-agents."
    )
    print(f"> {prompt}\n")
    asyncio.run(agent.aprint_response(prompt))

Run the Example

1

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
2

Install dependencies

uv pip install -U agno openai parallel-web
3

Export your API keys

export OPENAI_API_KEY="your_openai_api_key_here"
export PARALLEL_API_KEY="your_parallel_api_key_here"
export SLACK_BOT_TOKEN="your_slack_bot_token_here"
export SLACK_TOKEN="your_slack_token_here"
export SLACK_USER_TOKEN="your_slack_user_token_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
$Env:PARALLEL_API_KEY="your_parallel_api_key_here"
$Env:SLACK_BOT_TOKEN="your_slack_bot_token_here"
$Env:SLACK_TOKEN="your_slack_token_here"
$Env:SLACK_USER_TOKEN="your_slack_user_token_here"
4

Run the example

Save the code above as engineering_briefing.py, then run:
python engineering_briefing.py
Full source: cookbook/12_context/12_engineering_briefing.py