# Research Brief — sourced answers with citations (`physealabs/research-brief`) Actor

Researches a question from public web sources and supplied URLs, then produces a concise, citation-backed markdown brief plus machine-readable source records.

- **URL**: https://apify.com/physealabs/research-brief.md
- **Developed by:** [jay casey](https://apify.com/physealabs) (community)
- **Categories:** AI, Other
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-usage

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## Research Brief

Turn a research question into a concise, citation-backed Markdown brief. The Actor discovers public web sources (or uses URLs you provide), extracts readable evidence, and asks an OpenAI-compatible model to synthesize only from that evidence.

### Input

```json
{
  "question": "What are the strongest current arguments for and against small language models at the edge?",
  "context": "For a product strategy review; focus on 2025–2026 evidence.",
  "depth": "standard",
  "sourceUrls": [],
  "search": true
}
```

- `question` (required): the question to answer.
- `context` (optional): audience, constraints, or decision context.
- `depth`: `quick` (up to 3 sources), `standard` (up to 6), or `deep` (up to 10).
- `sourceUrls` (optional): URLs to prioritize.
- `search`: discover additional sources via DuckDuckGo (default `true`).
- `llm` (optional): `{ "baseUrl", "model", "apiKey" }` for an OpenAI-compatible `/v1/chat/completions` endpoint.

### Output

- `RESEARCH_BRIEF.md`: structured brief with inline citations such as `[S1]`.
- Dataset: one row per fetched or failed source, including citation ID, URL, excerpt, and status.
- `RUN_SUMMARY.json`: depth, model, source counts, timestamps, and any search/synthesis errors.

If model synthesis fails, the run stores an explicitly labeled evidence-only brief rather than inventing an answer. Pay-per-event charging occurs only after a fully synthesized, citation-validated brief.

### Local development

```bash
python -m venv .venv
.venv/bin/pip install -r requirements.txt pytest pytest-asyncio
.venv/bin/python -m pytest -q

mkdir -p storage/key_value_stores/default
cat > storage/key_value_stores/default/INPUT.json <<'JSON'
{"question":"What is this page about?","depth":"quick","sourceUrls":["https://example.com"],"search":false}
JSON
APIFY_LOCAL_STORAGE_DIR="$PWD/storage" CRAWLEE_STORAGE_DIR="$PWD/storage" LLM_FAKE=1 .venv/bin/python -m src
```

`LLM_FAKE=1` is deterministic and intended only for local pipeline verification. Remove it for real synthesis.

# Actor input Schema

## `question` (type: `string`):

The specific question the brief should answer.

## `context` (type: `string`):

Optional background, constraints, audience, or decision this research should support.

## `depth` (type: `string`):

Quick uses up to 3 sources, standard up to 6, and deep up to 10.

## `sourceUrls` (type: `array`):

Optional URLs to prioritize. The Actor can also discover web sources.

## `search` (type: `boolean`):

Discover additional public web sources with DuckDuckGo.

## `llm` (type: `object`):

Optional OpenAI-compatible endpoint override: baseUrl, model, apiKey. Leave blank to use the Actor default model.

## Actor input object example

```json
{
  "depth": "standard",
  "search": true
}
```

# Actor output Schema

## `brief` (type: `string`):

The completed structured brief with inline citations.

## `sources` (type: `string`):

Machine-readable source records and fetch status.

## `summary` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("physealabs/research-brief").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("physealabs/research-brief").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call physealabs/research-brief --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,physealabs/research-brief"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/gNtYc4ephztGB5cwu/builds/O8tnBIwimC8nOhQrs/openapi.json