# Merchant opportunity brief Agent Kit

Build a merchant opportunity brief with SignalTally Agent Kits. Run a real public Shopify example locally, then add LangChain, CrewAI or a Viktor task prompt.

Bring theme fit, payment evidence and popularity into your agent’s next account brief. Start with a real public observation and a reason your team can inspect.

## Check merchant fit

Match a premium theme with Apple Pay detected in the supplied evidence.

## Add popularity context

Keep the observed rank and its separate date. Open the report to investigate its history.

## Draft the next question

Prepare an account brief with evidence, unknowns and a specific point for discovery.

## Working commerce starters

Free starter code with local Python evidence checks, optional LangChain and CrewAI runners, and a Viktor task prompt. The five-minute quickstart refers to the local case with Python already installed. Model drafting requires your own provider account and credentials; Viktor requires your own workspace. No installed Viktor connector is included.

## Merchant opportunity brief

From merchant evidence to a useful account conversation.

Nanit is a selected public observation, not a customer endorsement. Theme and payment evidence is dated 12 September 2026; popularity has its own date and is not visits or revenue.

[Download ZIP](https://signaltally.com/assets/signaltally-merchant-opportunity-brief.zip)

```bash
cd signaltally-merchant-opportunity-brief
python3 run.py
```

Output: evidence.json and brief.md. Example output, replayed at 13 September 2026:

- Concept premium theme match
- Apple Pay detected
- Global rank #81,054 · 3 Sep 2026
- Product compatibility · validate

## Local quickstart

Python 3.10+ installed. Run the included case with no dependencies or network calls. The five-minute guide covers this local run.

```bash
python3 run.py
# Open output/brief.md and output/evidence.json
```

## LangChain

Python 3.10–3.13, a configured model and your Anthropic API key. The runner sends the selected evidence to your model provider; usage is billed by that provider.

```bash
python3 -m venv .venv-langchain
.venv-langchain/bin/python -m pip install -r requirements-langchain.txt
# Set ANTHROPIC_API_KEY and SIGNALTALLY_MODEL in your environment.
.venv-langchain/bin/python run.py --runtime langchain --output output-langchain
```

## CrewAI

Python 3.10–3.13 and your configured Anthropic model. An analyst and a reviewer prepare a draft in sequence. Provider usage is separate.

```bash
python3 -m venv .venv-crewai
.venv-crewai/bin/python -m pip install -r requirements-crewai.txt
# Set ANTHROPIC_API_KEY and SIGNALTALLY_MODEL in your environment.
.venv-crewai/bin/python run.py --runtime crewai --output output-crewai
```

## Viktor

Generate a task prompt locally. Paste it into your own Viktor conversation for review. A Viktor account is required for execution; this is a task template, not an installed connector.

```bash
python3 run.py --runtime viktor --output output-viktor
# Paste output-viktor/viktor-task.md into your Viktor conversation.
```

The local run reads case JSON and writes local files. It does not crawl stores, send messages or alter customer systems. Generated drafts require review. Supply your own entitled evidence with --input; paid SignalTally audience and delivery scope are agreed separately. Agency is $2,000/month USD. Source attribution and observation dates must remain attached.

## Related pages

- [All Agent Kits](https://signaltally.com/agent-kits): Choose your next workflow.
- [SignalTally Radar](https://signaltally.com/product/radar): Explore merchant evidence.
- [Plan your launch](https://signaltally.com/launch): Scope licensed intelligence.

Canonical source: [SignalTally](https://signaltally.com/agent-kits/merchant-opportunity-brief)

[Data and attribution guide](https://signaltally.com/llms.txt)