# AI use cases for DSH Industry Research (PerryLink/dsh-industry-research)

Repo: [PerryLink/dsh-industry-research](https://github.com/PerryLink/dsh-industry-research) | Use cases: 4 | Page: https://dedupedai.com/use-cases/perrylink-dsh-industry-research/

A DeepSeek Harness domain pack for industry and company research that builds sourced chain maps, tracks public sources, writes company cards, and assembles auditable reports.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Map an industry chain with sourced values and gap list: https://dedupedai.com/use-cases/perrylink-dsh-industry-research/build-sourced-industry-chain-map/
- Track policy and news for an industry in one timeline: https://dedupedai.com/use-cases/perrylink-dsh-industry-research/track-industry-policy-and-news-timeline/
- Build company research cards from your own data files: https://dedupedai.com/use-cases/perrylink-dsh-industry-research/produce-company-cards-from-workspace-files/
- Assemble an auditable industry report with verified evidence: https://dedupedai.com/use-cases/perrylink-dsh-industry-research/assemble-auditable-industry-report/

## How to map an industry chain with sourced values and gap list with DSH Industry Research

Repo: [PerryLink/dsh-industry-research](https://github.com/PerryLink/dsh-industry-research) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Build an upstream, midstream, and downstream chain map where every number carries a source and missing data is listed.

**Who it is for:** An industry analyst starting a sector study who needs a structured chain map with no unsourced figures.

**The problem:** Chain maps often mix guessed numbers with sourced ones, and missing layers go unnoticed.

**The outcome:** A validated chain.json plus a list of explicit gap slots and bottleneck nodes for the industry.

### Steps

1. `dsh plugin --profile demo add dsh-industry-research`
2. `dsh --profile demo --dump-config | grep dsh-industry-research`
3. In a session, load the method: 加载 industry-research-method 技能
4. Call industry_map with a chain of nodes (tier upstream, midstream, downstream) and edges, giving each sourced metric a sourceRef
5. Read the gap list returned by industry_map and fill or keep each gap marked 待补

### Prompt to paste into your agent

```text
Using the dsh-industry-research plugin in DeepSeek Harness, call industry_map for the industry <industry-name> with a chain of nodes and edges. Expect a saved chain.json and a gap list. Verify that every metric with a value has a sourceRef, and that the tool reports the gaps rather than filling them.
```

### Caveat

The pack is for research support only and is not investment advice, and it does not use paid or login-walled sources.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/perrylink-dsh-industry-research/build-sourced-industry-chain-map/

## How to track policy and news for an industry in one timeline with DSH Industry Research

Repo: [PerryLink/dsh-industry-research](https://github.com/PerryLink/dsh-industry-research) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Search topics through the web tool and keep a deduplicated, dated timeline of public sources for an industry.

**Who it is for:** A researcher following regulation and sector news who needs a dated record with citations.

**The problem:** Policy and news for a sector scatter across pages, and it is hard to tell what changed since the last check.

**The outcome:** A timeline.jsonl with source snapshots, each entry labeled by evidence category, and a delta summary against the previous run.

### Steps

1. `dsh plugin --profile demo add dsh-industry-research`
2. Confirm ctx.web is mounted and that offline is false in the profile config
3. Optionally set sourceAllowlist to the public hosts you trust
4. Call industry_track with the industry name, topics, and a since date
5. Review the timeline entries and any citation-only entries with their failure notes

### Prompt to paste into your agent

```text
With the dsh-industry-research plugin in DeepSeek Harness, call industry_track for the industry <industry-name> with a list of topics and a since date. Expect timeline.jsonl entries and a delta summary. Verify that each entry has an evidence category and that failed snapshots appear as citation-only entries with a note.
```

### Caveat

industry_track fails loud when ctx.web is not mounted or offline is true, so it needs a web-enabled profile.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/perrylink-dsh-industry-research/track-industry-policy-and-news-timeline/

## How to build company research cards from your own data files with DSH Industry Research

Repo: [PerryLink/dsh-industry-research](https://github.com/PerryLink/dsh-industry-research) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Turn Markdown, text, CSV, TSV, or JSON files in the workspace into company cards with explicit gaps.

**Who it is for:** A buy-side or corporate strategy analyst with company filings and notes saved locally who needs consistent company cards.

**The problem:** Company notes are uneven, and metrics often lack a source or a date.

**The outcome:** A company card per company, with rejected files listed with reasons and every unestablished item shown as a gap.

### Steps

1. `dsh plugin --profile demo add dsh-industry-research`
2. Place the company data files (.md, .txt, .csv, .tsv, or .json) in the session workspace; PDF is not parsed in v1
3. Load the method: 加载 company-research-method 技能
4. Call company_scan with the company name or a batch of companies and the dataFiles list
5. Check that every metric carries source and asOf, and review the rejected-file reasons

### Prompt to paste into your agent

```text
Using the dsh-industry-research plugin in DeepSeek Harness, call company_scan for the companies <company-list> with the listed data files. Expect company cards and a list of rejected files with reasons. Verify that each metric has source and asOf, and that unsupported items appear as gaps.
```

### Caveat

Cards are research support only and do not give investment advice, and tickers must match the built-in formats unless strictTicker is set to false.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/perrylink-dsh-industry-research/produce-company-cards-from-workspace-files/

## How to assemble an auditable industry report with verified evidence with DSH Industry Research

Repo: [PerryLink/dsh-industry-research](https://github.com/PerryLink/dsh-industry-research) | Difficulty: Advanced | Time: 60 minutes | Basis: From the README

Combine chain, timeline, and company evidence into a report where each claim points to registered evidence.

**Who it is for:** A research lead who must hand over an industry report that another reader can audit claim by claim.

**The problem:** Reports drift from their sources, and unsourced or undated assertions slip through.

**The outcome:** A report.md and manifest.json with a source-traceability table, and claims marked by verdict or as unverified.

### Steps

1. `dsh plugin --profile demo add dsh-industry-research`
2. Finish the chain map with industry_map and the timeline with industry_track first
3. Run company_scan for any companies the report will cover
4. Call industry_report with the industry name, sections, and optional draft, or let it build the auto-draft
5. Open report.md and manifest.json and confirm each claim links to an evidence ID

### Prompt to paste into your agent

```text
With the dsh-industry-research plugin in DeepSeek Harness, call industry_report for the industry <industry-name>, using the existing chain, timeline, and company artifacts. Expect report.md and manifest.json in the reports folder. Verify that every claim's evidence IDs exist and that the delivery contract passed with no placeholders.
```

### Caveat

The report is research support only, and claims marked unverified on the fallback path still need a human check against their sources.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/perrylink-dsh-industry-research/assemble-auditable-industry-report/