[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [FDA complete response letter search](https://spiral.ai/integrations/instinct/fda-complete-response-letter-search)

# How to Use FDA complete response letter search in Instinct

Finds published FDA complete response letters for drug and biologic applications, including applications later approved. Use it to identify relevant letters before reading their detailed findings.

|  |  |
| --- | --- |
| Model | FDA complete response letter search |
| Available through | Alexandria |
| Category | Health |
| Price | $0.00873 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with FDA complete response letter search in Instinct

- Each week, use FDA complete response letter search to check for newly available Regeneron letters and summarize any letters absent from the previous digest.
- Every Monday at 9am: use FDA complete response letter search to look this up and give me the result as a table.
- Pull the latest numbers from FDA complete response letter search and tell me what changed since last week.
- Check FDA complete response letter search and summarize what you find in three bullet points.
- Pull the newest data from FDA complete response letter search and give me the result as a table.

## How to set up FDA complete response letter search in Instinct

Pick the way that suits you. Each takes about two minutes.

### Use the Spiral skill

1. **Send Instinct this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use Spiral's MCP server

1. **Create an API key**: In the console, open API keys and create a key for Instinct. Copy it.

2. **Send Instinct this message**: Instinct reads Spiral's skill and asks for your API key.

```text
set up https://spiral.ai/SKILL.md
```

3. **Give Instinct the key**: When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run FDA complete response letter search**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "alexandria",
    "model": "fda-gov/records/complete_response_letters",
    "input": {
      "skip": 0
    }
  }'
```

Then paste one of the prompts above: Instinct finds FDA complete response letter search on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/instinct

## FDA complete response letter search tools and prices

- [FDA · Complete response letters](https://spiral.ai/tools/alexandria/fda-gov/records/complete_response_letters) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| skip | 0 to 25000 | 0 | skip |
| limit | 1 to 50 | 10 | limit |
| query |  | — | Words that must all appear in the letter text; wrap a phrase in double quotes, e.g. "Form 483" or immunogenicity. |
| company_name |  | — | Company name words, e.g. Regeneron. |
| letter_date_to |  | — | Latest letter date, YYYY-MM-DD. Pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}$. |
| letter_date_from |  | — | Earliest letter date, YYYY-MM-DD. Pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}$. |

## What can you do with FDA complete response letter search in Instinct?

Maintain an internal research digest of newly published FDA evidence for a product or company watchlist. A scheduled agent can compare successive results and summarize new documents or revised records while accounting for each dataset's publication lag.

### Company regulatory due diligence

Build an evidence packet for a public drug or device company using its published application decisions, documents, listings, labeling, adverse event reports, and recall findings. Keep each record's regulatory meaning attached to the finding.

### Internal FDA research digest

Prepare a recurring digest of newly available or changed FDA evidence for a company or product watchlist. Separate application decisions, submitted product information, reported reactions, and historical recall findings.

### Regulatory milestone timelines

Reconstruct a drug application's published review history or a device's 510(k) decision history. Put CRL findings beside subsequent application milestones and links to supporting documents.

### Product claim fact-checking

Check public claims about approval, labeling, product identity, reported adverse reactions, or recall findings against the relevant FDA records. Identify the exact passage or decision that supports each statement.

### Publication evidence archive

Assemble the FDA evidence behind a company profile, product explainer, or regulatory investigation. Preserve document links, source identifiers, dates, and the passages used so an editor can check the published account.

### CRL deficiency comparison

Find published letters mentioning manufacturing or clinical deficiencies, then read the relevant passages. Compare FDA's stated concerns and requested actions across applications without estimating unpublished rejection rates.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All Instinct guides](https://spiral.ai/integrations/instinct)

## FDA complete response letter search in other agents

- [Amp](https://spiral.ai/integrations/amp/fda-complete-response-letter-search)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/fda-complete-response-letter-search)
- [Claude](https://spiral.ai/integrations/claude-desktop/fda-complete-response-letter-search)
- [Claude Code](https://spiral.ai/integrations/claude-code/fda-complete-response-letter-search)
- [Cline](https://spiral.ai/integrations/cline/fda-complete-response-letter-search)
- [Codex](https://spiral.ai/integrations/codex/fda-complete-response-letter-search)
- [Cursor](https://spiral.ai/integrations/cursor/fda-complete-response-letter-search)
- [Devin](https://spiral.ai/integrations/devin/fda-complete-response-letter-search)
- [dots](https://spiral.ai/integrations/dots/fda-complete-response-letter-search)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/fda-complete-response-letter-search)
- [Gemini](https://spiral.ai/integrations/gemini/fda-complete-response-letter-search)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/fda-complete-response-letter-search)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/fda-complete-response-letter-search)
- [goose](https://spiral.ai/integrations/goose/fda-complete-response-letter-search)
- [Grok](https://spiral.ai/integrations/grok/fda-complete-response-letter-search)
- [Grok Build](https://spiral.ai/integrations/grok-build/fda-complete-response-letter-search)
- [Hermes](https://spiral.ai/integrations/hermes/fda-complete-response-letter-search)
- [Manus](https://spiral.ai/integrations/manus/fda-complete-response-letter-search)
- [Muse](https://spiral.ai/integrations/muse/fda-complete-response-letter-search)
- [Muse Code](https://spiral.ai/integrations/muse-code/fda-complete-response-letter-search)
- [n8n](https://spiral.ai/integrations/n8n/fda-complete-response-letter-search)
- [Notion](https://spiral.ai/integrations/notion/fda-complete-response-letter-search)
- [OpenClaw](https://spiral.ai/integrations/openclaw/fda-complete-response-letter-search)
- [opencode](https://spiral.ai/integrations/opencode/fda-complete-response-letter-search)
- [Perplexity](https://spiral.ai/integrations/perplexity/fda-complete-response-letter-search)
- [Raycast](https://spiral.ai/integrations/raycast/fda-complete-response-letter-search)
- [VS Code](https://spiral.ai/integrations/vscode/fda-complete-response-letter-search)
- [Windsurf](https://spiral.ai/integrations/windsurf/fda-complete-response-letter-search)
- [Zapier](https://spiral.ai/integrations/zapier/fda-complete-response-letter-search)

## More Instinct guides

- [FDA complete response letter details](https://spiral.ai/integrations/instinct/fda-complete-response-letter-details)
- [FDA device 510(k) decisions](https://spiral.ai/integrations/instinct/fda-device-510-k-decisions)
- [FDA cell and gene therapy approvals](https://spiral.ai/integrations/instinct/fda-cell-and-gene-therapy-approvals)
- [FDA device PMA approvals](https://spiral.ai/integrations/instinct/fda-device-pma-approvals)
- [FDA Purple Book biologic records](https://spiral.ai/integrations/instinct/fda-purple-book-biologic-records)
- [FDA device UDI records](https://spiral.ai/integrations/instinct/fda-device-udi-records)

## Questions about FDA complete response letter search in Instinct

**Can Instinct use FDA complete response letter search?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run FDA complete response letter search like any built-in tool.

**How much does FDA complete response letter search cost in Instinct?**

$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.

**Do I need an Alexandria account to use FDA complete response letter search in Instinct?**

You need no Alexandria account. Instinct uses one Spiral API key for every tool, and Spiral runs FDA complete response letter search on its own Alexandria account.

**How long does it take to set up FDA complete response letter search in Instinct?**

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

**Does Instinct wait while FDA complete response letter search runs?**

FDA complete response letter search runs in the background. Instinct starts the run, checks on it and gives you the json when it's ready.

**How fresh are FDA records?**

FDA datasets follow different schedules. Application records update on weekdays, labeling updates weekly, 510(k) records update monthly, and FAERS updates quarterly with a possible lag of three months or more.

**How far back does FDA's published history go?**

Coverage depends on the record type: Drugs@FDA includes most products approved since 1939, 510(k) history begins in 1976, and the recall datasets begin in 2004. Supporting drug documents are more widely available for products approved since 1998.

**Does appearing in an FDA database prove a product is approved?**

An NDC number does not establish approval, and submitted labeling may differ from approved labeling. The CRL database also includes unapproved applications, while 510(k) records concern substantial equivalence decisions.

**Are public FDA records complete and independently verified?**

Public CRLs have confidential commercial information and trade secrets removed. NDC information is submitted by labelers, and adverse event reports do not establish that a product caused the reported reaction.

**Can FDA data be reused in a commercial research product?**

Unless otherwise noted, openFDA materials carry a CC0 1.0 dedication that permits commercial reuse. Some third-party material has separate restrictions, so the terms do not grant unrestricted rights to every included work.

