aisa-search-skillIntelligent search for agents. Multi-source retrieval with confidence scoring - web, academic, and Tavily in one unified API.
Install via ClawdBot CLI:
clawdbot install bowen-dotcom/aisa-search-skillIntelligent search for autonomous agents. Powered by AIsa.
One API key. Multi-source retrieval. Confidence-scored answers.
Inspired by AIsa Verity - A next-generation search agent with trust-scored answers.
```
"Search for the latest papers on transformer architectures from 2024-2025"
```
```
"Find all web articles about AI startup funding in Q4 2025"
```
```
"Search for reviews and comparisons of RAG frameworks"
```
```
"Get the latest news about quantum computing breakthroughs"
```
```
"Smart search combining web and academic sources on 'autonomous agents'"
```
```bash
export AISA_API_KEY="your-key"
```
OpenClaw Search employs a Two-Phase Retrieval Strategy for comprehensive results:
Query 4 distinct search streams simultaneously:
Use AIsa Explain to perform meta-analysis on search results, generating:
```
┌─────────────────────────────────────────────────────────────┐
│ User Query │
└─────────────────────────────────────────────────────────────┘
│
┌───────────────┼───────────────┐
▼ ▼ ▼
┌─────────┐ ┌─────────┐ ┌─────────┐
│ Scholar │ │ Web │ │ Smart │
└─────────┘ └─────────┘ └─────────┘
│ │ │
└───────────────┼───────────────┘
▼
┌─────────────────┐
│ AIsa Explain │
│ (Meta-Analysis) │
└─────────────────┘
│
▼
┌─────────────────┐
│ Confidence Score│
│ + Synthesis │
└─────────────────┘
```
```bash
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/web?query=AI+frameworks&max_num_results=10" \
-H "Authorization: Bearer $AISA_API_KEY"
curl -X POST "https://api.aisa.one/apis/v1/search/full?query=latest+AI+news&max_num_results=10" \
-H "Authorization: Bearer $AISA_API_KEY"
```
```bash
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/scholar?query=transformer+models&max_num_results=10" \
-H "Authorization: Bearer $AISA_API_KEY"
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/scholar?query=LLM&max_num_results=10&as_ylo=2024&as_yhi=2025" \
-H "Authorization: Bearer $AISA_API_KEY"
```
```bash
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/smart?query=machine+learning+optimization&max_num_results=10" \
-H "Authorization: Bearer $AISA_API_KEY"
```
```bash
curl -X POST "https://api.aisa.one/apis/v1/tavily/search" \
-H "Authorization: Bearer $AISA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"query":"latest AI developments"}'
curl -X POST "https://api.aisa.one/apis/v1/tavily/extract" \
-H "Authorization: Bearer $AISA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"urls":["https://example.com/article"]}'
curl -X POST "https://api.aisa.one/apis/v1/tavily/crawl" \
-H "Authorization: Bearer $AISA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url":"https://example.com","max_depth":2}'
curl -X POST "https://api.aisa.one/apis/v1/tavily/map" \
-H "Authorization: Bearer $AISA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url":"https://example.com"}'
```
```bash
curl -X POST "https://api.aisa.one/apis/v1/scholar/explain" \
-H "Authorization: Bearer $AISA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"results":[...],"language":"en","format":"summary"}'
```
Unlike standard RAG systems, OpenClaw Search evaluates credibility and consensus:
| Factor | Weight | Description |
|--------|--------|-------------|
| Source Quality | 40% | Academic > Smart/Web > External |
| Agreement Analysis | 35% | Cross-source consensus checking |
| Recency | 15% | Newer sources weighted higher |
| Relevance | 10% | Query-result semantic match |
| Score | Confidence Level | Meaning |
|-------|-----------------|---------|
| 90-100 | Very High | Strong consensus across academic and web sources |
| 70-89 | High | Good agreement, reliable sources |
| 50-69 | Medium | Mixed signals, verify independently |
| 30-49 | Low | Conflicting sources, use caution |
| 0-29 | Very Low | Insufficient or contradictory data |
```bash
python3 {baseDir}/scripts/search_client.py web --query "latest AI news" --count 10
python3 {baseDir}/scripts/search_client.py scholar --query "transformer architecture" --count 10
python3 {baseDir}/scripts/search_client.py scholar --query "LLM" --year-from 2024 --year-to 2025
python3 {baseDir}/scripts/search_client.py smart --query "autonomous agents" --count 10
python3 {baseDir}/scripts/search_client.py full --query "AI startup funding"
python3 {baseDir}/scripts/search_client.py tavily-search --query "AI developments"
python3 {baseDir}/scripts/search_client.py tavily-extract --urls "https://example.com/article"
python3 {baseDir}/scripts/search_client.py verity --query "Is quantum computing ready for enterprise?"
```
| Endpoint | Method | Description |
|----------|--------|-------------|
| /scholar/search/web | POST | Web search with structured results |
| /scholar/search/scholar | POST | Academic paper search |
| /scholar/search/smart | POST | Intelligent hybrid search |
| /scholar/explain | POST | Generate result explanations |
| /search/full | POST | Full text search with content |
| /search/smart | POST | Smart web search |
| /tavily/search | POST | Tavily search integration |
| /tavily/extract | POST | Extract content from URLs |
| /tavily/crawl | POST | Crawl web pages |
| /tavily/map | POST | Generate site maps |
| Parameter | Type | Description |
|-----------|------|-------------|
| query | string | Search query (required) |
| max_num_results | integer | Max results (1-100, default 10) |
| as_ylo | integer | Year lower bound (scholar only) |
| as_yhi | integer | Year upper bound (scholar only) |
Want to build your own confidence-scored search agent? Here's the pattern:
```python
import asyncio
async def discover(query):
"""Phase 1: Parallel retrieval from multiple sources."""
tasks = [
search_scholar(query),
search_web(query),
search_smart(query),
search_tavily(query)
]
results = await asyncio.gather(*tasks)
return {
"scholar": results[0],
"web": results[1],
"smart": results[2],
"tavily": results[3]
}
```
```python
def score_confidence(results):
"""Calculate deterministic confidence score."""
score = 0
# Source quality (40%)
if results["scholar"]:
score += 40 * len(results["scholar"]) / 10
# Agreement analysis (35%)
claims = extract_claims(results)
agreement = analyze_agreement(claims)
score += 35 * agreement
# Recency (15%)
recency = calculate_recency(results)
score += 15 * recency
# Relevance (10%)
relevance = calculate_relevance(results, query)
score += 10 * relevance
return min(100, score)
```
```python
async def synthesize(query, results, score):
"""Generate final answer with citations."""
explanation = await explain_results(results)
return {
"answer": explanation["summary"],
"confidence": score,
"sources": explanation["citations"],
"claims": explanation["claims"]
}
```
For a complete implementation, see AIsa Verity.
| API | Cost |
|-----|------|
| Web search | ~$0.001 |
| Scholar search | ~$0.002 |
| Smart search | ~$0.002 |
| Tavily search | ~$0.002 |
| Explain | ~$0.003 |
Every response includes usage.cost and usage.credits_remaining.
export AISA_API_KEY="your-key"See API Reference for complete endpoint documentation.
Generated Feb 23, 2026
Researchers can use the skill to search for the latest academic papers and web articles on specific topics, such as transformer architectures or quantum computing, with confidence scoring to assess source reliability. The multi-source retrieval combines scholar, web, and Tavily streams for comprehensive results, aiding in literature reviews and hypothesis validation.
Business analysts can leverage the skill to gather web articles and reviews on AI startup funding or RAG frameworks, using the meta-analysis feature to generate synthesized answers with confidence scores. This helps in monitoring market trends, competitor activities, and making data-driven strategic decisions.
Media professionals can utilize the skill to aggregate the latest news on topics like quantum computing breakthroughs, with Tavily integration for content extraction and crawling. The confidence scoring engine ensures curated content is credible and up-to-date, supporting journalism and content marketing efforts.
Software developers and engineers can employ the skill for smart searches combining web and academic sources on topics like autonomous agents or machine learning optimization. The two-phase retrieval strategy provides detailed insights with source agreement analysis, aiding in technology adoption and development projects.
Compliance officers can use the skill to search for regulatory updates and academic studies on emerging technologies, with confidence scoring to evaluate source quality and recency. This assists in assessing risks, ensuring adherence to standards, and preparing compliance reports with reliable data.
Offer tiered subscription plans based on usage limits, such as number of API calls per month, with premium tiers including advanced features like Tavily integration and higher confidence scoring thresholds. Revenue is generated through monthly or annual fees from businesses and developers integrating the search functionality into their applications.
Provide enterprise licenses for large organizations requiring customized search capabilities, such as white-labeling or integration with internal data sources. Revenue comes from one-time licensing fees and ongoing support contracts, targeting industries like research institutions and corporate R&D departments.
Offer a free tier with basic search capabilities and limited API calls to attract individual users and small teams, while monetizing through premium features like advanced meta-analysis, higher confidence scoring, and priority support. Revenue is generated from upgrades and add-ons for power users and growing businesses.
💬 Integration Tip
Ensure the AISA_API_KEY environment variable is set and use the provided curl commands for quick testing before integrating into applications; consider starting with web search APIs for basic functionality.
Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.
This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
Search indexed Discord community discussions via Answer Overflow. Find solutions to coding problems, library issues, and community Q&A that only exist in Discord conversations.
Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.