smartgate-network research-agent
Purpose: When no definitive URL exists, collect material from multiple web sources, deduplicate and compress it, and return structured research ready for Host LLM analysis.
When to use:
- Competitor analysis: compare features, pricing, and positioning across products
- Industry research: aggregate recent news, reports, and trends in a domain
- Academic/technical surveys: gather paper abstracts, technical blogs, and solution comparisons on a topic
- News digests: aggregate coverage around an event or keyword from multiple outlets
When NOT to use:
- User already provided a definitive http(s) URL — use deep-reading for a single-chain read without extra search
- Only need to store or retrieve team conclusions — use remember-and-recall
- Querying token quota or usage — use usage-report
Returns: JSON string (parse via loader). Top level includes success and results (per-step array). Final smart_context_gate step data includes compressed, ratio, original_tokens, compressed_tokens. Earlier steps include search results[].url / results[].snippet, fetched page markdown, and dedup deduped_text / removed_count.
Composes with: Host LLM for synthesis and reports; conclusions via remember-and-recall (action=add); pre-flight usage-report (action=check) before large jobs.