Deep Research Patterns

​

Building Blocks

​

Common Patterns

​

Literature Review

1. Seed search using feature_search to retrieve recent papers across text and figures.
2. Narrow by publication date and venue with attribute_filter.
3. Classify by research area with taxonomy_enrich.
4. Synthesize findings with citations using summarize.
5. Store summaries alongside feature_id references for auditability.

​

Competitive Intelligence

1. Use external_web_search + web_scrape stages to pull public announcements.
2. Join with internal product docs via document_enrich to compare specs.
3. Apply an attribute_filter to spotlight price or feature gaps.
4. Generate a briefing memo with the summarize stage.

​

Incident Investigation

1. Collect relevant runbooks/logs via feature_search over internal collections.
2. Use attribute_filter to isolate the incident window.
3. Enrich with taxonomy-based tags (taxonomy_enrich) for impacted systems.
4. Summarize timeline and root cause via summarize, keeping citations.

​

Orchestrating Multi-Retriever Flows

{
  "stage_name": "retriever",
  "stage_type": "enrich",
  "config": {
    "stage_id": "document_enrich",
    "parameters": {
      "retriever_id": "ret_internal_logs",
      "input_mappings": {
        "query_text": "{{INPUT.primary_question}}",
        "time_range": "{{STAGE.filter.time_range}}"
      },
      "merge_strategy": "append"
    }
  }
}

​

Capturing Feedback

• Record user signals with the Interactions API (click, long_view, positive_feedback, etc.).
• Feed interactions back into auto-tuning or attribute_filter stages (“hide documents seen in this session”).
• Use Observability to optimize parameter choices (e.g., increase a feature_search stage’s final_top_k if users often tap beyond the top 10).

​

Operational Tips

1. Persist execution IDs – each execute response includes an execution id; link it to your research session for audit trails.
2. Monitor stage telemetry – stage_statistics identifies bottlenecks (e.g., LLM stages dominating latency).
3. Budget controls – set budget_limits on retrievers to cap time or spend for exploratory workflows.
4. Cache intermediate results – cache expensive discovery steps, especially when analysts reiterate queries.
5. Use tasks – schedule enrichment batches (clusters, taxonomies) ahead of time so research pipelines stay low-latency.

​

Suggested Architecture

Orchestration App
 ├─ Calls macro retriever (with document_enrich compose stages)
 ├─ Logs execution IDs + user prompts
 ├─ Stores generated summaries & citations
 └─ Sends interactions back to Mixpeek

​

Next Steps

• Review Retrievers for stage configuration details.
• Learn how Filters and Taxonomies contribute structure to exploratory pipelines.
• Use Operations → Observability to monitor research workloads in production.