diff --git a/ra_aid/__main__.py b/ra_aid/__main__.py
index 9d02bf8..9784d45 100644
--- a/ra_aid/__main__.py
+++ b/ra_aid/__main__.py
@@ -24,7 +24,6 @@ from ra_aid.prompts import (
     RESEARCH_PROMPT,
     PLANNING_PROMPT,
     IMPLEMENTATION_PROMPT,
-    SUMMARY_PROMPT
 )
 from ra_aid.exceptions import TaskCompletedException
 import time
@@ -172,42 +171,6 @@ def run_implementation_stage(base_task, tasks, plan, related_files):
         # Run agent for this task
         run_agent_with_retry(task_agent, task_prompt, {"configurable": {"thread_id": "abc123"}, "recursion_limit": 100})
 
-def summarize_research_findings(base_task: str, config: dict) -> None:
-    """Summarize research findings for informational queries.
-
-    Generates and prints a concise summary of research findings including key facts
-    and research notes collected during the research stage.
-
-    Args:
-        base_task: The original user query
-        config: Configuration dictionary for the agent
-    """
-    print_stage_header("Research Summary")
-    
-    # Create dedicated memory for research summarization
-    summary_memory = MemorySaver()
-    
-    # Create fresh agent for summarization with its own memory
-    summary_agent = create_react_agent(model, implementation_tools, checkpointer=summary_memory)
-    
-    summary_prompt = SUMMARY_PROMPT.format(
-        base_task=base_task,
-        research_notes=get_memory_value('research_notes'),
-        key_facts=get_memory_value('key_facts'),
-        key_snippets=get_memory_value('key_snippets')
-    )
-        
-    while True:
-        try:
-            for chunk in summary_agent.stream(
-                {"messages": [HumanMessage(content=summary_prompt)]}, 
-                config
-            ):
-                print_agent_output(chunk)
-            break
-        except ChatAnthropic.InternalServerError as e:
-            print(f"Encountered Anthropic Internal Server Error: {e}. Retrying...")
-            continue
 
 def run_research_subtasks(base_task: str, config: dict):
     """Run research subtasks with separate agents."""
@@ -301,11 +264,8 @@ Be very thorough in your research and emit lots of snippets, key facts. If you t
             # Run any research subtasks
             run_research_subtasks(base_task, config)
             
-            # For informational queries, summarize findings
-            if is_informational_query():
-                summarize_research_findings(base_task, config)
-            else:
-                # Only proceed with planning and implementation if not an informational query
+            # Proceed with planning and implementation if not an informational query
+            if not is_informational_query():
                 print_stage_header("Planning Stage")
                 planning_prompt = PLANNING_PROMPT.format(
                     research_notes=get_memory_value('research_notes'),
diff --git a/ra_aid/console/formatting.py b/ra_aid/console/formatting.py
index 9482073..f0a66da 100644
--- a/ra_aid/console/formatting.py
+++ b/ra_aid/console/formatting.py
@@ -19,7 +19,6 @@ def print_stage_header(stage: str) -> None:
         'task completed': '✅',
         'debug stage': '🐛',
         'testing stage': '🧪',
-        'research summary': '📋',
         'research subtasks': '📚',
         'skipping implementation stage': '⏭️'
     }
diff --git a/ra_aid/prompts.py b/ra_aid/prompts.py
index 1030e30..6258b7d 100644
--- a/ra_aid/prompts.py
+++ b/ra_aid/prompts.py
@@ -72,7 +72,7 @@ Single-Shot Task Detection
         - Situations where immediate response meets all user requirements
 
     One-shot completion will be blocked if:
-        - Research subtasks have been requested (must wait for research summary)
+        - Research subtasks have been requested
         - Complex implementation has been explicitly requested
 
     If you determine a task can be completed in a single shot:
@@ -163,41 +163,6 @@ Guidelines:
     Do not implement anything yet.
 """
 
-# Research summary prompt - guides generation of research summaries
-# Remains essentially the same, but with complexity scaling if needed.
-SUMMARY_PROMPT = """
-Using only the information provided in the Research Notes and Key Facts below, write a concise and direct answer to the user's query.
-
-User's Query:
-{base_task}
-
-Research Notes:
-{research_notes}
-
-Key Facts:
-{key_facts}
-
-Key Snippets:
-{key_snippets}
-
-Fact Management:
-    Each fact is identified with [Fact ID: X].
-    Facts may be deleted if they become outdated, irrelevant, or duplicates.
-    Use delete_key_facts([id1, id2, ...]) with a list of numeric Fact IDs to remove unnecessary facts.
-
-Snippet Management:
-    Each snippet is identified with [Snippet ID: X].
-    Snippets include file path, line number, and source code.
-    Snippets may have optional descriptions explaining their significance.
-    Delete snippets with delete_key_snippets([id1, id2, ...]) to remove outdated or irrelevant ones.
-    Use emit_key_snippets to store important code sections needed for reference in batches.
-
-Instructions:
-- **Stay Within Provided Information**: Do not include any information not present in the Research Notes or Key Facts.
-- **Handle Contradictions Appropriately**: If contradictions exist, consider additional research or note the contradictions.
-- **Maintain Focus and Brevity**: Keep the response concise, focusing on the user's query.
-- **Include Technical Details If Relevant**: For technical queries, reference discovered files and snippets.
-"""
 
 # Implementation stage prompt - guides specific task implementation
 # Added instruction to adjust complexity of implementation to match request.