Skip to content

Agent never calls its tools — system prompt explicitly forbids tool use - #6

Draft
langsmith-engine[bot] wants to merge 1 commit into
devfrom
issues-agent/f085dba8-8e03-464a-bd0c-d5d31f219fed
Draft

Agent never calls its tools — system prompt explicitly forbids tool use#6
langsmith-engine[bot] wants to merge 1 commit into
devfrom
issues-agent/f085dba8-8e03-464a-bd0c-d5d31f219fed

Conversation

@langsmith-engine

Copy link
Copy Markdown

The seed AGENTS.md in src/chat_langchain_lite/context_hub.py contains the instruction "Do not use any tools — answer entirely from your own expertise," so the agent answers in-domain LangChain/LangGraph/LangSmith questions from memory instead of calling lookup_concept, get_setup_guide, or get_security_advice. The auto-evaluator tool_usage averages 0.19 across the 48h window and 12 of 18 traces have zero tool calls, defeating the agent's core value proposition of grounded answers from canonical sources and compounding factual drift.

…ool-first guidance

Removes the 'Do not use any tools' instruction that was suppressing
lookup_concept / get_setup_guide / get_security_advice calls and
defeating the agent's grounded-answer value prop.
@hosted-langserve

hosted-langserve Bot commented Jul 13, 2026

Copy link
Copy Markdown

LangSmith preview deployment is ready.

This preview is ready for the current PR commit.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

0 participants