How Langchain auto-responds to ~2.5k technical support questions per month.
~4 support engineers saved by having kapa.ai implemented (assuming avg. 15mins per question, 2,500 questions, 160 working hrs per month)
300 days of end-user waiting time saved per month from instant answers (assuming avg. human response delay of 3hrs)
97% accuracy of questions answered by kapa.ai based on user-rated feedback
Rapid developer community growth puts a burden on support
Langchain, an open-source project that helps developers build Large language models (LLMs), experienced explosive growth in its community community, attracting almost 20,000 Github stars within a few months.
However, the surge in users also led to an overwhelming number of support questions, which puts a larger support burden on the core engineering team.
An LLM powered chatbot trained on Langchain knowledge sources
The kapa.ai worked with the Langchain team to identify relevant knowledge sources to feed into a chatbot including +500 docs files covering Conceptual Guides, Python docs, and JS docs, and +400 open GitHub issues.
The chatbot was then deployed in the Langchain Discord server in the #ask-kapa-langchain channel. Here it, over the course of four weeks, grew over 600% in Langchain's Discord and went from answering 175 questions to 1166 questions as more and more community users became aware of the kapa.ai chatbot.
Try kapa.ai in the #ask-kapa-langchain discord: discord.gg/6adMQxSpJS
Kapa.ai handles 2.5k questions per month
kapa.ai's chatbot is a game-changer for Langchain founder Harrison Chase and team. The chatbot has currently answered over 2,500 questions with an estimated accuracy of 97%, significantly reducing the support hours needed to handle Langchain's community. In fact, kapa.ai's solution has allowed Langchain to reduce support hours by +500hrs, freeing up the team's time to focus on more strategic tasks, such as developing new features and improving the platform's performance
Langchain's community was thrilled with kapa.ai's solution. The chatbot provided quick and accurate answers to their most pressing questions, allowing them to use the tooling to its full potential. The reduction in support hours also means that Langchain's community is receiving faster responses to their tickets, improving their overall user experience.
Software Framework for Large Language Model Application Development