Novus's agent drew on analytics or code—never both—invisible to the team. Traces caught it; 60% of problems now caught before customers.
A product analytics platform that built Novus, a multi-step AI agent that monitors live user sessions, diagnoses usability issues via session replays, and generates code fixes by correlating behavioral data with specific source files.
Novus runs a complex pipeline across session replay analysis, behavioral data aggregation, code file correlation, and PR generation. When any step...
“Novus is a product agent that detects usability issues in live applications, fixes the underlying code, and improves the user experience. It achieves a 90%+ success rate on PM-reviewed evals and we shipped it to production in days, not months. LangSmith is a core reason we could do both.”
Product experience platform for user analytics and in-app adoption.
Framework and developer platform for building LLM-powered applications.
Pendo's Agent debugging is part of this use case:
Related implementations across industries and use cases
Untangling 30-call AI interactions consumed developers. Now, support teams use system traces to resolve context issues without engineers.
Blind spots in agent chains delayed debugging. Engineers now use one-click tracing to instantly pinpoint and fix errors in production.
Debugging scattered across individual notebooks meant week-long fixes. One shared platform now catches errors before customers do.
Blind spots in agent chains delayed debugging. Engineers now use one-click tracing to instantly pinpoint and fix errors in production.
Tracking spend for 300M AI agent runs was a black box. Real-time tracing now lets finance pinpoint costs and update pricing within hours.
Surging calls caused long holds and overtime. A 24/7 AI voice agent handles routine payroll, freeing 700 HR partners for advisory work.
Keyword bots bottlenecked 100 agents supporting millions. Now, AI resolves FAQs, freeing staff to mine chat logs for product feedback.
Querying Wikidata required specialized syntax, locking out most AI systems. Vector search now lets LLMs navigate 100M+ entities in plain language.
On-premise systems, dispersed and brittle, bottlenecked every release. AI agents now run routine dev steps — hours cut to minutes.
Novus's agent drew on analytics or code—never both—invisible to the team. Traces caught it; 60% of problems now caught before customers.
A product analytics platform that built Novus, a multi-step AI agent that monitors live user sessions, diagnoses usability issues via session replays, and generates code fixes by correlating behavioral data with specific source files.
Novus runs a complex pipeline across session replay analysis, behavioral data aggregation, code file correlation, and PR generation. When any step...
“Novus is a product agent that detects usability issues in live applications, fixes the underlying code, and improves the user experience. It achieves a 90%+ success rate on PM-reviewed evals and we shipped it to production in days, not months. LangSmith is a core reason we could do both.”
Product experience platform for user analytics and in-app adoption.
Framework and developer platform for building LLM-powered applications.
Pendo's Agent debugging is part of this use case:
Related implementations across industries and use cases
Untangling 30-call AI interactions consumed developers. Now, support teams use system traces to resolve context issues without engineers.
Blind spots in agent chains delayed debugging. Engineers now use one-click tracing to instantly pinpoint and fix errors in production.
Debugging scattered across individual notebooks meant week-long fixes. One shared platform now catches errors before customers do.
Blind spots in agent chains delayed debugging. Engineers now use one-click tracing to instantly pinpoint and fix errors in production.
Tracking spend for 300M AI agent runs was a black box. Real-time tracing now lets finance pinpoint costs and update pricing within hours.
Surging calls caused long holds and overtime. A 24/7 AI voice agent handles routine payroll, freeing 700 HR partners for advisory work.
Keyword bots bottlenecked 100 agents supporting millions. Now, AI resolves FAQs, freeing staff to mine chat logs for product feedback.
Querying Wikidata required specialized syntax, locking out most AI systems. Vector search now lets LLMs navigate 100M+ entities in plain language.
On-premise systems, dispersed and brittle, bottlenecked every release. AI agents now run routine dev steps — hours cut to minutes.