--- title: Semantic Flamegraphs for AI Agent Traces | daily.dev description: agentpprof is a tool that applies flamegraph-style visualization to AI agent traces, grouping prompts and tool calls by semantic intent to reveal token, time,... canonical: https://daily.dev/posts/semantic-flamegraphs-for-ai-agent-traces-grrcborhd twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Semantic Flamegraphs for AI Agent Traces | daily.dev og:description: agentpprof is a tool that applies flamegraph-style visualization to AI agent traces, grouping prompts and tool calls by semantic intent to reveal token, time,... og:url: https://daily.dev/posts/semantic-flamegraphs-for-ai-agent-traces-grrcborhd og:image: https://api.daily.dev/og/posts/grRCbORHD.png og:image:alt: Semantic Flamegraphs for AI Agent Traces og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Semantic Flamegraphs for AI Agent Traces **[eunomia eBPF Blog](https://daily.dev/sources/eunomia)** · 10 min read · 0 upvotes · 0 comments ## Summary agentpprof is a tool that applies flamegraph-style visualization to AI agent traces, grouping prompts and tool calls by semantic intent to reveal token, time, file, and network cost hotspots across sessions. Unlike single-trace debuggers, it aggregates cross-session data by mapping natural language prompts to stable labels (debug, review, docs, etc.) using regex rules, LLM inference, or TF-IDF clustering. Width in the flamegraph encodes token consumption, elapsed time, or operation count, enabling teams to identify which prompt categories dominate agent budgets. The tool is part of AgentSight, an eBPF-based observability framework, and currently supports Codex and Claude Code traces. Key open problems include tagging stability, cross-project rule transfer, and optimal label granularity. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do semantic flamegraphs differ from traditional CPU flamegraphs when applied to AI agent traces? Semantic flamegraphs replace deterministic function names with stable semantic tags (e.g., debug, review, docs) mapped from free-form prompts. Width encodes token consumption, elapsed time, or operation count instead of CPU time. The stack represents a causal chain — prompt → LLM decision → tool invocation → file or network effect — rather than a call hierarchy, enabling cross-session budget attribution by intent category. _Teams profiling AI agent costs track these patterns on daily.dev as the tooling matures._ ### What tagging approaches does agentpprof support for classifying natural language prompts? agentpprof offers three backends: regex rules (production default, deterministic, version-controllable, requires 5–10 iterative rounds to reach 95% coverage), an LLM tagger via llama.cpp (handles multilingual and semantically similar prompts but produces unstable results across runs), and TF-IDF + K-Means clustering (unsupervised, auto-selects 5–25 clusters, no predefined categories but produces keyword-derived rather than semantic tag names). _Developers choosing between rule-based and model-based classification for agent observability find the trade-off discussions on daily.dev._ ### What are the current limitations of agentpprof for AI agent observability? Agent coverage is limited to Codex and Claude Code local traces; other agents need parser extensions via the agent-session crate. Tagging remains unsolved — project-specific rules are required and one-word tags may conflate distinct activities. Cost attribution relies on agent-reported usage, which may not match actual billing due to cached tokens and batch discounts. No user studies yet confirm that the flamegraph view improves developer decisions. _Keeping up with agentpprof's evolving limitations and new agent support is easier through daily.dev._ ## Similar posts on daily.dev - [You can’t debug what you can’t see — Observability for AI Agents](https://daily.dev/posts/you-can-t-debug-what-you-can-t-see-observability-for-ai-agents-8yaiqpabv) · CNCF · 1 upvotes · 0 comments - [Introducing “Explain Flame Graph”: Stop Fighting Fires and Start Explaining Them](https://daily.dev/posts/introducing-explain-flame-graph-stop-fighting-fires-and-start-explaining-them-le7zn4h1c) · Coralogix · 0 upvotes · 0 comments - [Session Traces and Cost Controls Help Diagnose AI Agent Failures](https://daily.dev/posts/session-traces-and-cost-controls-help-diagnose-ai-agent-failures-cphogfesa) · InfoQ · 0 upvotes · 0 comments - [AI Agent Observability: Logging, Tracing, and Debugging Explained](https://daily.dev/posts/ai-agent-observability-logging-tracing-and-debugging-explained-95izimukh) · Machine Learning Mastery · 1 upvotes · 0 comments --- Tags: [#linux](https://daily.dev/tags/linux), [#ai-agents](https://daily.dev/tags/ai-agents), [#observability](https://daily.dev/tags/observability) [View this post on daily.dev](https://daily.dev/posts/semantic-flamegraphs-for-ai-agent-traces-grrcborhd) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Semantic Flamegraphs for AI Agent Traces","url":"https://daily.dev/posts/semantic-flamegraphs-for-ai-agent-traces-grrcborhd","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/semantic-flamegraphs-for-ai-agent-traces-grrcborhd"},"datePublished":"2026-08-11T08:54:37.117Z","dateModified":"2026-08-11T09:30:28.101Z","description":"agentpprof is a tool that applies flamegraph-style visualization to AI agent traces, grouping prompts and tool calls by semantic intent to reveal token, time,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/b59e04eefe0ea85df0b7e50151b0b12e?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/b59e04eefe0ea85df0b7e50151b0b12e?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"eunomia eBPF Blog","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"eunomia eBPF Blog","logo":"https://media.daily.dev/image/upload/s--z-nTl7TK--/f_auto,q_auto/v1786438304/logos/eunomia?_a=BAMAMicg0","url":"https://daily.dev/sources/eunomia"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/semantic-flamegraphs-for-ai-agent-traces-grrcborhd","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"linux,ai-agents,observability","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"eunomia eBPF Blog","item":"https://daily.dev/sources/eunomia"},{"@type":"ListItem","position":3,"name":"Semantic Flamegraphs for AI Agent Traces"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/semantic-flamegraphs-for-ai-agent-traces-grrcborhd#faq","mainEntity":[{"@type":"Question","name":"How do semantic flamegraphs differ from traditional CPU flamegraphs when applied to AI agent traces?","acceptedAnswer":{"@type":"Answer","text":"Semantic flamegraphs replace deterministic function names with stable semantic tags (e.g., debug, review, docs) mapped from free-form prompts. Width encodes token consumption, elapsed time, or operation count instead of CPU time. The stack represents a causal chain — prompt → LLM decision → tool invocation → file or network effect — rather than a call hierarchy, enabling cross-session budget attribution by intent category. Teams profiling AI agent costs track these patterns on daily.dev as the tooling matures."}},{"@type":"Question","name":"What tagging approaches does agentpprof support for classifying natural language prompts?","acceptedAnswer":{"@type":"Answer","text":"agentpprof offers three backends: regex rules (production default, deterministic, version-controllable, requires 5–10 iterative rounds to reach 95% coverage), an LLM tagger via llama.cpp (handles multilingual and semantically similar prompts but produces unstable results across runs), and TF-IDF + K-Means clustering (unsupervised, auto-selects 5–25 clusters, no predefined categories but produces keyword-derived rather than semantic tag names). Developers choosing between rule-based and model-based classification for agent observability find the trade-off discussions on daily.dev."}},{"@type":"Question","name":"What are the current limitations of agentpprof for AI agent observability?","acceptedAnswer":{"@type":"Answer","text":"Agent coverage is limited to Codex and Claude Code local traces; other agents need parser extensions via the agent-session crate. Tagging remains unsolved — project-specific rules are required and one-word tags may conflate distinct activities. Cost attribution relies on agent-reported usage, which may not match actual billing due to cached tokens and batch discounts. No user studies yet confirm that the flamegraph view improves developer decisions. Keeping up with agentpprof's evolving limitations and new agent support is easier through daily.dev."}}]} ```