id stringlengths 23 27 | source stringclasses 1
value | task stringlengths 49 1.15k | messages listlengths 3 3 | input_tokens int64 32 599 | output_tokens int64 1.74k 16.4k |
|---|---|---|---|---|---|
traj_1779884057103_17_73106 | synthetic-qwen3.6-27b | Write a pipeline prompt for a tool that must decide when to search, when to calculate, and when to respond directly based on user intent. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a pipeline prompt for a tool that must decide when to search, when to calculate, and when to respond directly based on user intent."
},
{
"role": "assistant",
"content": "Here's a ... | 50 | 2,957 |
traj_1779884058980_3_36051 | synthetic-qwen3.6-27b | Design a customer support notification agent that monitors events, applies routing rules, and delivers alerts through appropriate channels. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a customer support notification agent that monitors events, applies routing rules, and delivers alerts through appropriate channels."
},
{
"role": "assistant",
"content": "Here's ... | 43 | 2,971 |
traj_1779884088400_4_67448 | synthetic-qwen3.6-27b | Design an agent that follows the 'decompose-solve-compose' pattern: the agent first decomposes data, then solves it, and finally composes the result. Specify the tools and state management for each phase. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design an agent that follows the 'decompose-solve-compose' pattern: the agent first decomposes data, then solves it, and finally composes the result. Specify the tools and state management for each ... | 65 | 3,125 |
traj_1779884119962_9_68674 | synthetic-qwen3.6-27b | Design a tool that extracts structured medical report data from unstructured text. Specify the output schema with all fields: patient_id, diagnosis, medications, test_results, recommendations, follow_up_date. Include validation rules. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a tool that extracts structured medical report data from unstructured text. Specify the output schema with all fields: patient_id, diagnosis, medications, test_results, recommendations, follo... | 64 | 3,403 |
traj_1779884156740_13_33314 | synthetic-qwen3.6-27b | Design an agent that follows the 'parse-transform-load' pattern: the agent first parses data, then transforms it, and finally loads the result. Specify the tools and state management for each phase. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design an agent that follows the 'parse-transform-load' pattern: the agent first parses data, then transforms it, and finally loads the result. Specify the tools and state management for each phase.... | 61 | 3,480 |
traj_1779884186725_0_35961 | synthetic-qwen3.6-27b | Build a test suite for an agent that uses fallback chain: try primary, then secondary, then cached. Cover success paths, partial failures, and full failures. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a test suite for an agent that uses fallback chain: try primary, then secondary, then cached. Cover success paths, partial failures, and full failures."
},
{
"role": "assistant",
"... | 54 | 3,941 |
traj_1779884189096_8_99661 | synthetic-qwen3.6-27b | Build a timeout recovery for an LLM-based analysis tool. The call hangs for 30 seconds. How does the agent cancel, retry with fewer tokens, and proceed? | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a timeout recovery for an LLM-based analysis tool. The call hangs for 30 seconds. How does the agent cancel, retry with fewer tokens, and proceed?"
},
{
"role": "assistant",
"conte... | 57 | 3,951 |
traj_1779884197430_36_28074 | synthetic-qwen3.6-27b | Design a personal finance agent that connects to bank APIs, categorizes transactions, detects unusual spending, generates budgets, and sends weekly reports. Describe the data flow. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a personal finance agent that connects to bank APIs, categorizes transactions, detects unusual spending, generates budgets, and sends weekly reports. Describe the data flow."
},
{
"ro... | 54 | 3,174 |
traj_1779884199115_28_1009 | synthetic-qwen3.6-27b | Build a multi-turn conversation agent that maintains state across tool calls: remembering previous search results, user preferences, and pending actions. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a multi-turn conversation agent that maintains state across tool calls: remembering previous search results, user preferences, and pending actions."
},
{
"role": "assistant",
"cont... | 47 | 3,373 |
traj_1779884199910_19_19331 | synthetic-qwen3.6-27b | Build a travel workflow automation agent that sequences multi-step processes with approval gates at each stage. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a travel workflow automation agent that sequences multi-step processes with approval gates at each stage."
},
{
"role": "assistant",
"content": "Here's a thinking process:\n\n1. *... | 40 | 3,489 |
traj_1779884204082_39_19681 | synthetic-qwen3.6-27b | Build a legal customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a legal customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic."
},
{
"role": "... | 53 | 3,161 |
traj_1779884410970_46_84879 | synthetic-qwen3.6-27b | Write a prompt template for a tool that has access to a code interpreter, file system, and web browser. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a prompt template for a tool that has access to a code interpreter, file system, and web browser."
},
{
"role": "assistant",
"content": "Here's a thinking process:\n\n1. **Analyze... | 44 | 2,184 |
traj_1779884447981_43_84202 | synthetic-qwen3.6-27b | Build a HR customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a HR customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic."
},
{
"role": "ass... | 53 | 2,581 |
traj_1779884520562_36_66208 | synthetic-qwen3.6-27b | Design an agent that uses a search tool, a calculator tool, a code execution tool, and a storage tool to solve complex multi-step problems. Describe the interaction flow. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design an agent that uses a search tool, a calculator tool, a code execution tool, and a storage tool to solve complex multi-step problems. Describe the interaction flow."
},
{
"role": "assi... | 56 | 3,136 |
traj_1779884538573_39_7594 | synthetic-qwen3.6-27b | Design a customer support customer service agent that handles account inquiries, processes requests, and escalates complex issues to huma tools. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a customer support customer service agent that handles account inquiries, processes requests, and escalates complex issues to huma tools. Define the tool set and decision logic."
},
{
... | 54 | 3,337 |
traj_1779884543408_17_13714 | synthetic-qwen3.6-27b | Build an approval workflow for destructive tools like file deletion or database writes. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build an approval workflow for destructive tools like file deletion or database writes."
},
{
"role": "assistant",
"content": "Here's a thinking process:\n\n1. **Understand User Request... | 36 | 3,382 |
traj_1779884601887_4_6936 | synthetic-qwen3.6-27b | Implement sequential tool calls with state passing. Describe the code structure, error handling, and concurrency management. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Implement sequential tool calls with state passing. Describe the code structure, error handling, and concurrency management."
},
{
"role": "assistant",
"content": "Here's a thinking proc... | 42 | 3,894 |
traj_1779884606585_0_80883 | synthetic-qwen3.6-27b | Write a HR compliance checking agent that reviews documents against regulatory requirements and flags violations. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a HR compliance checking agent that reviews documents against regulatory requirements and flags violations."
},
{
"role": "assistant",
"content": "Here's a thinking process:\n\n1. ... | 38 | 3,926 |
traj_1779884609058_5_85892 | synthetic-qwen3.6-27b | Create a banking compliance checking agent that reviews documents against regulatory requirements and flags violations. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Create a banking compliance checking agent that reviews documents against regulatory requirements and flags violations."
},
{
"role": "assistant",
"content": "Here's a thinking process:\... | 38 | 3,668 |
traj_1779884611027_19_44485 | synthetic-qwen3.6-27b | Implement conditional tool selection based on results. Describe the code structure, error handling, and concurrency management. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Implement conditional tool selection based on results. Describe the code structure, error handling, and concurrency management."
},
{
"role": "assistant",
"content": "Here's a thinking p... | 42 | 3,956 |
traj_1779884619109_26_61527 | synthetic-qwen3.6-27b | Design a IT operations customer service agent that handles account inquiries, processes requests, and escalates complex issues to huma tools. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a IT operations customer service agent that handles account inquiries, processes requests, and escalates complex issues to huma tools. Define the tool set and decision logic."
},
{
"r... | 54 | 3,246 |
traj_1779884623231_28_3908 | synthetic-qwen3.6-27b | Write a IT operations recommendation agent that analyzes user preferences, cross-references available options, and suggests personalized choices. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a IT operations recommendation agent that analyzes user preferences, cross-references available options, and suggests personalized choices."
},
{
"role": "assistant",
"content": "H... | 44 | 4,029 |
traj_1779884640267_21_59516 | synthetic-qwen3.6-27b | Design a real estate customer service agent that handles account inquiries, processes requests, and escalates complex issues to huma tools. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a real estate customer service agent that handles account inquiries, processes requests, and escalates complex issues to huma tools. Define the tool set and decision logic."
},
{
"rol... | 54 | 3,460 |
traj_1779884649986_27_69237 | synthetic-qwen3.6-27b | Design a tool that follows the 'monitor-detect-alert' pattern: the agent first monitors data, then detects it, and finally alerts the result. Define the tools and state management for each phase. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a tool that follows the 'monitor-detect-alert' pattern: the agent first monitors data, then detects it, and finally alerts the result. Define the tools and state management for each phase."
... | 62 | 3,414 |
traj_1779884657229_8_7891 | synthetic-qwen3.6-27b | Build a banking workflow automation agent that sequences multi-step processes with approval gates at each stage. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a banking workflow automation agent that sequences multi-step processes with approval gates at each stage."
},
{
"role": "assistant",
"content": "Here's a thinking process:\n\n1. ... | 40 | 4,283 |
traj_1779884666446_16_57545 | synthetic-qwen3.6-27b | Design a tool that lets a tool spawn and monitor background processes with output streaming. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a tool that lets a tool spawn and monitor background processes with output streaming."
},
{
"role": "assistant",
"content": "Here's a thinking process:\n\n1. **Understand User Re... | 38 | 3,778 |
traj_1779884679744_35_85690 | synthetic-qwen3.6-27b | Build a routing system that decides whether to call a tool or respond directly based on user intent. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a routing system that decides whether to call a tool or respond directly based on user intent."
},
{
"role": "assistant",
"content": "Here's a thinking process:\n\n1. **Understand... | 41 | 3,571 |
traj_1779884683406_20_51359 | synthetic-qwen3.6-27b | Write a voting mechanism where 2 agents independently solve a problem and a separate aggregator agent reconciles their answers. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a voting mechanism where 2 agents independently solve a problem and a separate aggregator agent reconciles their answers."
},
{
"role": "assistant",
"content": "Here's a thinking p... | 44 | 3,885 |
traj_1779884689481_30_98745 | synthetic-qwen3.6-27b | Design a tool that lets a tool spawn and monitor background processes with output streaming. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a tool that lets a tool spawn and monitor background processes with output streaming."
},
{
"role": "assistant",
"content": "Here's a thinking process:\n\n1. **Understand User Re... | 38 | 3,729 |
traj_1779884694843_42_68634 | synthetic-qwen3.6-27b | Build an agent that follows the 'query-analyze-report' pattern: the agent first querys data, then analyzes it, and finally reports the result. Define the tools and state management for each phase. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build an agent that follows the 'query-analyze-report' pattern: the agent first querys data, then analyzes it, and finally reports the result. Define the tools and state management for each phase."
... | 63 | 3,610 |
traj_1779884708280_29_38460 | synthetic-qwen3.6-27b | Design a tool that extracts structured medical report data from unstructured text. Specify the output schema with all fields: patient_id, diagnosis, medications, test_results, recommendations, follow_up_date. Include validation rules. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a tool that extracts structured medical report data from unstructured text. Specify the output schema with all fields: patient_id, diagnosis, medications, test_results, recommendations, follo... | 64 | 3,876 |
traj_1779884710580_31_41704 | synthetic-qwen3.6-27b | Build a real estate customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a real estate customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic."
},
{
"ro... | 54 | 3,881 |
traj_1779884713469_44_7897 | synthetic-qwen3.6-27b | Design a tool that follows the 'monitor-detect-alert' pattern: the agent first monitors data, then detects it, and finally alerts the result. Define the tools and state management for each phase. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a tool that follows the 'monitor-detect-alert' pattern: the agent first monitors data, then detects it, and finally alerts the result. Define the tools and state management for each phase."
... | 62 | 3,748 |
traj_1779884718610_34_60023 | synthetic-qwen3.6-27b | Build a recruitment agent that parses resumes, matches against job descriptions, ranks candidates, schedules interviews, and sends rejection/acceptance emails. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a recruitment agent that parses resumes, matches against job descriptions, ranks candidates, schedules interviews, and sends rejection/acceptance emails."
},
{
"role": "assistant",
... | 49 | 3,902 |
traj_1779884720726_45_40424 | synthetic-qwen3.6-27b | Design a travel customer service agent that handles account inquiries, processes requests, and escalates complex issues to huma tools. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a travel customer service agent that handles account inquiries, processes requests, and escalates complex issues to huma tools. Define the tool set and decision logic."
},
{
"role": "... | 53 | 3,804 |
traj_1779884730595_56_21367 | synthetic-qwen3.6-27b | Build a system prompt that instructs a model to call tools transparently — showing reasoning before calling and summarizing results afterwards. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a system prompt that instructs a model to call tools transparently — showing reasoning before calling and summarizing results afterwards."
},
{
"role": "assistant",
"content": "Her... | 47 | 2,334 |
traj_1779884742591_47_63184 | synthetic-qwen3.6-27b | Write a data analysis agent that queries a SQL database, computes statistics with Python, generates a visualization, and emails the results. Specify each tool and how results flow between them. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a data analysis agent that queries a SQL database, computes statistics with Python, generates a visualization, and emails the results. Specify each tool and how results flow between them."
}... | 57 | 3,999 |
traj_1779884745341_22_36974 | synthetic-qwen3.6-27b | Implement recursive tool calls for depth-first exploration. Describe the code structure, error handling, and concurrency management. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Implement recursive tool calls for depth-first exploration. Describe the code structure, error handling, and concurrency management."
},
{
"role": "assistant",
"content": "Here's a think... | 43 | 4,401 |
traj_1779884747425_38_65520 | synthetic-qwen3.6-27b | Design a test suite for an agent that uses fan-out to multiple tools then fan-in results. Cover success paths, partial failures, and full failures. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a test suite for an agent that uses fan-out to multiple tools then fan-in results. Cover success paths, partial failures, and full failures."
},
{
"role": "assistant",
"content": ... | 52 | 4,152 |
traj_1779884759820_1_68628 | synthetic-qwen3.6-27b | Build an agent that orchestrates a REST API workflow: authenticate, fetch paginated data, transform results, and post to another service. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build an agent that orchestrates a REST API workflow: authenticate, fetch paginated data, transform results, and post to another service."
},
{
"role": "assistant",
"content": "Here's a ... | 49 | 5,026 |
traj_1779884762708_18_40149 | synthetic-qwen3.6-27b | Build a IT operations notification agent that monitors events, applies routing rules, and delivers alerts through appropriate channels. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a IT operations notification agent that monitors events, applies routing rules, and delivers alerts through appropriate channels."
},
{
"role": "assistant",
"content": "Here's a th... | 43 | 4,641 |
traj_1779884765950_11_16974 | synthetic-qwen3.6-27b | Build a competitive analysis agent that monitors competitor websites, tracks changes, summarizes diff content, and alerts on significant updates. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a competitive analysis agent that monitors competitor websites, tracks changes, summarizes diff content, and alerts on significant updates."
},
{
"role": "assistant",
"content": "H... | 45 | 4,919 |
traj_1779884771065_7_22576 | synthetic-qwen3.6-27b | Write a conflict resolution agent: two tools provide contradictory results. How does the agent resolve, cross-validate, and report the discrepancy? | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a conflict resolution agent: two tools provide contradictory results. How does the agent resolve, cross-validate, and report the discrepancy?"
},
{
"role": "assistant",
"content": ... | 48 | 5,042 |
traj_1779884778004_25_87626 | synthetic-qwen3.6-27b | Build a legal reporting agent that generates scheduled reports by querying data sources, formatting results, and distributing via email or dashboards. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a legal reporting agent that generates scheduled reports by querying data sources, formatting results, and distributing via email or dashboards."
},
{
"role": "assistant",
"content... | 47 | 4,659 |
traj_1779884790007_10_56352 | synthetic-qwen3.6-27b | Implement pipeline: each tool output feeds the next. Describe the code structure, error handling, and concurrency management. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Implement pipeline: each tool output feeds the next. Describe the code structure, error handling, and concurrency management."
},
{
"role": "assistant",
"content": "Here's a thinking pro... | 44 | 5,234 |
traj_1779884794193_6_85732 | synthetic-qwen3.6-27b | Write a deployment agent that can pull code from GitHub, build a Docker image, run tests, deploy to Kubernetes, and roll back on failure. Describe the tool chain and error handling. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a deployment agent that can pull code from GitHub, build a Docker image, run tests, deploy to Kubernetes, and roll back on failure. Describe the tool chain and error handling."
},
{
"r... | 59 | 5,294 |
traj_1779884800922_40_49331 | synthetic-qwen3.6-27b | Build an agent that maintains a todo list within its context, tracks progress on multi-step tasks, and persists intermediate state for resumption. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build an agent that maintains a todo list within its context, tracks progress on multi-step tasks, and persists intermediate state for resumption."
},
{
"role": "assistant",
"content": "... | 49 | 4,684 |
traj_1779884803365_41_65921 | synthetic-qwen3.6-27b | Build a multi-turn conversation agent that maintains state across tool calls: remembering previous search results, user preferences, and pending actions. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a multi-turn conversation agent that maintains state across tool calls: remembering previous search results, user preferences, and pending actions."
},
{
"role": "assistant",
"cont... | 47 | 4,685 |
traj_1779884804829_61_51357 | synthetic-qwen3.6-27b | Write a e-commerce compliance checking agent that reviews documents against regulatory requirements and flags violations. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a e-commerce compliance checking agent that reviews documents against regulatory requirements and flags violations."
},
{
"role": "assistant",
"content": "Here's a thinking process... | 39 | 3,002 |
traj_1779885000013_30_31092 | synthetic-qwen3.6-27b | Write a recovery flow for a file write tool that fails with 'disk full'. The agent needs to check disk space, clean up temp files, retry, or gracefully report failure. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a recovery flow for a file write tool that fails with 'disk full'. The agent needs to check disk space, clean up temp files, retry, or gracefully report failure."
},
{
"role": "assista... | 58 | 2,411 |
traj_1779885024847_27_83079 | synthetic-qwen3.6-27b | Build a education customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a education customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic."
},
{
"role... | 53 | 2,916 |
traj_1779885051235_21_57568 | synthetic-qwen3.6-27b | Build a content safety agent that verifies generated content against usage policies before allowing tool outputs to reach users. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a content safety agent that verifies generated content against usage policies before allowing tool outputs to reach users."
},
{
"role": "assistant",
"content": "Here's a thinking ... | 42 | 3,258 |
traj_1779885051342_17_81911 | synthetic-qwen3.6-27b | Create a toolic workflow that takes a batch of invoice documents, extracts structured data using a tool, validates against schema rules, and flags anomalies. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Create a toolic workflow that takes a batch of invoice documents, extracts structured data using a tool, validates against schema rules, and flags anomalies."
},
{
"role": "assistant",
"... | 51 | 3,812 |
traj_1779885065060_28_75905 | synthetic-qwen3.6-27b | Write a education compliance checking agent that reviews documents against regulatory requirements and flags violations. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a education compliance checking agent that reviews documents against regulatory requirements and flags violations."
},
{
"role": "assistant",
"content": "Here's a thinking process:... | 38 | 3,497 |
traj_1779885067485_5_16896 | synthetic-qwen3.6-27b | Write a developer tool agent that reads code, runs linters, suggests fixes, applies approved changes, runs tests, and commits if tests pass. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a developer tool agent that reads code, runs linters, suggests fixes, applies approved changes, runs tests, and commits if tests pass."
},
{
"role": "assistant",
"content": "Here's... | 51 | 3,728 |
traj_1779885116584_8_57413 | synthetic-qwen3.6-27b | Design an agent that follows the 'query-analyze-report' pattern: the agent first querys data, then analyzes it, and finally reports the result. Specify the tools and state management for each phase. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design an agent that follows the 'query-analyze-report' pattern: the agent first querys data, then analyzes it, and finally reports the result. Specify the tools and state management for each phase.... | 63 | 3,636 |
traj_1779885119972_20_22066 | synthetic-qwen3.6-27b | Design a tool that orchestrates a REST API workflow: authenticate, fetch paginated data, transform results, and post to another service. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a tool that orchestrates a REST API workflow: authenticate, fetch paginated data, transform results, and post to another service."
},
{
"role": "assistant",
"content": "Here's a t... | 49 | 3,413 |
traj_1779885132607_16_47323 | synthetic-qwen3.6-27b | Build a tool that lets the agent query its own past conversations for context retrieval. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a tool that lets the agent query its own past conversations for context retrieval."
},
{
"role": "assistant",
"content": "Here's a thinking process:\n\n1. **Understand User Reques... | 38 | 3,685 |
traj_1779885162619_50_34042 | synthetic-qwen3.6-27b | Design an error recovery strategy for a web search tool: the API returns a 429 rate limit error. How should the agent handle this, retry, back off, and inform the user? | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design an error recovery strategy for a web search tool: the API returns a 429 rate limit error. How should the agent handle this, retry, back off, and inform the user?"
},
{
"role": "assist... | 62 | 2,329 |
traj_1779885171361_22_48764 | synthetic-qwen3.6-27b | Build a HR customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a HR customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic."
},
{
"role": "ass... | 53 | 3,233 |
traj_1779885181890_56_62199 | synthetic-qwen3.6-27b | Build a IT operations customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a IT operations customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic."
},
{
"... | 54 | 3,474 |
traj_1779885187403_12_16703 | synthetic-qwen3.6-27b | Build a legal customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a legal customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic."
},
{
"role": "... | 53 | 3,369 |
traj_1779885189308_61_13577 | synthetic-qwen3.6-27b | Design a pipeline using tool calling where a tool searches a knowledge base, retrieves documents, and answers based on retrieved context. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a pipeline using tool calling where a tool searches a knowledge base, retrieves documents, and answers based on retrieved context."
},
{
"role": "assistant",
"content": "Here's a ... | 46 | 3,407 |
traj_1779885200723_29_40621 | synthetic-qwen3.6-27b | Design an agent that follows the 'plan-execute-verify' pattern: the agent first plans data, then executes it, and finally verifys the result. Specify the tools and state management for each phase. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design an agent that follows the 'plan-execute-verify' pattern: the agent first plans data, then executes it, and finally verifys the result. Specify the tools and state management for each phase."
... | 65 | 3,945 |
traj_1779885201077_35_26838 | synthetic-qwen3.6-27b | Write a reusable agent template for the 'collect-validate-store' pattern that can be configured with different backend tools via dependency injection. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a reusable agent template for the 'collect-validate-store' pattern that can be configured with different backend tools via dependency injection."
},
{
"role": "assistant",
"content... | 47 | 4,103 |
traj_1779885208687_41_18874 | synthetic-qwen3.6-27b | Build an error recovery strategy for tool calling: what happens when a tool returns an error or times out. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build an error recovery strategy for tool calling: what happens when a tool returns an error or times out."
},
{
"role": "assistant",
"content": "Here's a thinking process:\n\n1. **Unde... | 43 | 3,589 |
traj_1779885211552_1_67076 | synthetic-qwen3.6-27b | Write an agentic workflow that takes a batch of invoice documents, extracts structured data using a tool, validates against schema rules, and flags anomalies. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write an agentic workflow that takes a batch of invoice documents, extracts structured data using a tool, validates against schema rules, and flags anomalies."
},
{
"role": "assistant",
... | 51 | 3,613 |
traj_1779885236571_24_66819 | synthetic-qwen3.6-27b | Build a healthcare customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a healthcare customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic."
},
{
"rol... | 53 | 3,369 |
traj_1779885237397_14_59983 | synthetic-qwen3.6-27b | Write a data analysis agent that queries a SQL database, computes statistics with Python, generates a visualization, and emails the results. Specify each tool and how results flow between them. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a data analysis agent that queries a SQL database, computes statistics with Python, generates a visualization, and emails the results. Specify each tool and how results flow between them."
}... | 57 | 3,684 |
traj_1779885248453_25_31498 | synthetic-qwen3.6-27b | Build a HR reporting agent that generates scheduled reports by querying data sources, formatting results, and distributing via email or dashboards. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a HR reporting agent that generates scheduled reports by querying data sources, formatting results, and distributing via email or dashboards."
},
{
"role": "assistant",
"content": ... | 47 | 3,967 |
traj_1779885290015_51_80022 | synthetic-qwen3.6-27b | Design a test suite for a tool that uses parallel tool calls with aggregation. Cover success paths, partial failures, and full failures. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a test suite for a tool that uses parallel tool calls with aggregation. Cover success paths, partial failures, and full failures."
},
{
"role": "assistant",
"content": "Here's a t... | 48 | 3,483 |
traj_1779885291579_45_91452 | synthetic-qwen3.6-27b | Write a data redaction agent that scans tool outputs for PII, secrets, or sensitive info and redacts before returning to the user. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a data redaction agent that scans tool outputs for PII, secrets, or sensitive info and redacts before returning to the user."
},
{
"role": "assistant",
"content": "Here's a thinkin... | 50 | 4,702 |
traj_1779885292334_54_120 | synthetic-qwen3.6-27b | Design a legal customer service agent that handles account inquiries, processes requests, and escalates complex issues to huma tools. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a legal customer service agent that handles account inquiries, processes requests, and escalates complex issues to huma tools. Define the tool set and decision logic."
},
{
"role": "a... | 53 | 3,302 |
traj_1779885298603_6_92749 | synthetic-qwen3.6-27b | Build an agent that follows the 'monitor-detect-alert' pattern: the agent first monitors data, then detects it, and finally alerts the result. Define the tools and state management for each phase. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build an agent that follows the 'monitor-detect-alert' pattern: the agent first monitors data, then detects it, and finally alerts the result. Define the tools and state management for each phase."
... | 62 | 4,427 |
traj_1779885303812_10_98889 | synthetic-qwen3.6-27b | Write an agent that can switch between reading from a database, writing to a file, calling an API, and sending an email based on intermediate results. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write an agent that can switch between reading from a database, writing to a file, calling an API, and sending an email based on intermediate results."
},
{
"role": "assistant",
"content... | 52 | 4,477 |
traj_1779885312416_37_79761 | synthetic-qwen3.6-27b | Design a tool that maintains a todo list within its context, tracks progress on multi-step tasks, and persists intermediate state for resumption. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a tool that maintains a todo list within its context, tracks progress on multi-step tasks, and persists intermediate state for resumption."
},
{
"role": "assistant",
"content": "H... | 49 | 3,732 |
traj_1779885314124_18_41253 | synthetic-qwen3.6-27b | Design a tool that extracts structured medical report data from unstructured text. Specify the output schema with all fields: patient_id, diagnosis, medications, test_results, recommendations, follow_up_date. Include validation rules. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a tool that extracts structured medical report data from unstructured text. Specify the output schema with all fields: patient_id, diagnosis, medications, test_results, recommendations, follo... | 64 | 4,557 |
traj_1779885314788_23_81460 | synthetic-qwen3.6-27b | Write a session management pattern for an agent that handles multiple concurrent user requests, isolating state per session and cleaning up on timeout. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write a session management pattern for an agent that handles multiple concurrent user requests, isolating state per session and cleaning up on timeout."
},
{
"role": "assistant",
"conten... | 48 | 4,160 |
traj_1779885320911_33_76588 | synthetic-qwen3.6-27b | Code pipeline: each tool output feeds the next. Show the code structure, error handling, and concurrency management. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Code pipeline: each tool output feeds the next. Show the code structure, error handling, and concurrency management."
},
{
"role": "assistant",
"content": "Here's a thinking process:\n\n... | 44 | 3,847 |
traj_1779885324718_32_48522 | synthetic-qwen3.6-27b | Build a real estate customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a real estate customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Define the tool set and decision logic."
},
{
"ro... | 54 | 3,999 |
traj_1779885325751_7_13182 | synthetic-qwen3.6-27b | Build a news monitoring agent that follows specified topics, deduplicates headlines from multiple sources, and generates a daily briefing email. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a news monitoring agent that follows specified topics, deduplicates headlines from multiple sources, and generates a daily briefing email."
},
{
"role": "assistant",
"content": "He... | 46 | 4,631 |
traj_1779885330559_58_6019 | synthetic-qwen3.6-27b | Design a pipeline using tool calling where a tool searches a knowledge base, retrieves documents, and answers based on retrieved context. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a pipeline using tool calling where a tool searches a knowledge base, retrieves documents, and answers based on retrieved context."
},
{
"role": "assistant",
"content": "Here's a ... | 46 | 3,189 |
traj_1779885339702_60_36320 | synthetic-qwen3.6-27b | Write an agentic workflow that takes a batch of invoice documents, extracts structured data using a tool, validates against schema rules, and flags anomalies. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write an agentic workflow that takes a batch of invoice documents, extracts structured data using a tool, validates against schema rules, and flags anomalies."
},
{
"role": "assistant",
... | 51 | 3,226 |
traj_1779885350673_40_252 | synthetic-qwen3.6-27b | Implement fan-out to multiple tools then fan-in results. Describe the code structure, error handling, and concurrency management. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Implement fan-out to multiple tools then fan-in results. Describe the code structure, error handling, and concurrency management."
},
{
"role": "assistant",
"content": "Here's a thinking... | 45 | 4,848 |
traj_1779885357869_52_84503 | synthetic-qwen3.6-27b | Build a research agent that takes a question, breaks it into sub-questions, searches the web for each, cross-references findings, and produces a synthesized answer with citations. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a research agent that takes a question, breaks it into sub-questions, searches the web for each, cross-references findings, and produces a synthesized answer with citations."
},
{
"rol... | 57 | 3,964 |
traj_1779885396039_63_23691 | synthetic-qwen3.6-27b | Design a tool that follows the 'query-analyze-report' pattern: the agent first querys data, then analyzes it, and finally reports the result. Define the tools and state management for each phase. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a tool that follows the 'query-analyze-report' pattern: the agent first querys data, then analyzes it, and finally reports the result. Define the tools and state management for each phase."
... | 63 | 3,625 |
traj_1779885545730_16_15349 | synthetic-qwen3.6-27b | Create a toolic workflow that takes a batch of invoice documents, extracts structured data using a tool, validates against schema rules, and flags anomalies. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Create a toolic workflow that takes a batch of invoice documents, extracts structured data using a tool, validates against schema rules, and flags anomalies."
},
{
"role": "assistant",
"... | 51 | 3,167 |
traj_1779885583000_28_35066 | synthetic-qwen3.6-27b | Write an agentic workflow that takes a batch of resume documents, extracts structured data using a tool, validates against schema rules, and flags anomalies. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Write an agentic workflow that takes a batch of resume documents, extracts structured data using a tool, validates against schema rules, and flags anomalies."
},
{
"role": "assistant",
"... | 51 | 3,577 |
traj_1779885597970_21_47250 | synthetic-qwen3.6-27b | Design a real estate customer service agent that handles account inquiries, processes requests, and escalates complex issues to huma tools. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a real estate customer service agent that handles account inquiries, processes requests, and escalates complex issues to huma tools. Define the tool set and decision logic."
},
{
"rol... | 54 | 3,705 |
traj_1779885602815_50_5489 | synthetic-qwen3.6-27b | Build an agent that follows the 'authenticate-authorize-audit' pattern: the agent first authenticates data, then authorizes it, and finally audits the result. Define the tools and state management for each phase. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build an agent that follows the 'authenticate-authorize-audit' pattern: the agent first authenticates data, then authorizes it, and finally audits the result. Define the tools and state management f... | 65 | 3,500 |
traj_1779885614875_61_32300 | synthetic-qwen3.6-27b | Design a travel customer service agent that handles account inquiries, processes requests, and escalates complex issues to huma tools. Define the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a travel customer service agent that handles account inquiries, processes requests, and escalates complex issues to huma tools. Define the tool set and decision logic."
},
{
"role": "... | 53 | 3,449 |
traj_1779885624476_20_11552 | synthetic-qwen3.6-27b | Create a session management pattern for a tool that handles multiple concurrent user requests, isolating state per session and cleaning up on timeout. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Create a session management pattern for a tool that handles multiple concurrent user requests, isolating state per session and cleaning up on timeout."
},
{
"role": "assistant",
"content... | 48 | 3,724 |
traj_1779885630513_43_77843 | synthetic-qwen3.6-27b | Build a routing system that decides whether to call a tool or respond directly based on user intent. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a routing system that decides whether to call a tool or respond directly based on user intent."
},
{
"role": "assistant",
"content": "Here's a thinking process:\n\n1. **Understand... | 41 | 3,922 |
traj_1779885641621_51_26060 | synthetic-qwen3.6-27b | Build a healthcare notification agent that monitors events, applies routing rules, and delivers alerts through appropriate channels. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a healthcare notification agent that monitors events, applies routing rules, and delivers alerts through appropriate channels."
},
{
"role": "assistant",
"content": "Here's a think... | 42 | 2,747 |
traj_1779885646593_1_82085 | synthetic-qwen3.6-27b | Design a banking customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Specify the tool set and decision logic. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a banking customer service agent that handles account inquiries, processes requests, and escalates complex issues to human agents. Specify the tool set and decision logic."
},
{
"role... | 53 | 3,343 |
traj_1779885653354_41_31452 | synthetic-qwen3.6-27b | Design a tool that uses a search tool, a calculator tool, a code execution tool, and a storage tool to solve complex multi-step problems. Show the interaction flow. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a tool that uses a search tool, a calculator tool, a code execution tool, and a storage tool to solve complex multi-step problems. Show the interaction flow."
},
{
"role": "assistant"... | 56 | 3,449 |
traj_1779885662608_8_37968 | synthetic-qwen3.6-27b | Build a legal notification agent that monitors events, applies routing rules, and delivers alerts through appropriate channels. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a legal notification agent that monitors events, applies routing rules, and delivers alerts through appropriate channels."
},
{
"role": "assistant",
"content": "Here's a thinking p... | 42 | 4,070 |
traj_1779885666323_29_96460 | synthetic-qwen3.6-27b | Design a test suite for a tool that uses round-robin across equivalent tools for load distribution. Cover success paths, partial failures, and full failures. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a test suite for a tool that uses round-robin across equivalent tools for load distribution. Cover success paths, partial failures, and full failures."
},
{
"role": "assistant",
"... | 52 | 3,652 |
traj_1779885673457_24_68375 | synthetic-qwen3.6-27b | Build a security model for agent tool access: which tools require approval, which run automatically. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Build a security model for agent tool access: which tools require approval, which run automatically."
},
{
"role": "assistant",
"content": "Here's a thinking process:\n\n1. **Understand... | 40 | 3,488 |
traj_1779885674920_14_72999 | synthetic-qwen3.6-27b | Design a test suite for a tool that uses fallback chain: try primary, then secondary, then cached. Cover success paths, partial failures, and full failures. | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "Design a test suite for a tool that uses fallback chain: try primary, then secondary, then cached. Cover success paths, partial failures, and full failures."
},
{
"role": "assistant",
"c... | 54 | 3,469 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.