Agent Tools

This tool searches your saved documents using a combination of keywords and meaning. It covers each document's title, your own description and the AI-written description as well as the full body, so a document is findable by what it is about even when the title doesn't say.

This tool uses Perplexity AI Sonar to perform comprehensive web searches with synthesized, researched answers. Unlike simple search engines, Perplexity provides cited sources and contextual understanding. Best for research questions, current events, fact-checking, and queries requiring authoritative sources. Responses include citations and contextual analysis.

This tool searches the Internet Archive OpenLibrary database for books, authors, and works. Returns comprehensive book metadata including title, author, publication year, ISBN, edition count, and availability information. Best for finding books by title, author, or subject. OpenLibrary contains millions of books from libraries around the world.

This tool searches OpenAlex, a fully open catalog of 240M+ scholarly works, authors, institutions, and topics. Returns comprehensive academic metadata including citations, open access status, author affiliations, publication venues, and subject classifications. Best for finding research papers, tracking citations, discovering authors and institutions, and analyzing academic trends. Supports advanced filtering by publication year, citation count, open access status, and more.

This tool saves a new document to your library, including a generated title and markdown content, for easy retrieval later.

This tool fetches a single document from your library using its ID, returning the title, description, content, and metadata for direct access to specific documents.

This tool fetches a file the user has attached to the conversation by its id, returning the parsed markdown content when available (or a download link otherwise), so the agent can read uploaded PDFs and other files on demand. Injected automatically when a conversation has attached files.

This tool finds files in your library by name, your own description, or the text parsed out of them — so a PDF is findable by a phrase on page four even when its filename says nothing. Results are metadata (name, type, folder, parse status); the agent reads a file with Get File. You can narrow to images, PDFs, or everything else, or to a single folder.

This tool lets the AI author a new skill — a reusable title + one-line description + Markdown body — and save it to the user's private Agent Skills Library for retrieval in future conversations. Use it when a repeatable task is worth remembering. The skill is always created private to the user (sharing with others or the whole platform stays a human-only action from the /library/skills page). Content is screened for safety before saving (Agent Skills Library, issue #2523).

This tool edits an existing document in your library. Supports full content replacement, targeted section replacement (by heading), appending content, and find/replace operations. Changes are saved immediately and the document is updated in real-time.

This tool reads a rectangular range of cells from a spreadsheet document using A1 notation (e.g. "A1:D50") or zero-based coordinates. Use it for surgical reads of large sheets instead of fetching the entire document.

This tool updates individual cells in a spreadsheet document. Provide a list of edits with zero-based row/column and the new value (or null to clear). Rows and columns grow to fit out-of-bounds edits. Use this instead of edit_document for spreadsheets.

This tool allows the AI to create new folders or update existing folder properties including name, description, and instructions. Folder instructions guide AI behavior for all conversations within that folder. Instructions are screened for safety.

This tool finds your folders by name, description, notes or folder instructions, and reports how many conversations, documents and files each one holds. It is what lets the AI turn a folder you name in words — "my Term 2 folder" — into the folder it actually works on, so Manage Folder can move things into it.

This tool retrieves conversations by ID and provides flexible access to conversation data. You can get the full conversation history, generate a summary, or ask specific questions about the conversation content.

This tool searches your conversation history using full-text search. You can search conversation details — title, auto-generated title, description, subject, tags, notes and instructions — or message content, or both. Returns matching conversations with metadata and message snippets. Use get_conversation with a conversation nanoid to retrieve more information.

This tool allows your TeamTeacher agent to make a request to another TeamTeacher agent.

This tool delegates research and search tasks to a specialized subagent with access to multiple search tools (OpenAlex, OpenLibrary, Web Search, Perplexity). Useful for complex research queries that benefit from using multiple search sources or when you want a specialized research assistant to handle the search comprehensively. The subagent can orchestrate multiple tool calls and synthesize findings across academic, web, and book searches.

This tool delegates curriculum and educational standards queries to a specialized subagent with access to multiple educational knowledge bases (IB Diploma Programme (DP), IB Middle Years Programme (MYP), Common Core State Standards (CCSS), Universal Design for Learning (UDL), NGSS, WIDA, and state standards). Useful for cross-curriculum comparisons, comprehensive curriculum research, or when you need deep expertise across multiple educational frameworks. The subagent searches the knowledge bases systematically and returns a synthesized answer plus cited sources — with verbatim quotes for open knowledge bases — so the calling assistant can cross-check and refer back to the underlying material. Set "priority" to trade speed for context window: "speed" (default) runs a fast model; "depth" uses a larger context window and stronger synthesis for big multi-framework comparisons (escalates the model for subscribers).

This tool computes math with real math engines instead of relying on AI prediction — the same "never trust mental arithmetic" approach used by dedicated math tutors. It evaluates arithmetic, fractions, unit conversions, matrices, and statistics; simplifies and expands algebraic expressions; and solves equations symbolically. The AI uses it to verify answer keys, worked solutions, and any numeric claims before presenting them, and results come back as beautifully rendered notation.

This tool searches the web using Tavily, an AI-optimized search engine. It supports multiple search topics (general, news, finance), adjustable search depth, time-based filtering, and can extract full page content. You can filter by specific domains and request AI-generated answers synthesized from results.

Tool to take and edit notes throughout the conversation. This helps the TeamTeacher stay on task and keep track of work done and other notes about the conversation. It acts as a shared scratchpad for you and the TT.

A curated collection covering all 8 MYP subject groups across years 1–5, derived from official IB documents. Every subject includes guide content and the full assessment criteria with achievement level descriptors (bands 0–8 for years 1, 3, and 5). When you ask the AI to help design a summative task or give feedback on student work, it's drawing on the same criteria you'd look up in the subject guide yourself. Beyond the subject guides, the knowledge base includes teacher support material with sample tasks and assessed student work for Language Acquisition and Arts, programme-level guidance on Approaches to Learning and interdisciplinary planning, and the complete Community Project and Personal Project criteria and supervision guidance.

All 6 DP subject groups — with guide content, assessment criteria, and the three core components: Theory of Knowledge, Extended Essay, and CAS. Whether you're planning a History unit, checking the internal assessment criteria for Biology, or looking up the Extended Essay marking descriptors, the AI has the source material to work from. Coverage spans every DP subject from Language A through the Arts, including all SL and HL options. The knowledge base also includes the command terms glossary used across all DP subjects and assessments — so when you need to know exactly what "evaluate" means in a DP context, it's there.

Full ELA/Literacy and Mathematics standards for K–12, plus all official appendices — text exemplars, annotated student writing samples, and high school math course pathways. The knowledge base goes beyond the standards themselves to include instructional practice guides for classroom observation and lesson planning across multiple grade bands, curriculum-alignment tools, and reading foundational skills resources. If you're planning a lesson, observing a colleague, or differentiating for English language learners, the AI has standards-aligned guidance to draw on — including implementation guidance for students with disabilities and ELLs, and research-backed resources on close reading, spelling instruction, and MTSS.

The UDL Guidelines (version 2.2 and the 3.0 draft), the CAST Schoolwide Implementation Criteria, and a wide range of classroom tools for putting UDL into practice. Whether you're designing a lesson with multiple means of engagement, preparing for a UDL-focused observation, or leading schoolwide implementation, the AI can reference the specific guidelines, checkpoints, and planning tools that apply. The classroom tools collection covers observation and coaching (what to look for, how to track growth), lesson and assessment design, student self-reflection, and goal-setting. For school leaders, the knowledge base includes schoolwide readiness indicators, self-assessment tools, implementation planning resources, and guidance on antiracist UDL leadership. Enable this knowledge base alongside any curriculum KB, and the AI can apply UDL principles directly to your standards-aligned planning — building in multiple means of engagement, representation, and action from the start rather than retrofitting accessibility after the fact.

All Minnesota K–12 subject areas with standards content and implementation support, including learning progressions, instructional shifts, and assessment alignment charts. What makes this knowledge base distinctive is its depth beyond the core standards: it includes Indigenous education resources grounded in Dakota history and Minnesota tribal nations, English Language Development materials from Project Momentum for multilingual learner support, and PELSB licensing standards for professional educators. The Project Momentum collection is particularly deep — with ELD curriculum overlays by grade band, asset-based grading guides, individual language plan templates, translanguaging resources, and a full ESL licensure pathway handbook. If you're a Minnesota teacher working with multilingual learners or pursuing ESL licensure, the AI already has these tools at hand and can put them to work the moment you ask.

Texas education standards and assessments across all K–12 subject areas. The Texas Essential Knowledge and Skills (TEKS) are included for every subject — from core academics through fine arts, CTE, and career development. If you need to reference a specific standard, check a STAAR scoring guide or blueprint, or understand TELPAS proficiency expectations for a multilingual learner, the AI can pull from the relevant material without you having to look anything up first. STAAR coverage spans grades 3–8 and all high school end-of-course exams; TELPAS covers English language proficiency across grades 2–12. The knowledge base also includes College and Career Readiness standards across all four content areas, and accelerated instruction guidance — with implementation resources, high-impact tutoring best practices, and sample district schedules.

The WIDA English Language Development Standards Framework, 2020 Edition, Kindergarten through Grade 12. Includes all grade-level cluster standards with Proficiency Level Descriptors across six proficiency levels for both Interpretive and Expressive modes, and the four Key Language Uses — Narrate, Inform, Explain, and Argue — with genre examples and grade-level progressions. If you co-plan with content teachers, the AI can draw on collaborative planning guidance for content-language integration, tools for aligning your curriculum to the four Key Language Uses, conversation resources for engaging multilingual families, and a focused guide on applying WIDA principles in science classrooms. Enable this knowledge base alongside a curriculum KB like Minnesota, Texas, or IB MYP, and the AI can align your standards-based planning with WIDA language development expectations — so your content and language goals work together from the start.

All K–12 performance expectations organized in both the DCI and Topic arrangements used for unit planning, plus the official appendices covering Science and Engineering Practices, Crosscutting Concepts, engineering design, and grade-band progressions. When you ask the AI to help build a science assessment or align a unit to specific performance expectations, it's grounded in the actual NGSS documents. The knowledge base also includes classroom vignettes showing NGSS-aligned instruction for diverse learner populations — including English language learners, students with disabilities, and economically disadvantaged students — along with equity-focused resources and practical tools for designing assessments that are genuinely three-dimensional.

Case summaries of how international criminal tribunals — the ICC, ICTY, ICTR, SCSL, STL, and IRMCT — have admitted, weighed, and excluded digitally derived evidence: video, satellite imagery, intercepted communications, photographs, audio, geolocation analysis, and metadata. Built with the Fenix Project. Each summary captures the evidentiary issues a court grappled with — relevance, probative value, prejudice, authenticity, chain of custody, and corroboration — across procedural stages from Pre-Trial through Appeal. Filter by tribunal, situation, case number, proceedings stage, DDE type, or legal issue; use sparse search to pin exact case numbers like `ICC-01/12-01/15`.

Official College Board Course and Exam Descriptions (CEDs) for all 36 AP courses — big ideas and enduring understandings, units with exam weightings, learning objectives, essential knowledge statements, science and disciplinary practices, and sample exam questions. Coverage spans all 7 AP subject groups: History and Social Sciences, Sciences, World Languages and Cultures, Math and Computer Science, Arts, English, and Capstone. Filter by `course` (e.g. `biology`, `us-history`) or `subject_area` to narrow a search to a specific AP course or group.

Official Cambridge International IGCSE syllabuses for every current subject — 102 syllabus documents covering subject aims, content overview, subject content by numbered topic (Core and Extended tiers), assessment structure and paper breakdown, and grade descriptions. Coverage spans all eight Cambridge subject groups — world languages, sciences, humanities and social science, English and literature, business and economics, creative and vocational, technology and computing, and mathematics. Many subjects appear under both grading scales, so filter by `grading_type` (`a-star-g` or `9-1`), by `subject_area`, or by `course_code` (the Cambridge syllabus code, e.g. `0610`) to narrow a search.

Returns a detailed README for a specific knowledge base tool, including its contents, search capabilities, filtering options, and tips for effective searches. Use this to understand what a knowledge base contains and how to search it effectively before making queries. Supports a "mode" parameter for targeted retrieval — a table of contents, a specific section by heading, or a condensed summary — instead of always reading the full README.

This tool uses image generation models from Google or OpenAI to create images from text descriptions. Supports long descriptions. Choose a size (s, m, l, xl) and an aspect ratio (square, landscape, or portrait); on OpenAI models, small and medium always render as 1024x1024 (so pick large or extra large for non-square output) and large square is also capped at 1024x1024. Generates one to four images per request.

This tool uses OpenAI GPT image models to edit images the user has attached. Common uses include making a background transparent, changing the style while keeping the composition, combining multiple reference images into one, or applying targeted edits. Requires one or more images attached to the current message.

This tool leverages Anthropic agent skills to create professional documents as files including PDFs, PowerPoint presentations, Word documents, and Excel spreadsheets. The AI agent executes code to generate files based on your detailed instructions, including content, structure, formatting, and data requirements.

Connect to an external Knowledge Graph server that provides tools for exploring educational concepts, relationships between topics, and curriculum alignment data.

This tool delegates curriculum and educational standards queries to a specialized subagent with access to multiple educational knowledge bases (IB Diploma Programme (DP), IB Middle Years Programme (MYP), Common Core State Standards (CCSS), Universal Design for Learning (UDL), NGSS, WIDA, and state standards). Useful for cross-curriculum comparisons, comprehensive curriculum research, or when you need deep expertise across multiple educational frameworks. The subagent searches the knowledge bases systematically and returns a synthesized answer plus cited sources — with verbatim quotes for open knowledge bases — so the calling assistant can cross-check and refer back to the underlying material. Set "priority" to trade speed for context window: "speed" (default) runs a fast model; "depth" uses a larger context window and stronger synthesis for big multi-framework comparisons (escalates the model for subscribers).

A curated collection covering all 8 MYP subject groups across years 1–5, derived from official IB documents. Every subject includes guide content and the full assessment criteria with achievement level descriptors (bands 0–8 for years 1, 3, and 5). When you ask the AI to help design a summative task or give feedback on student work, it's drawing on the same criteria you'd look up in the subject guide yourself. Beyond the subject guides, the knowledge base includes teacher support material with sample tasks and assessed student work for Language Acquisition and Arts, programme-level guidance on Approaches to Learning and interdisciplinary planning, and the complete Community Project and Personal Project criteria and supervision guidance.

All 6 DP subject groups — with guide content, assessment criteria, and the three core components: Theory of Knowledge, Extended Essay, and CAS. Whether you're planning a History unit, checking the internal assessment criteria for Biology, or looking up the Extended Essay marking descriptors, the AI has the source material to work from. Coverage spans every DP subject from Language A through the Arts, including all SL and HL options. The knowledge base also includes the command terms glossary used across all DP subjects and assessments — so when you need to know exactly what "evaluate" means in a DP context, it's there.

Full ELA/Literacy and Mathematics standards for K–12, plus all official appendices — text exemplars, annotated student writing samples, and high school math course pathways. The knowledge base goes beyond the standards themselves to include instructional practice guides for classroom observation and lesson planning across multiple grade bands, curriculum-alignment tools, and reading foundational skills resources. If you're planning a lesson, observing a colleague, or differentiating for English language learners, the AI has standards-aligned guidance to draw on — including implementation guidance for students with disabilities and ELLs, and research-backed resources on close reading, spelling instruction, and MTSS.

The UDL Guidelines (version 2.2 and the 3.0 draft), the CAST Schoolwide Implementation Criteria, and a wide range of classroom tools for putting UDL into practice. Whether you're designing a lesson with multiple means of engagement, preparing for a UDL-focused observation, or leading schoolwide implementation, the AI can reference the specific guidelines, checkpoints, and planning tools that apply. The classroom tools collection covers observation and coaching (what to look for, how to track growth), lesson and assessment design, student self-reflection, and goal-setting. For school leaders, the knowledge base includes schoolwide readiness indicators, self-assessment tools, implementation planning resources, and guidance on antiracist UDL leadership. Enable this knowledge base alongside any curriculum KB, and the AI can apply UDL principles directly to your standards-aligned planning — building in multiple means of engagement, representation, and action from the start rather than retrofitting accessibility after the fact.

All Minnesota K–12 subject areas with standards content and implementation support, including learning progressions, instructional shifts, and assessment alignment charts. What makes this knowledge base distinctive is its depth beyond the core standards: it includes Indigenous education resources grounded in Dakota history and Minnesota tribal nations, English Language Development materials from Project Momentum for multilingual learner support, and PELSB licensing standards for professional educators. The Project Momentum collection is particularly deep — with ELD curriculum overlays by grade band, asset-based grading guides, individual language plan templates, translanguaging resources, and a full ESL licensure pathway handbook. If you're a Minnesota teacher working with multilingual learners or pursuing ESL licensure, the AI already has these tools at hand and can put them to work the moment you ask.

Texas education standards and assessments across all K–12 subject areas. The Texas Essential Knowledge and Skills (TEKS) are included for every subject — from core academics through fine arts, CTE, and career development. If you need to reference a specific standard, check a STAAR scoring guide or blueprint, or understand TELPAS proficiency expectations for a multilingual learner, the AI can pull from the relevant material without you having to look anything up first. STAAR coverage spans grades 3–8 and all high school end-of-course exams; TELPAS covers English language proficiency across grades 2–12. The knowledge base also includes College and Career Readiness standards across all four content areas, and accelerated instruction guidance — with implementation resources, high-impact tutoring best practices, and sample district schedules.

The WIDA English Language Development Standards Framework, 2020 Edition, Kindergarten through Grade 12. Includes all grade-level cluster standards with Proficiency Level Descriptors across six proficiency levels for both Interpretive and Expressive modes, and the four Key Language Uses — Narrate, Inform, Explain, and Argue — with genre examples and grade-level progressions. If you co-plan with content teachers, the AI can draw on collaborative planning guidance for content-language integration, tools for aligning your curriculum to the four Key Language Uses, conversation resources for engaging multilingual families, and a focused guide on applying WIDA principles in science classrooms. Enable this knowledge base alongside a curriculum KB like Minnesota, Texas, or IB MYP, and the AI can align your standards-based planning with WIDA language development expectations — so your content and language goals work together from the start.

All K–12 performance expectations organized in both the DCI and Topic arrangements used for unit planning, plus the official appendices covering Science and Engineering Practices, Crosscutting Concepts, engineering design, and grade-band progressions. When you ask the AI to help build a science assessment or align a unit to specific performance expectations, it's grounded in the actual NGSS documents. The knowledge base also includes classroom vignettes showing NGSS-aligned instruction for diverse learner populations — including English language learners, students with disabilities, and economically disadvantaged students — along with equity-focused resources and practical tools for designing assessments that are genuinely three-dimensional.

Case summaries of how international criminal tribunals — the ICC, ICTY, ICTR, SCSL, STL, and IRMCT — have admitted, weighed, and excluded digitally derived evidence: video, satellite imagery, intercepted communications, photographs, audio, geolocation analysis, and metadata. Built with the Fenix Project. Each summary captures the evidentiary issues a court grappled with — relevance, probative value, prejudice, authenticity, chain of custody, and corroboration — across procedural stages from Pre-Trial through Appeal. Filter by tribunal, situation, case number, proceedings stage, DDE type, or legal issue; use sparse search to pin exact case numbers like `ICC-01/12-01/15`.

Official College Board Course and Exam Descriptions (CEDs) for all 36 AP courses — big ideas and enduring understandings, units with exam weightings, learning objectives, essential knowledge statements, science and disciplinary practices, and sample exam questions. Coverage spans all 7 AP subject groups: History and Social Sciences, Sciences, World Languages and Cultures, Math and Computer Science, Arts, English, and Capstone. Filter by `course` (e.g. `biology`, `us-history`) or `subject_area` to narrow a search to a specific AP course or group.

Official Cambridge International IGCSE syllabuses for every current subject — 102 syllabus documents covering subject aims, content overview, subject content by numbered topic (Core and Extended tiers), assessment structure and paper breakdown, and grade descriptions. Coverage spans all eight Cambridge subject groups — world languages, sciences, humanities and social science, English and literature, business and economics, creative and vocational, technology and computing, and mathematics. Many subjects appear under both grading scales, so filter by `grading_type` (`a-star-g` or `9-1`), by `subject_area`, or by `course_code` (the Cambridge syllabus code, e.g. `0610`) to narrow a search.

Returns a detailed README for a specific knowledge base tool, including its contents, search capabilities, filtering options, and tips for effective searches. Use this to understand what a knowledge base contains and how to search it effectively before making queries. Supports a "mode" parameter for targeted retrieval — a table of contents, a specific section by heading, or a condensed summary — instead of always reading the full README.

This tool uses Perplexity AI Sonar to perform comprehensive web searches with synthesized, researched answers. Unlike simple search engines, Perplexity provides cited sources and contextual understanding. Best for research questions, current events, fact-checking, and queries requiring authoritative sources. Responses include citations and contextual analysis.

This tool searches the Internet Archive OpenLibrary database for books, authors, and works. Returns comprehensive book metadata including title, author, publication year, ISBN, edition count, and availability information. Best for finding books by title, author, or subject. OpenLibrary contains millions of books from libraries around the world.

This tool searches OpenAlex, a fully open catalog of 240M+ scholarly works, authors, institutions, and topics. Returns comprehensive academic metadata including citations, open access status, author affiliations, publication venues, and subject classifications. Best for finding research papers, tracking citations, discovering authors and institutions, and analyzing academic trends. Supports advanced filtering by publication year, citation count, open access status, and more.

This tool delegates research and search tasks to a specialized subagent with access to multiple search tools (OpenAlex, OpenLibrary, Web Search, Perplexity). Useful for complex research queries that benefit from using multiple search sources or when you want a specialized research assistant to handle the search comprehensively. The subagent can orchestrate multiple tool calls and synthesize findings across academic, web, and book searches.

This tool searches the web using Tavily, an AI-optimized search engine. It supports multiple search topics (general, news, finance), adjustable search depth, time-based filtering, and can extract full page content. You can filter by specific domains and request AI-generated answers synthesized from results.

This tool searches your saved documents using a combination of keywords and meaning. It covers each document's title, your own description and the AI-written description as well as the full body, so a document is findable by what it is about even when the title doesn't say.

This tool saves a new document to your library, including a generated title and markdown content, for easy retrieval later.

This tool fetches a single document from your library using its ID, returning the title, description, content, and metadata for direct access to specific documents.

This tool edits an existing document in your library. Supports full content replacement, targeted section replacement (by heading), appending content, and find/replace operations. Changes are saved immediately and the document is updated in real-time.

This tool reads a rectangular range of cells from a spreadsheet document using A1 notation (e.g. "A1:D50") or zero-based coordinates. Use it for surgical reads of large sheets instead of fetching the entire document.

This tool updates individual cells in a spreadsheet document. Provide a list of edits with zero-based row/column and the new value (or null to clear). Rows and columns grow to fit out-of-bounds edits. Use this instead of edit_document for spreadsheets.

This tool allows the AI to create new folders or update existing folder properties including name, description, and instructions. Folder instructions guide AI behavior for all conversations within that folder. Instructions are screened for safety.

This tool finds your folders by name, description, notes or folder instructions, and reports how many conversations, documents and files each one holds. It is what lets the AI turn a folder you name in words — "my Term 2 folder" — into the folder it actually works on, so Manage Folder can move things into it.

This tool fetches a file the user has attached to the conversation by its id, returning the parsed markdown content when available (or a download link otherwise), so the agent can read uploaded PDFs and other files on demand. Injected automatically when a conversation has attached files.

This tool finds files in your library by name, your own description, or the text parsed out of them — so a PDF is findable by a phrase on page four even when its filename says nothing. Results are metadata (name, type, folder, parse status); the agent reads a file with Get File. You can narrow to images, PDFs, or everything else, or to a single folder.

This tool uses image generation models from Google or OpenAI to create images from text descriptions. Supports long descriptions. Choose a size (s, m, l, xl) and an aspect ratio (square, landscape, or portrait); on OpenAI models, small and medium always render as 1024x1024 (so pick large or extra large for non-square output) and large square is also capped at 1024x1024. Generates one to four images per request.

This tool uses OpenAI GPT image models to edit images the user has attached. Common uses include making a background transparent, changing the style while keeping the composition, combining multiple reference images into one, or applying targeted edits. Requires one or more images attached to the current message.

This tool leverages Anthropic agent skills to create professional documents as files including PDFs, PowerPoint presentations, Word documents, and Excel spreadsheets. The AI agent executes code to generate files based on your detailed instructions, including content, structure, formatting, and data requirements.

This tool lets the AI author a new skill — a reusable title + one-line description + Markdown body — and save it to the user's private Agent Skills Library for retrieval in future conversations. Use it when a repeatable task is worth remembering. The skill is always created private to the user (sharing with others or the whole platform stays a human-only action from the /library/skills page). Content is screened for safety before saving (Agent Skills Library, issue #2523).

This tool retrieves conversations by ID and provides flexible access to conversation data. You can get the full conversation history, generate a summary, or ask specific questions about the conversation content.

This tool searches your conversation history using full-text search. You can search conversation details — title, auto-generated title, description, subject, tags, notes and instructions — or message content, or both. Returns matching conversations with metadata and message snippets. Use get_conversation with a conversation nanoid to retrieve more information.

Tool to take and edit notes throughout the conversation. This helps the TeamTeacher stay on task and keep track of work done and other notes about the conversation. It acts as a shared scratchpad for you and the TT.

This tool allows your TeamTeacher agent to make a request to another TeamTeacher agent.

This tool computes math with real math engines instead of relying on AI prediction — the same "never trust mental arithmetic" approach used by dedicated math tutors. It evaluates arithmetic, fractions, unit conversions, matrices, and statistics; simplifies and expands algebraic expressions; and solves equations symbolically. The AI uses it to verify answer keys, worked solutions, and any numeric claims before presenting them, and results come back as beautifully rendered notation.

Connect to an external Knowledge Graph server that provides tools for exploring educational concepts, relationships between topics, and curriculum alignment data.