[{"data":1,"prerenderedAt":777},["ShallowReactive",2],{"page-\u002Fagentic-modelling\u002F04-draw-a-tool-that-reaches-any-host":3,"navigation":455},{"id":4,"title":5,"body":6,"description":447,"extension":448,"meta":449,"navigation":450,"path":451,"seo":452,"stem":453,"__hash__":454},"docs\u002F07.agentic-modelling\u002F04.04-draw-a-tool-that-reaches-any-host.md","Lesson 4: Draw a Tool That Reaches Any Host",{"type":7,"value":8,"toc":432},"minimark",[9,13,31,36,39,42,46,54,57,61,66,69,76,81,91,97,102,110,114,160,163,166,170,176,218,224,227,258,264,271,275,278,299,318,324,330,334,337,345,353,357,383,387,389,409,413,419,422,426],[10,11,5],"h1",{"id":12},"lesson-4-draw-a-tool-that-reaches-any-host",[14,15,16,21,22,26,27],"p",{},[17,18,20],"a",{"href":19},"\u002Fagentic-modelling","Training overview"," · Lesson 4 of 11 · Previous: ",[17,23,25],{"href":24},"\u002Fagentic-modelling\u002F03-mark-who-is-outside","Mark who is outside"," · Next: ",[17,28,30],{"href":29},"\u002Fagentic-modelling\u002F05-state-what-the-agent-can-do","State what the agent can do",[32,33,35],"h2",{"id":34},"goal","Goal",[14,37,38],{},"A tool that can reach any host is one flow to an untrusted \"any host\" element, and it is both a way out and a way in.",[14,40,41],{},"After this lesson you can draw a web fetch, a shell or any other tool whose destination the attacker can choose, without drawing every host it might reach.",[32,43,45],{"id":44},"what-you-start-from","What you start from",[14,47,48,49,53],{},"Your model from lesson 3, or import ",[17,50,52],{"href":51},"\u002Fguides\u002Fagentic-modelling\u002FL3-solution.zip","L3-solution.zip",".",[14,55,56],{},"The team adds a web-fetch tool to the copilot, so it can open links that customers paste into tickets.",[32,58,60],{"id":59},"the-recipe-step","The recipe step",[62,63,65],"h3",{"id":64},"step-4-draw-tools-that-reach-any-host","Step 4: Draw tools that reach any host",[14,67,68],{},"Draw every flow an agent's tools can open, outbound ones included. A tool that can reach any host (a web fetch, a shell, an image fetched while rendering) gets one flow to an \"Arbitrary internet hosts\" element in the Untrusted boundary, and the content it brings back as a Context Ingress.",[14,70,71,75],{},[72,73,74],"strong",{},"Why:"," A tool that can reach any host is both a way out and a way in. Nothing infers it from an attribute: it counts only when it is drawn.",[14,77,78],{},[72,79,80],{},"Ask:",[82,83,84,88],"ul",{},[85,86,87],"li",{},"Which of the agent's tools can reach a host the attacker chooses?",[85,89,90],{},"Can it reach internal addresses or the cloud metadata endpoint? If so, draw those flows too.",[14,92,93,96],{},[72,94,95],{},"Classes:"," Untrusted Content Source, Agent Tool Call, HTTP\u002FS Request, Context Ingress.",[14,98,99],{},[72,100,101],{},"What the analysis reads here:",[82,103,104,107],{},[85,105,106],{},"A source whose content is untrusted by its class: Untrusted Content Source, Public AI Artifact Hub.",[85,108,109],{},"A frontend that renders model output: Agent Chat Frontend.",[32,111,113],{"id":112},"steps","Steps",[115,116,117,127,140,150],"ol",{},[85,118,119,120,123,124,53],{},"Add ",[72,121,122],{},"Arbitrary internet hosts"," (class Untrusted Content Source), inside ",[72,125,126],{},"Internet",[85,128,129,130,133,134,137,138,53],{},"Draw ",[72,131,132],{},"Fetch URL"," (class Agent Tool Call) from ",[72,135,136],{},"Support copilot"," to ",[72,139,122],{},[85,141,129,142,145,146,137,148,53],{},[72,143,144],{},"Context Ingress: fetched page"," (class Context Ingress) from ",[72,147,122],{},[72,149,136],{},[85,151,152,153,155,156,159],{},"On the Data tab of ",[72,154,144],{},", add the data item ",[72,157,158],{},"Fetched page"," (no class). Sensitivity: Public; Origin: Arbitrary public; Credential: No.",[14,161,162],{},"The fetched page has no class: no data class describes a page fetched live. Give it the three fields anyway: they are what the analysis reads.",[14,164,165],{},"Generate again.",[32,167,169],{"id":168},"what-you-should-see","What you should see",[14,171,172,175],{},[72,173,174],{},"Findings:"," 1 systemic finding: 1 Confirmed · 0 Not ruled out.",[177,178,184],"div",{"className":179,"tabIndex":181,"role":182,"ariaLabel":183},[180],"table-frame",0,"region","Table: What you should see",[185,186,187,203],"table",{},[188,189,190],"thead",{},[191,192,193,197,200],"tr",{},[194,195,196],"th",{},"Finding",[194,198,199],{},"State",[194,201,202],{},"Legs",[204,205,206],"tbody",{},[191,207,208,212,215],{},[209,210,211],"td",{},"Lethal trifecta at Support copilot",[209,213,214],{},"Confirmed · unmitigated",[209,216,217],{},"U present · P present · X present · W undetermined (aggravating)",[14,219,220,223],{},[72,221,222],{},"Facts to establish:"," 3 questions.",[14,225,226],{},"Facts that could raise a finding:",[82,228,229,241,255],{},[85,230,231,232,235,236,240],{},"Set the attribute ",[72,233,234],{},"Code Execution Tools Present"," (",[237,238,239],"code",{},"code_execution_tools_present",", in Application Security) on Support copilot, or draw its Agent Tool Call to the harness",[85,242,231,243,235,246,249,250,235,252,254],{},[72,244,245],{},"Consequential Tools Present",[237,247,248],{},"consequential_tools_present",", in Human Oversight) or ",[72,251,234],{},[237,253,239],{},", in Application Security) on Support copilot",[85,256,257],{},"Draw the runtime boundary or the Agent Tool Call that ties Support copilot to its harness",[14,259,260,263],{},[72,261,262],{},"Model gaps:"," 1 of 1 agents have no hosting harness drawn, so their W cannot be read from one (on Support copilot)",[14,265,266,267,270],{},"The summary looks the same as after lesson 3: the trifecta is still ",[72,268,269],{},"Confirmed",". The change is inside the finding.",[32,272,274],{"id":273},"what-changed-and-why","What changed and why",[14,276,277],{},"Expand the lethal trifecta and look at its legs.",[14,279,280,283,284,287,288,291,292,294,295,298],{},[72,281,282],{},"X has a new route of the copilot's own."," The fetch is a tool the copilot calls, so you draw it as an Agent Tool Call, like ",[72,285,286],{},"CRM lookup"," and ",[72,289,290],{},"Post reply",". The fetch flow goes from the copilot straight to ",[72,293,122],{},", in the Untrusted zone. The copilot can send data out on its own, not only through the ticket system's e-mail. The route is labelled ",[72,296,297],{},"stated",": you drew it.",[14,300,301,304,305,307,308,310,311,313,314,317],{},[72,302,303],{},"U has a new route too."," The content of a fetched page comes back on the Context Ingress from ",[72,306,122],{},". The route reads ",[72,309,297],{},": the ",[72,312,158],{}," item you drew on it has a stated origin, ",[72,315,316],{},"Arbitrary public",". Its basis adds two more reasons: the source sits in the Untrusted zone, and it is an Untrusted Content Source, whose content is untrusted because of what the element is (a class premise). That premise would hold even with no data item drawn on the flow.",[14,319,320,323],{},[72,321,322],{},"One element stands for every host."," You do not draw each website. One element in the Untrusted boundary, one flow out to it and one Context Ingress back cover every host the tool can reach. Nothing infers a tool like this from an attribute: it counts only when it is drawn.",[14,325,326,329],{},[72,327,328],{},"\"Any host\" can mean your own hosts too."," If the tool can also reach internal addresses or the cloud metadata endpoint, those are destinations an attacker can choose as well. The step's second question asks about them: draw those flows too.",[32,331,333],{"id":332},"exercise-think-in-routes-not-in-tools","Exercise: Think in routes, not in tools",[14,335,336],{},"Make this change and generate again:",[14,338,339,340,344],{},"On a scratch copy: import ",[17,341,343],{"href":342},"\u002Fguides\u002Fagentic-modelling\u002FL4-solution.zip","L4-solution.zip"," and rename it.",[115,346,347],{},[85,348,349,350,53],{},"Delete ",[72,351,352],{},"Reply e-mail",[14,354,355,175],{},[72,356,174],{},[177,358,361],{"className":359,"tabIndex":181,"role":182,"ariaLabel":360},[180],"Table: Exercise: Think in routes, not in tools",[185,362,363,373],{},[188,364,365],{},[191,366,367,369,371],{},[194,368,196],{},[194,370,199],{},[194,372,202],{},[204,374,375],{},[191,376,377,379,381],{},[209,378,211],{},[209,380,214],{},[209,382,217],{},[14,384,385,223],{},[72,386,222],{},[14,388,226],{},[82,390,391,397,407],{},[85,392,231,393,235,395,240],{},[72,394,234],{},[237,396,239],{},[85,398,231,399,235,401,249,403,235,405,254],{},[72,400,245],{},[237,402,248],{},[72,404,234],{},[237,406,239],{},[85,408,257],{},[14,410,411,263],{},[72,412,262],{},[14,414,415,416,418],{},"The trifecta stays ",[72,417,269],{}," through the fetch. Removing the reply e-mail closed one way out, but the fetch is another. A leg is present as long as one route is present. When you look for a fix, count the routes, not the tools.",[14,420,421],{},"Delete the copy when you are done.",[32,423,425],{"id":424},"next","Next",[14,427,428,431],{},[17,429,430],{"href":29},"Lesson 5: State what the agent can do",". You answer the facts about the copilot that no drawing can show.",{"title":433,"searchDepth":434,"depth":434,"links":435},"",3,[436,438,439,442,443,444,445,446],{"id":34,"depth":437,"text":35},2,{"id":44,"depth":437,"text":45},{"id":59,"depth":437,"text":60,"children":440},[441],{"id":64,"depth":434,"text":65},{"id":112,"depth":437,"text":113},{"id":168,"depth":437,"text":169},{"id":273,"depth":437,"text":274},{"id":332,"depth":437,"text":333},{"id":424,"depth":437,"text":425},"Training overview · Lesson 4 of 11 · Previous: Mark who is outside · Next: State what the agent can do","md",{},true,"\u002Fagentic-modelling\u002F04-draw-a-tool-that-reaches-any-host",{"title":5,"description":447},"07.agentic-modelling\u002F04.04-draw-a-tool-that-reaches-any-host","Cw8M5Hc5no98fPdtHmjpNQp30zIhmcQ5LbyFU9HV9UY",[456,511,546,601,635,679,694,757],{"title":457,"description":458,"path":459,"stem":460,"children":461,"page":-1},"Platform","Modelling, analysis, findings and controls in the Dethernety platform.","\u002Fplatform","01.platform",[462,466,471,476,481,486,491,496,501,506],{"title":463,"path":459,"stem":464,"description":465},"Dethernety User Documentation","01.platform\u002Findex","User guide for the Dethernety threat modeling platform",{"title":467,"path":468,"stem":469,"description":470},"Quick Start","\u002Fplatform\u002Fquick-start","01.platform\u002F01.quick-start","Install Dethernety on your own machine, draw a four-element model and read its first threat finding.",{"title":472,"path":473,"stem":474,"description":475},"Building Your First Model","\u002Fplatform\u002Fbuilding-your-first-model","01.platform\u002F02.building-your-first-model","Build a threat model of an online store in about 30 minutes, run a Threat Report on it, and raise an issue from a finding.",{"title":477,"path":478,"stem":479,"description":480},"Security Analysis Workflow","\u002Fplatform\u002Fsecurity-analysis-workflow","01.platform\u002F03.security-analysis-workflow","How to run security analysis and interpret results to improve your threat models.",{"title":482,"path":483,"stem":484,"description":485},"Managing Findings","\u002Fplatform\u002Fmanaging-findings","01.platform\u002F04.managing-findings","Record decisions on system-generated exposures and countermeasures — affirm them as confirmed live risk, or mute them as not applicable, false positive, waived, or superseded — instead of deleting them.",{"title":487,"path":488,"stem":489,"description":490},"Working with Security Controls","\u002Fplatform\u002Fworking-with-security-controls","01.platform\u002F05.working-with-security-controls","Learn how to create, manage, and assign reusable security controls in Dethernety to protect your threat models.",{"title":492,"path":493,"stem":494,"description":495},"Issue Management Guide","\u002Fplatform\u002Fissue-management-guide","01.platform\u002F06.issue-management-guide","Issue tracking, filtering, and management in Dethernety.",{"title":497,"path":498,"stem":499,"description":500},"Boundary Trust Zones","\u002Fplatform\u002Fboundary-trust-zones","01.platform\u002F07.boundary-trust-zones","Record each security boundary's trust zone, business domains, operational role, and approved channels to document how your system is meant to be segmented.",{"title":502,"path":503,"stem":504,"description":505},"Understanding Modules","\u002Fplatform\u002Funderstanding-modules","01.platform\u002F08.understanding-modules","How Dethernety's module system extends your threat modeling capabilities.",{"title":507,"path":508,"stem":509,"description":510},"Component Configuration Guide","\u002Fplatform\u002Fcomponent-configuration-guide","01.platform\u002F09.component-configuration-guide","Detailed guide on configuring different types of components and their security implications.",{"title":512,"description":513,"path":514,"stem":515,"children":516,"page":-1},"BYODt cloud","Deploying the platform yourself and connecting it to the BYODt cloud.","\u002Fbyodt-cloud","02.byodt-cloud",[517,521,526,531,536,541],{"title":518,"path":514,"stem":519,"description":520},"BYODt Deployment","02.byodt-cloud\u002Findex","Run Dethernety on your own machine: install, configure, operate, and recover",{"title":522,"path":523,"stem":524,"description":525},"Installing the BYODt Deployment","\u002Fbyodt-cloud\u002Finstallation","02.byodt-cloud\u002F01.installation","Install Dethernety on your own machine: check the requirements, download and verify the signed bundle, start it, and confirm the deployment is healthy",{"title":527,"path":528,"stem":529,"description":530},"Configuring the BYODt Deployment","\u002Fbyodt-cloud\u002Fconfiguration","02.byodt-cloud\u002F02.configuration","The .env settings reference, the generated secret file, database storage, and how to apply a change",{"title":532,"path":533,"stem":534,"description":535},"Operating the BYODt Deployment","\u002Fbyodt-cloud\u002Foperations","02.byodt-cloud\u002F03.operations","The byodt command reference and the day-to-day tasks: start, stop, inspect, back up, restore, TLS, upgrade, remove",{"title":537,"path":538,"stem":539,"description":540},"Connecting the BYODt Deployment to the Cloud","\u002Fbyodt-cloud\u002Fcloud","02.byodt-cloud\u002F04.cloud","Add cloud sign-in and content packages from the operator console, and disconnect again",{"title":542,"path":543,"stem":544,"description":545},"Troubleshooting the BYODt Deployment","\u002Fbyodt-cloud\u002Ftroubleshooting","02.byodt-cloud\u002F05.troubleshooting","Symptom, cause, and fix for the failures this deployment reports",{"title":547,"description":548,"path":549,"stem":550,"children":551,"page":-1},"Dethereal","The Claude Code plugin: build a threat model in conversation and publish it to the platform.","\u002Fdethereal","03.dethereal",[552,556,561,566,571,576,581,586,591,596],{"title":553,"path":549,"stem":554,"description":555},"Dethereal — Claude Code Plugin for Threat Modeling","03.dethereal\u002Findex","Comprehensive documentation for the Dethereal threat modeling plugin",{"title":557,"path":558,"stem":559,"description":560},"Getting Started with Dethereal","\u002Fdethereal\u002Fgetting-started","03.dethereal\u002F01.getting-started","Install the plugin, authenticate, and create your first threat model",{"title":562,"path":563,"stem":564,"description":565},"The 11-Step Guided Workflow","\u002Fdethereal\u002Fguided-workflow","03.dethereal\u002F02.guided-workflow","Complete walkthrough of the \u002Fdethereal:threat-model guided process",{"title":567,"path":568,"stem":569,"description":570},"Command Reference","\u002Fdethereal\u002Fcommand-reference","03.dethereal\u002F03.command-reference","Complete reference for all 14 Dethereal slash commands",{"title":572,"path":573,"stem":574,"description":575},"Threat Model Concepts","\u002Fdethereal\u002Fmodel-concepts","03.dethereal\u002F04.model-concepts","Components, boundaries, data flows, classes, attributes, and quality scoring",{"title":577,"path":578,"stem":579,"description":580},"Discovery and Enrichment","\u002Fdethereal\u002Fdiscovery-and-enrichment","03.dethereal\u002F05.discovery-and-enrichment","Infrastructure scanning, security attributes, MITRE ATT&CK, credentials, and compliance",{"title":582,"path":583,"stem":584,"description":585},"Sync and Version Control","\u002Fdethereal\u002Fsync-and-version-control","03.dethereal\u002F06.sync-and-version-control","Push\u002Fpull workflow, conflict handling, git integration, and multi-model projects",{"title":587,"path":588,"stem":589,"description":590},"Review and Attack Surface Analysis","\u002Fdethereal\u002Freview-and-analysis","03.dethereal\u002F07.review-and-analysis","Quality review, attack surface summary, and platform analysis integration",{"title":592,"path":593,"stem":594,"description":595},"Agents, Tools, and Hooks","\u002Fdethereal\u002Fagents-and-architecture","03.dethereal\u002F08.agents-and-architecture","How the 5 AI agents, 22 MCP tools, and 3 lifecycle hooks work together",{"title":597,"path":598,"stem":599,"description":600},"Dethereal Glossary","\u002Fdethereal\u002Fglossary","03.dethereal\u002F09.glossary","Definitions for Dethereal-specific terminology",{"title":602,"description":603,"path":604,"stem":605,"children":606,"page":-1},"Threat Report","The residual-risk report over a threat model: reading it, filtering it and exporting it.","\u002Fthreat-report","04.threat-report",[607,610,615,620,625,630],{"title":602,"path":604,"stem":608,"description":609},"04.threat-report\u002Findex","Read, filter, drill into, and export a residual-risk report over a threat model",{"title":611,"path":612,"stem":613,"description":614},"Getting Started with the Threat Report","\u002Fthreat-report\u002Fgetting-started","04.threat-report\u002F01.getting-started","Generate, open, refresh, and export a threat report over a model",{"title":616,"path":617,"stem":618,"description":619},"Reading the Report","\u002Fthreat-report\u002Freading-the-report","04.threat-report\u002F02.reading-the-report","Navigating the report, the shared visual language, and the Posture and Boundary Crossings views",{"title":621,"path":622,"stem":623,"description":624},"Understanding Coverage and Gaps","\u002Fthreat-report\u002Funderstanding-coverage","04.threat-report\u002F03.understanding-coverage","Reading the MITRE ATT&CK coverage matrix: tiers, prevent vs detect, off-grid notes, and what coverage does and does not mean",{"title":626,"path":627,"stem":628,"description":629},"Reachability and Flow Routes","\u002Fthreat-report\u002Freachability","04.threat-report\u002F04.reachability","Exploring flow routes to crown-jewel assets and between any two elements — and what the analysis does and does not model",{"title":631,"path":632,"stem":633,"description":634},"Working with Findings","\u002Fthreat-report\u002Fworking-with-findings","04.threat-report\u002F05.working-with-findings","The Residual Risk ledger, triaging findings, filtering, and the per-element Component Profile",{"title":636,"description":637,"path":638,"stem":639,"children":640,"page":-1},"Risk assessment","The risk assessment module: the register, the reports and the method behind them.","\u002Frisk-assessment","05.risk-assessment",[641,645,650,655,660,665,669,674],{"title":642,"path":638,"stem":643,"description":644},"Dethernety Risk Assessment User Guide","05.risk-assessment\u002Findex","Dethernety Risk Assessment turns a threat model you have built on the Dethernety platform into a grounded, board-ready draft risk report. From one point-in-time assessment of your model you get a prioritized worklist, a likelihood × impact risk matrix, a security-coverage posture, ten kinds of finding, a management risk register your team authors and maintains, and audience-tiered stakeholder reports — Board, Risk Committee, and Technical — plus machine-readable data exports.",{"title":646,"path":647,"stem":648,"description":649},"FAQ and Troubleshooting","\u002Frisk-assessment\u002Ffaq","05.risk-assessment\u002F01.faq","Short answers to the questions analysts, risk managers, and compliance officers ask most often about the Risk Assessment. Each answer links to the guide that covers it in full.",{"title":651,"path":652,"stem":653,"description":654},"Findings","\u002Frisk-assessment\u002Ffindings","05.risk-assessment\u002F02.findings","A finding is a specific observation the Risk Assessment makes about your threat model. Every finding is grounded in something concrete you have declared — an element, a data flow, a trust zone, a crown jewel — and it points you at a place worth a closer look. This guide is the reference to open when you see a finding and want to know what it means and what to do about it.",{"title":656,"path":657,"stem":658,"description":659},"Getting Started","\u002Frisk-assessment\u002Fgetting-started","05.risk-assessment\u002F03.getting-started","Risk Assessment turns a threat model you have built on the Dethernety platform into a grounded, board-ready draft risk report — a prioritized worklist, a likelihood × impact matrix, a security-coverage posture, ten kinds of finding, a risk register your team authors, and audience-tiered stakeholder reports and exports.",{"title":661,"path":662,"stem":663,"description":664},"Methodology and Trust","\u002Frisk-assessment\u002Fmethodology-and-trust","05.risk-assessment\u002F04.methodology-and-trust","Every number in a Risk Assessment is meant to survive scrutiny. This chapter explains why you can trust the report and — just as importantly — what it deliberately declines to claim, so you can put it in front of your board, a regulator, or an external auditor and defend every line.",{"title":616,"path":666,"stem":667,"description":668},"\u002Frisk-assessment\u002Freading-the-report","05.risk-assessment\u002F05.reading-the-report","The Risk Assessment turns your threat model into a single, scannable draft risk report: an executive summary at the top and a set of analytical tabs below it. This guide explains how to read what you see — what a matrix cell means, how coverage is stated, what a severity band is (and is not), and how to interpret each tab.",{"title":670,"path":671,"stem":672,"description":673},"Stakeholder Reports and Exports","\u002Frisk-assessment\u002Fstakeholder-reports","05.risk-assessment\u002F06.stakeholder-reports","One assessment produces reporting for every audience you answer to. From a single generated Risk Assessment you can hand your board a one-page brief, give your risk committee the full reconciliation, keep the complete technical detail for your own team, and export the underlying data into your GRC tool — without ever re-running anything or reconciling one document against another.",{"title":675,"path":676,"stem":677,"description":678},"The Risk Register","\u002Frisk-assessment\u002Fthe-risk-register","05.risk-assessment\u002F07.the-risk-register","The Risk Register is where your team records and manages the real risks your organisation is carrying — on top of, but separate from, what the analysis computed for you. Each entry is written by a person: a plain-language risk statement, your own assessment of how likely it is and how much it would hurt, the findings and elements from the analysis that back it up, a treatment decision, an owner, a review date, and a reference handle you can quote in a ticket or a board pack.",{"title":680,"description":681,"path":682,"stem":683,"children":684,"page":-1},"Threat Patterns","The Threat Patterns module and its modelling checklist.","\u002Fthreat-patterns","06.threat-patterns",[685,689],{"title":686,"path":682,"stem":687,"description":688},"Threat Patterns User Guide","06.threat-patterns\u002Findex","Threat Patterns finds threats in your model that no single element shows on its own. Each one appears only when several elements line up. For example, an agent may read content anyone can write, hold private data, and be able to send data where an outsider reads it. Each element can look acceptable alone, but together they form a path an attacker can use.",{"title":690,"path":691,"stem":692,"description":693},"Modelling Checklist","\u002Fthreat-patterns\u002Fmodelling-checklist","06.threat-patterns\u002F01.modelling-checklist","Threat Patterns decides a leg only from what your model states. An unanswered attribute or field is undetermined, never read as \"no\". This checklist lists the facts and drawings the analysis asks for most often. For each one it says where to set it and which leg it settles. Attribute names are shown as they appear on the class, in code.",{"title":695,"description":696,"path":19,"stem":697,"children":698,"page":-1},"Agentic modelling","A hands-on training: model one agentic system step by step, with Threat Patterns after each step.","07.agentic-modelling",[699,703,708,713,717,718,722,727,732,737,742,747,752],{"title":700,"path":19,"stem":701,"description":702},"Model an Agentic Architecture","07.agentic-modelling\u002Findex","A hands-on training in modelling systems that run AI agents, so that Threat Patterns can analyse them. You build one system, a fictional customer-support copilot, in eleven short lessons. Each lesson adds one thing to the model, and you run Threat Patterns after each one to see what the change did.",{"title":704,"path":705,"stem":706,"description":707},"Lesson 1: Draw the Agent and What It Talks To","\u002Fagentic-modelling\u002F01-draw-the-agent","07.agentic-modelling\u002F01.01-draw-the-agent","Training overview · Lesson 1 of 11 · Next: Say what data moves",{"title":709,"path":710,"stem":711,"description":712},"Lesson 2: Say What Data Moves","\u002Fagentic-modelling\u002F02-say-what-data-moves","07.agentic-modelling\u002F02.02-say-what-data-moves","Training overview · Lesson 2 of 11 · Previous: Draw the agent · Next: Mark who is outside",{"title":714,"path":24,"stem":715,"description":716},"Lesson 3: Mark Who Is Outside","07.agentic-modelling\u002F03.03-mark-who-is-outside","Training overview · Lesson 3 of 11 · Previous: Say what data moves · Next: Draw a tool that reaches any host",{"title":5,"path":451,"stem":453,"description":447},{"title":719,"path":29,"stem":720,"description":721},"Lesson 5: State What the Agent Can Do","07.agentic-modelling\u002F05.05-state-what-the-agent-can-do","Training overview · Lesson 5 of 11 · Previous: Draw a tool that reaches any host · Next: Fix a finding with a fact",{"title":723,"path":724,"stem":725,"description":726},"Lesson 6: Fix a Finding With a Fact","\u002Fagentic-modelling\u002F06-fix-a-finding-with-a-fact","07.agentic-modelling\u002F06.06-fix-a-finding-with-a-fact","Training overview · Lesson 6 of 11 · Previous: State what the agent can do · Next: Record a compensating control",{"title":728,"path":729,"stem":730,"description":731},"Lesson 7: Record a Compensating Control","\u002Fagentic-modelling\u002F07-record-a-compensating-control","07.agentic-modelling\u002F07.07-record-a-compensating-control","Training overview · Lesson 7 of 11 · Previous: Fix a finding with a fact · Next: Leave what you don't know open",{"title":733,"path":734,"stem":735,"description":736},"Lesson 8: Leave What You Don't Know Open","\u002Fagentic-modelling\u002F08-leave-unknowns-open","07.agentic-modelling\u002F08.08-leave-unknowns-open","Training overview · Lesson 8 of 11 · Previous: Record a compensating control · Next: Follow a credential",{"title":738,"path":739,"stem":740,"description":741},"Lesson 9: Follow a Credential","\u002Fagentic-modelling\u002F09-follow-a-credential","07.agentic-modelling\u002F09.09-follow-a-credential","Training overview · Lesson 9 of 11 · Previous: Leave what you don't know open · Next: Watch what gets into knowledge and memory",{"title":743,"path":744,"stem":745,"description":746},"Lesson 10: Watch What Gets Into Knowledge and Memory","\u002Fagentic-modelling\u002F10-what-gets-in","07.agentic-modelling\u002F10.10-what-gets-in","Training overview · Lesson 10 of 11 · Previous: Follow a credential · Next: Draw tools from others and hand-offs",{"title":748,"path":749,"stem":750,"description":751},"Lesson 11: Draw Tools From Others and Hand-offs","\u002Fagentic-modelling\u002F11-tools-and-handoffs","07.agentic-modelling\u002F11.11-tools-and-handoffs","Training overview · Lesson 11 of 11 · Previous: Watch what gets into knowledge and memory",{"title":753,"path":754,"stem":755,"description":756},"The recipe at a glance","\u002Fagentic-modelling\u002Frecipe-at-a-glance","07.agentic-modelling\u002F12.recipe-at-a-glance","The ten steps of the training on one page. Each lesson teaches one or two of them.",{"title":758,"description":759,"path":760,"stem":761,"children":762,"page":-1},"BYODt subscription","Subscribing on the BYODt Portal, and moving a deployment you already run to a new team.","\u002Fbyodt-subscription","08.byodt-subscription",[763,767,772],{"title":764,"path":760,"stem":765,"description":766},"BYODt Subscription","08.byodt-subscription\u002Findex","Buy content for the deployment you run yourself, and decide where that deployment goes when you buy a team edition",{"title":768,"path":769,"stem":770,"description":771},"Your Subscription","\u002Fbyodt-subscription\u002Fyour-subscription","08.byodt-subscription\u002F01.your-subscription","Create an account, subscribe by card, and find the values your deployment needs on the portal",{"title":773,"path":774,"stem":775,"description":776},"Moving a Deployment to a New Team","\u002Fbyodt-subscription\u002Fmoving-a-deployment-to-a-new-team","08.byodt-subscription\u002F02.moving-a-deployment-to-a-new-team","What to do with the deployment you already run once you buy a team edition: three ways forward, best first",1793748186442]