creating-flow

Robomotion Flow Builder

Robomotion is an RPA platform with a TypeScript SDK and a visual node editor. This skill is a thin index over the reference docs in ./docs/. Read the relevant doc when a topic comes up — don't try to memorize it from this file.

Hard Rules (SDK rejects violations at validate time)

The SDK enforces these. Violations throw at robomotion validate / build with descriptive messages, so the agent never silently produces broken flows:

1. Node IDs MUST be 6-char lowercase hex — /^[0-9a-f]{6}$/. f.node(), .then(), f.edge() reject non-hex IDs ('begin', 'label', 'maps', uppercase) at registration. Generate each id at random (openssl rand -hex 3); never copy an example id from these docs and never write a pattern like a1b2c3 or aa11bb. See ./docs/reference/id-format.md.
2. Subflow node ID = subflows/<id>.ts filename, exactly. Both must be 6-hex. The Designer's "enter subflow" UX depends on the match.
3. f.addDependency(namespace, version) is validated against the live package index. version must be concrete ('latest' is rejected) and must exist in the package's published versions list. namespace must exist in https://packages.robomotion.io/stable/index.json. Run robomotion get packages <ns> or robomotion describe package <ns> to resolve real versions before calling addDependency. Never invent a version.
4. Terminal nodes (Debug, Log, Stop, GoTo, End, WaitGroup.Done) have 0 outputs — wire TO them via f.edge(), never .then() from them.
5. Every Core.Flow.GoTo references a Core.Flow.Label id that exists in the same flow file.
6. A flow file is a declaration the Flow Designer can READ, not a program only Bun can run. The Designer parses main.ts and each subflows/*.ts statically, one file at a time, draws what it understood, and regenerates the whole file from the canvas on every save - whatever it could not read is gone from git after the person's first save. So: the ONE import is @robomotion/sdk; every node is a literal f.node() / .then() / f.edge() written inside the create callback (no helper functions, no loops, no .map()); every prop is a literal, an array/object of literals, a scope helper over one, or a string built from same-file consts with a template, + or [..].join('\n'); no spreads ({ ...SHARED }), no shorthand props, no imported helpers in a func. A shared helper string is declared again in each file that uses it. robomotion validate refuses the rest with "the Flow Designer cannot read it". Full table: ./docs/reference/project-format.md.
7. The program is the flow; a Function node is glue code, written only where necessary, and written for a person to read. We do write code, but only where a step needs it: a Function shapes msg for the next node. The work goes into nodes: SQL lives in the SQL node with {{{field}}} placeholders, never string-built in JavaScript; a rule the person would name is its own Function with outputs: 2; formatting is the screen's job; there is no helper library, and never one pasted into every node. The code is formatted: one statement per line, blocks on their own lines, indented, blank lines between parts. No line limit - a long Function that does one thing and reads top to bottom is fine. robomotion validate refuses crammed code ("several statements on one line", "a whole block on one line") and the same block opening three or more Functions. Where each urge belongs: ./docs/reference/function-nodes.md.

Required First Line

Every flow file (main.ts and every subflows/*.ts) starts with this exact import — copy verbatim, including helpers you don't currently use (Bun won't flag dead imports, but missing ones become runtime ReferenceError):

import { flow, Message, Custom, JS, Global, Flow, Credential, AI } from '@robomotion/sdk';

For library files swap flow for library / subflow. This is the rule for every file, however small: there is no shorter "minimal" import, and every example in these docs starts with this line. Full reference: ./docs/reference/imports.md.

Builder grammar

• f.node(id, type, name, props) — param order. Only emit non-default props (Go runtime fills defaults from pspec).
• .then() for sequential, .edge() for multi-port wiring.
• Message(name) for variables · Custom(value) for literals · JS(expr) for one-line JS · Credential({vaultId, itemId}) for secrets.
• A field takes a scope helper based on its TYPE IN THAT NODE, not its in*/opt* name — and the SAME name can differ across nodes. Every in*/out* port takes a scope helper (Custom('…') / Message()); a bare literal there is silently dropped. For opt* fields, don't guess from the name — check robomotion describe node <type>: a field typed object + variableType (even a numeric one) takes a scope helper; a plain number/boolean/enum field takes a bare literal and must NOT be wrapped. The very same property can differ by node: Core.Browser.OpenLink optTimeout is a plain number → optTimeout: 32, but Core.Browser.WaitElement optTimeout is variableType:Integer → optTimeout: Custom('30'). Mismatching either way VALIDATES but FAILS TO LOAD on the robot (flow_error: failed / Config parse error, no nodes run): wrapping a plain field sends an object to a scalar; leaving a variable-backed field bare sends a scalar into a {scope,name} slot. Enums/booleans are always plain (optBrowser: 'chrome', optMethod: 'post', optInsecure: true); in* ports and value fields like optUrl/optDownloadDir/optNofBranches always take Custom()/Message().
• func is a literal string (NOT JS()).
• Common runtime props also take raw values: delayBefore: 2, delayAfter: 0.5, continueOnError: true.
• ES5-only inside func: no =>, no template literals, no const/let, no destructuring. No require() / fs / Buffer / process (pure JS sandbox).
• Loops: Label → ForEach → body → GoTo. Stop is standalone, wired via f.edge() on ForEach port 1.
• GoTo/Label are not only for loops: a long wire is a GoTo. Any edge that would travel back, or across other rows to reach a shared or late-declared node (an error handler, a common "say why" responder, a rejoin after a branch), draws a diagonal over everything in between - once per branch - and the canvas becomes unreadable. Put a Core.Flow.Label beside the target, and end each far branch with a Core.Flow.GoTo sitting in its own row. A GoTo has no outgoing wire, so the long edge stops existing rather than being redrawn shorter. Rule of thumb: more than about two rows of travel, make it a GoTo, and name it after where it goes so the row still reads left to right. A chain too long for one row is the same case: end the row with a GoTo and start the next one with a Label, never a wire running back across the canvas. See ./docs/patterns/branches.md; for row wraps and where a multi-port node's targets go, ./docs/patterns/comments-and-layout.md.
• Library projects use library.create(id, name, fn) with Begin/End nodes (no .start()). Inline subflows use subflow.create(name, fn).
• Every flow ends with .start(). Every flow has a Core.Flow.Stop node that the path from the trigger reaches — except two kinds of flow that never stop: an app backend (a flow triggered by Robomotion.Apps.Action is a long-lived service behind a Robomotion App's screens; each path ends at App Respond; see the building-app skill), and a chat flow (a flow triggered by Robomotion.ChatAssistant.ChatIn answers message after message; each turn ends at Chat Out; see ./docs/patterns/conversational-chat.md and, for guided mode, ./docs/patterns/guided-chat.md). Neither has a Stop or an End. robomotion validate warns only when a flow has no Stop at all (Chat In and App Action flows excepted); a Stop the trigger's path never reaches validates clean — check the wiring yourself.
• Core.* packages (Core.Trigger, Core.Browser, Core.Programming, Core.CSV, Core.Flow, Core.Vault, Core.Net, Core.Excel, …) are embedded in the robot — NEVER call f.addDependency('Core.*', …). The Designer auto-loads them. Only call f.addDependency(ns, ver) for non-Core.* packages. When updating an existing flow, NEVER bump existing addDependency versions; only add missing ones.
• Comments & canvas layout — Core.Flow.Comment nodes (with an optText markdown string) title the flow and fence its logical phases; the visual arrangement — node positions, comment box colors/sizes, and Sugiyama-style layering — lives in main.designer.ts. Layout is cosmetic (never affects runtime) but it's what makes a flow readable. See ./docs/patterns/comments-and-layout.md.

Full grammar: ./docs/sdk-grammar.md. Architecture: ./docs/architecture.md.

Diagnostic map

Map an error symptom to the doc that fixes it. When robomotion validate fails, look up the symptom here before reading the full failure trace.

Symptom	Likely cause	Fix
[SDK] Invalid node ID '<x>' in f.node('<x>', …)	Semantic / non-hex ID	./docs/reference/id-format.md — pick 6-hex
[SDK] Invalid subflow filename '<x>.ts'	Subflow filename non-hex	Rename file + update parent SubFlow node ID to match
version must be concrete; 'latest' and empty are not allowed	f.addDependency(ns, 'latest')	robomotion describe package <ns> → pin a real version
package '<ns>' not found in repository	Hallucinated namespace	robomotion get packages <kw> → use the real namespace
version '<v>' is not published for <ns>	Wrong version pinned	Pick from available_versions returned by validator
Cannot chain from node (outputs=0)	.then() after Debug/Log/Stop/GoTo/End	Wire TO terminals via f.edge(), never FROM them
the Flow Designer cannot read it (an import, a spread, a helper, a value "not a const declared in this file")	The file is a program, not a declaration (hard rule 6)	Inline: one @robomotion/sdk import, nodes written in the callback, same-file consts, no spreads. ./docs/reference/project-format.md
several statements on one line / a whole block on one line / the same block opens N Function nodes	Code not written for a person, or a helper library pasted into the steps (hard rule 7)	Format it (one statement per line, blocks on their own lines); SQL into the SQL node with {{{field}}}; one Function per rule; formatting on the screen. ./docs/reference/function-nodes.md
Invalid input port 0. Node has 0 input(s) on a Label	Wired into Core.Flow.Label (Label has 0 inputs in some pspecs)	Use Core.Flow.GoTo with optNodes.ids: [<labelId>] to jump to the Label
Vault has to be selected at runtime	Missing optCredentials on Core.Vault.GetItem	./docs/patterns/credentials.md
Property 'optCredentials' requires vault credentials but has empty/placeholder values	An OPTIONAL credential prop (e.g. Core.Excel.Open for password-protected files) set with _/blank placeholders	Omit optCredentials entirely unless you have a real vault reference — ./docs/patterns/credentials.md
inSelectorType invalid value 'xpath' (allowed: xpath:position, css)	Wrote inSelectorType: 'xpath' — not a valid enum value	For XPath just OMIT inSelectorType (it's the default); the XPath enum literal is xpath:position, never xpath. CSS ⇒ inSelectorType: 'css'. ./docs/patterns/browser.md
inLabel property not found on GoTo	Wrong property	optNodes: { ids: [...], type: 'goto', all: false }
Core.Programming.If not found	Node doesn't exist	Core.Programming.Function with outputs: 2 (./docs/patterns/conditions.md)
Wrong node name (e.g. Core.CSV.Read, Browser.Click)	Common naming mistake	./docs/reference/node-naming.md
inPath: Custom('$Home$/file') literal not resolved	System variables only resolve in Function nodes	global.get('$Home$') + '/file' (./docs/reference/system-variables.md)
Flow VALIDATES but FAILS TO LOAD on robot (flow_error: failed / Config parse error, no nodes run)	An opt* value shape mismatches its per-node type: a plain number/bool/enum field wrapped in Custom(), OR a variableType/object field left as a bare literal	Check robomotion describe node <type> per node. Enums/bools are plain (optBrowser: 'chrome'). Numeric fields depend on the node: OpenLink.optTimeout: 32 (plain number) vs WaitElement.optTimeout: Custom('30') (variableType:Integer). in* ports + optUrl/optDownloadDir/optNofBranches always take Custom()/Message().
Any CSV / Excel / Sheets / SQLite / Pandas / Airtable / DOMParser / DataTable node in scope	Custom data shape is wrong (e.g. {header: [...]}, rows as arrays)	MANDATORY read ./docs/patterns/data-tables.md — the format is {columns: [...], rows: [{key: value}]} with row keys matching column names
Write produces empty cells / ErrFilePath / "table not recognized"	header instead of columns, or rows are arrays not objects	./docs/patterns/data-tables.md — the property is columns, never header; rows are objects keyed by column name, never positional arrays

Drift-prone reminders before every Write / Edit of flow code:

• Never output TypeScript as chat text — always use Write / Edit. Plans and explanations stay in chat.
• Hex IDs from the start. Cross-references (optNodes.ids, Catch.optNodes.ids, subflow filenames) must use the same hex.
• For image flows (Robomotion.ImageAutomation.* - a Remote Desktop / Citrix session, a legacy app nothing else can see into): explore the live screen first with Skill(exploring-image) (mcp__image__* after ToolSearch warmup) and build from its recorded sequence; read ./docs/patterns/image.md. Never draw a template or guess coordinates: the recorded templates were verified unique on the screen. image: IMG_X is the identifier of a const written by image_write_templates - never a string, never pasted base64. deltaX/Y, booleans and enums are plain; in* ports and optConfidence/optWaitTimeout take Custom().
• For Java desktop flows (Robomotion.JavaAutomation.*, a Swing/AWT app): explore the live app first with Skill(exploring-java) (mcp__java__* after ToolSearch warmup) and build from its recorded sequence; read ./docs/patterns/java.md. Never guess a Window Title or Full Path: the recorded ones were verified against the running app. Key slots inMod1..3, enums and optTimeout are plain values; in* ports take Custom().
• For browser flows: explore the live page first (Skill(exploring-browser) or mcp__browser__* after ToolSearch warmup). Don't guess selectors. Core.Browser.* element nodes (ClickElement/TypeText/GetValue/SetValue/WaitElement/Select) default inSelector to XPath — translate CSS handles you find (#email, input[type="email"]) to XPath (//input[@id='email']) and omit inSelectorType; use a CSS string ONLY with inSelectorType: 'css' (plain literal — inSelectorType is an enum, so NEVER Custom('css')). A CSS string with the default engine fails at runtime with "element not found". Never write inSelectorType: 'xpath' (invalid; the value is xpath:position). Also: enum/dropdown opts (optBrowser, optProxy, optProxyAuth, optClickType) take a PLAIN string/boolean — NEVER Custom(); wrapping an enum in Custom() emits a {name,scope} object and the robot rejects the node at load with Config parse error (flow never starts). Custom()/Message() are only for variable value fields (selectors/URLs/text/paths). See ./docs/patterns/browser.md.
• For Windows desktop apps (Notepad, Excel's UI, an ERP client, any Robomotion.WindowsAutomation.* node): explore the live app first (Skill(exploring-windows) or mcp__windows__* after ToolSearch warmup) and build from the recorded sequence — its selectors were verified against the app. Never write desktop selectors from guesses or screenshots. Programs start with Core.Process.StartProcess + optBackground: true (without it the node waits for the app to exit). optWaitTimeout / optTimeout / optIndex and enums are plain values; in* and optText take Custom() / Message(). See ./docs/patterns/windows.md.
• For any flow that READS or WRITES tabular data (CSV / Excel / Google Sheets / Excel 365 / SQLite / Airtable / Pandas / DataTable / DOMParser) — read ./docs/patterns/data-tables.md BEFORE adding the node, both for the Function that builds the table AND for the reader/writer node. That doc names the exact node and shows its properties (e.g. write CSV = Core.CSV.WriteCSV with inFilePath + inTable; write Sheets = Robomotion.GoogleSheets.SetRange; etc.) and the {columns: [...], rows: [{key: value}]} format (never {header: ...}, never rows-as-arrays). Do NOT robomotion search for data-output nodes — search returns TEMPLATES, not nodes, and looping on it wastes the turn. The node names are in data-tables.md; once you know the node, use robomotion describe node <type> for its exact properties. When a search returns templates instead of the node you need, stop searching and read the relevant pattern doc.
• For any Robomotion.ChatAssistant flow in conversational mode — read ./docs/patterns/conversational-chat.md BEFORE writing it. One user message is one ChatIn → ChatOut run and ChatOut is the only thing that unlocks the composer, so a branch that ends anywhere else (an error, a missing ChatOut) freezes the chat until the page is reloaded — the most common bug in these flows, and it looks like a product fault rather than a flow fault. That doc also carries the streaming wiring (Callback In stream_delta → Streaming Text, and no Text node repeating the answer) and the attachments wiring (GetAttachments, because msg.payload.files is names and versions, never files on disk).
• For a Robomotion.ChatAssistant flow in guided mode (questions the flow asks one after another: Textbox, ButtonGroup, Checkbox, …) — read ./docs/patterns/guided-chat.md BEFORE writing it. Fixed options are [{ scope: 'Custom', name: { label: '…' } }] (a shape describe node shows only as array and validate does not check), and every outResult is an object: read msg.<x>.value.
• Validate BEFORE save — robomotion validate first; a git push stores whatever is in the folder, broken or not.

Pattern reference

Read these docs before writing the corresponding code:

Pattern	Doc
Loops (Label → ForEach → body → GoTo)	./docs/patterns/loops.md
Conditions (Function with outputs: N)	./docs/patterns/conditions.md
Credentials (vault + categories)	./docs/patterns/credentials.md
Browser automation (incl. proxy)	./docs/patterns/browser.md
Remote Desktop / Citrix / screens by their pixels (Robomotion.ImageAutomation) — explore with exploring-image first	./docs/patterns/image.md
Java desktop apps (Swing / AWT, Robomotion.JavaAutomation) — explore with exploring-java first	./docs/patterns/java.md
Windows desktop automation (Robomotion.WindowsAutomation: selectors, nodes, converting an exploring-windows recording)	./docs/patterns/windows.md
Exception handling (Catch, continueOnError)	./docs/patterns/exceptions.md
Branches & parallel (ForkBranch, WaitGroup)	./docs/patterns/branches.md
Subflows (Begin/End, multi-output)	./docs/patterns/subflows.md
Data tables (CSV / Excel / Sheets / SQLite / Pandas / Airtable / DOMParser / DataTable) — MANDATORY before writing any code that produces or consumes msg.table	./docs/patterns/data-tables.md
Captcha solving	./docs/patterns/captcha.md
Migrating a legacy Robomotion.Assistant flow → Robomotion.ChatAssistant	./docs/patterns/assistant-migration.md
Conversational Chat Assistant (turn contract, Stop, streaming, attachments) — MANDATORY before writing any conversational-mode chat flow	./docs/patterns/conversational-chat.md
Guided Chat Assistant (question widgets, fixed options, outResult.value, asking again, error path) — MANDATORY before writing any guided-mode chat flow	./docs/patterns/guided-chat.md
Comments, grouping & Sugiyama layout (title box, colored phase headers + description text, box sizing, long wires as GoTo/Label, multi-port fan-out, main.designer.ts)	./docs/patterns/comments-and-layout.md

References:

Topic	Doc
Imports (every scope helper + example)	./docs/reference/imports.md
Node ID format (the hex rule)	./docs/reference/id-format.md
The project format both the Designer and the CLI can read and save (hard rule 6)	./docs/reference/project-format.md
Function nodes: glue code written only where necessary, formatted for a person; where each urge belongs (hard rule 7)	./docs/reference/function-nodes.md
System variables ($Home$, $TempDir$)	./docs/reference/system-variables.md
Node naming (wrong → correct)	./docs/reference/node-naming.md
Credential categories (field layouts)	./docs/reference/credential-categories.md

For schemas, examples, and package docs, use the robomotion CLI (it's already on PATH, call it by bare name):

Need	Command
Cross-source fuzzy/semantic search	robomotion search <query>
Find packages	robomotion get packages [query]
Find nodes	robomotion get nodes [query] [--in <ns>]
Find templates	robomotion get templates [query] [--category <name>] [--tag <name>]
Full node schema + docs + example	robomotion describe node <type>[,<type>...]
Package info (incl. published versions)	robomotion describe package <namespace>
Template source	robomotion describe template <slug>
Package docs (llms.txt)	robomotion docs <namespace> [--grep <pattern>]
List vaults / vault items	robomotion get vaults · robomotion get vault-items <vault-id>
List robots	robomotion get robots

Public templates repo: github.com/robomotionio/robomotion-templates is the canonical source. Prefer cloning/forking a matching template over building from scratch.

Workflow

Full step-by-step: ./docs/workflow.md. Outline:

0a. The project. A flow is a folder: main.ts at its root, a git checkout of the flow's own repository, signed in. When there is none yet, make it, in the folder the person wants it under:

robomotion create flow "<short human name>"

It makes the folder (a slug of the name, or --dir <path>), signs it in when it is not (a code and a link the person approves in their browser; run it in the background, it waits for the approval; --workspace <host> when they named one), creates the flow on the server and checks it out there. Then cd into it. An existing checkout (a git clone from the flow's Home card) needs nothing; if robomotion auth whoami says not logged in, robomotion auth login --workspace <host> in it. 0. Gather requirements (interactive only) — credentials (commit to a vault-item pick from robomotion get vaults / robomotion get vault-items <vault-id>, don't quiz the user; never ask for the secret itself — ask them to add it to Vault first: ./docs/patterns/credentials.md), URLs, files, iteration, error handling.

1. Discover — robomotion search, robomotion get nodes, robomotion docs <namespace> for every non-Core.* package (when a package has no llms.txt, robomotion describe package <ns> and describe node).
2. Plan — output plan as chat text, then ask "Build it, or change the plan?" with your own question tool (or in plain chat).
3. Write — read 1-2 relevant ./docs/patterns/*.md, verify property names with robomotion describe node, then Write main.ts (and any subflows/<id>.ts). For browser flows: explore live first.
4. Validate — robomotion validate in the flow folder. Pspec-checks AND dependency-checks. MUST pass BEFORE save.
5. Save — git add -A && git commit -m "..." && git push from inside the flow dir (the checkout robomotion create flow made pushes with no setup; commit main.designer.ts with main.ts). This ends the job unless the person asked for a run too. Report success — do NOT chain into running the flow on your own. Running is a separate user request handled by the running-flow skill; when a run there finds a bug and you fix it, validate and save again.
6. When the request includes running it ("build it, run it, and save it when it works"): build → validate → run (running-flow: robomotion run runs the folder as it is, nothing needs saving first) → fix until the run is green → save, after the green run. A Chat In flow is run by running-chat-assistant instead, whose loop pushes before every chat (in a flow checkout that push is the save). Without that ask: build → validate → save, and stop.

If invoked in direct mode ("Write main.ts for X", "Generate a flow that does Y"), skip 0-2 and jump to 3.

Inside the Designer's Build with AI, the same steps are tools: validate_flow for step 4, save_flow for step 5 (git is refused there), get_node_schema for describe node, and AskUserQuestion (with its vault_picker) for questions. In a terminal, use the commands above.

Browser caveat: if code changed after the initial exploration (different selectors, new actions), re-verify selectors against the live page before saving. Selectors are owned by Step 3, not a post-save step. And close the exploration browser the moment exploring ends - whichever tool opened it (robomotion-browser-mcp, a Playwright MCP) - before writing the flow; never leave it open while the flow is built or run. The robot opens its own.

Canonical example (simple chain)

For loop / conditional / subflow / catch examples, see the corresponding pattern docs — they have richer working snippets.

import { flow, Message, Custom, JS, Global, Flow, Credential, AI } from '@robomotion/sdk';

flow.create('<flow-id>', 'Simple Flow', (f) => {
  f.node('42ec21', 'Core.Trigger.Inject', 'Start', {})
    .then('7dbafc', 'Core.Programming.Function', 'Setup', {
      func: `msg.url = 'https://example.com';

return msg;`
    })
    .then('a06926', 'Core.Browser.Open', 'Open Browser', {
      outBrowserId: Message('browser_id')
    })
    .then('8e1c4b', 'Core.Browser.OpenLink', 'Navigate', {
      inBrowserId: Message('browser_id'),
      inUrl: Message('url'),
      outPageId: Message('page_id')
    })
    .then('d52f73', 'Core.Browser.Close', 'Close', {
      inBrowserId: Message('browser_id')
    })
    .then('b9a841', 'Core.Flow.Stop', 'Stop', {});
}).start();

CLI & MCP

• robomotion — self-sufficient CLI. Builds, validates, runs, searches, inspects. robomotion help for the full verb list.
• robomotion-browser-mcp — MCP server for interactive browser exploration (used by exploring-browser and mcp__browser__* tools).
• robomotion-image-mcp — MCP server for screens seen only as pixels: Remote Desktop, Citrix, legacy apps (used by exploring-image and mcp__image__* tools; Windows).
• robomotion-java-mcp — MCP server for Java desktop applications through the Java Access Bridge (used by exploring-java and mcp__java__* tools; Windows).
• robomotion-windows-mcp — Windows only: MCP server for interactive desktop app exploration (used by exploring-windows and mcp__windows__* tools).

The robomotion CLI shells out to robomotion-sdk-mcp internally for search-backed commands and calls api.robomotion.io directly for run/stop/vault/robot operations. No additional MCP servers required.

Regression suite

For people editing this skill: an automated eval suite lives in the agent-skills repository (github.com/robomotionio/agent-skills, skills/creating-flow/evals/) — Tier A pinpoint regressions (handcrafted fixtures, one rule each) plus Tier B integration tests (live main.ts from the public robomotion-templates repo). robomotion skills install does not install it. In a checkout of that repo, run bun run skills/creating-flow/evals/run-evals.ts from the root before committing edits to this SKILL.md or the ./docs/ files; its README.md covers adding new cases and the assertion grammar.

Related skills

• validating-flow — schema validation
• testing-flow — behavioral tests
• running-flow — execute on robot
• running-chat-assistant — run and test a Chat Assistant flow (Chat In) as an Agent in the real chat page
• searching-packages — find packages, nodes, templates
• exploring-browser — interactive browser automation
• exploring-image — explore a Remote Desktop / Citrix / legacy screen by its pixels and record verified Image Automation steps
• exploring-java — explore a Java (Swing/AWT) desktop app and record verified Java Automation steps
• exploring-windows — interactive Windows desktop app automation
• reversing-network — convert a browser flow to HTTP after capturing traffic