Warp vs iTerm2

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round to Warp
   Warp✓fullprobed9/10

   Warp publishes a dedicated llms.txt (confirmed live via HTTP 200 probe at docs.warp.dev/llms.txt) describing its agentic docs, plus a whole family of agent-oriented doc pages under the _llms-txt/ path (code, warp-agent-cli, automation-platform, api-reference, knowledge-and-collaboration, factories), giving AI agents a structured, machine-readable entry point into Warp's documentation. Missing for 10: no independent/community confirmation that an external agent has actually consumed this llms.txt successfully.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.warp.dev/llms.txt # Warp > Documentation for Warp, the agentic development environment. Covers the…”
   • [claimed-docs] “Warp comes with a native code editor designed for quick, in-flow edits alongside your Agent conversations... with essentials like syntax hig…”
   • [claimed-docs] “Because it’s a regular command-line program, it works in any terminal emulator, including over SSH.”
   • [claimed-docs] “Cloud agents are autonomous, background agents that run on Warp’s cloud infrastructure or your own, triggered by system events, schedules, o…”
   • [claimed-docs] “open the run transcript; inspect the prompt, plan, commands, logs, and output; and share the session link with teammates for review.”
   • [claimed-docs] “API Keys - Create and manage API keys to authenticate the Oz CLI without human interaction, ideal for CI pipelines, headless servers, and co…”
   • [claimed-docs] “The Admin Panel gives team administrators centralized control over organization-wide Warp settings, including agent autonomy, privacy contro…”
   • [claimed-docs] “A software factory takes in requests (bug reports, feature specs, support escalations), and a coordinated fleet of agents works them into a …”

   proof ↗⚑ flag

   iTerm2—none0/10

   Probes explicitly show no llms.txt or machine-readable/agent-oriented docs endpoint exists (404s), and no other evidence indicates agent-oriented documentation formats are offered.

   • [probe] “PROBE llms.txt: HTTP 404 at https://iterm2.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://iterm2.com/documentation.html.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://iterm2.com/openapi.json, https://iterm2.com/swagger.json, https://iterm2.com/api/openapi.jso…”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round to Warp
   Warp✓fullclaimed8/10

   Warp ships the Oz CLI explicitly documented for running/managing cloud agents 'from any terminal, script, or CI pipeline,' with API keys for headless/non-interactive auth 'ideal for CI pipelines, headless servers, and containers,' plus the standalone Warp Agent CLI that works over SSH/any terminal without the desktop app. Schedules and webhook/event triggers further support automation use cases outside interactive sessions. Missing for 10: independent/hands-on verification of actual CI pipeline runs and more detail on exit codes/output parsing for scripting.

   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline.”
   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline. Use it to start …”
   • [claimed-docs] “With the Oz CLI, you can: Run agents locally for development and debugging, Run agents on remote machines, Connect agents to MCP servers lik…”
   • [claimed-docs] “API Keys - Create and manage API keys to authenticate the Oz CLI without human interaction, ideal for CI pipelines, headless servers, and co…”
   • [claimed-docs] “Because it’s a regular command-line program, it works in any terminal emulator, including over SSH.”
   • [claimed-docs] “The Warp Agent CLI lets you switch directories while in an agent session, and even run agents on remote machines without installing remote b…”
   • [claimed-docs] “Triggers: React to events from Slack, Linear, GitHub, or custom webhooks”
   • [claimed-docs] “Schedules: Run recurring tasks like dependency updates or dead code removal”
   • [claimed-docs] “Cloud agents are autonomous, background agents that run on Warp’s cloud infrastructure or your own, triggered by system events, schedules, o…”

   proof ↗⚑ flag

   iTerm2—none0/10

   The axis applies to terminal emulators as a kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/terminals-na-harmonize.ts.)

   ⚑ flag

3. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round to Warp
   Warp✓fullclaimed9/10

   Warp has documented, first-party support for connecting MCP servers to extend its agents ('MCP servers extend Warp's local agents... acting as plugins for Warp'), plus explicit CLI support (Oz CLI) to 'connect MCP servers like GitHub and Linear' and agent profiles to control MCP server usage. This is corroborated across multiple doc pages describing MCP as a first-class integration point for tool use. Missing for 10: independent/hands-on community confirmation of MCP server usage specifically (community evidence covers other topics, not MCP directly).

   • [claimed-docs] “Connect Warp AI to any tool via the Model Context Protocol. Pull context from databases, APIs, docs, and internal services so the AI underst…”
   • [claimed-docs] “MCP servers extend Warp’s local agents in a modular, flexible way by exposing custom tools or data sources through a standardized interface …”
   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline. Use it to start …”
   • [claimed-docs] “With the Oz CLI, you can: Run agents locally for development and debugging, Run agents on remote machines, Connect agents to MCP servers lik…”
   • [claimed-docs] “Agent Profiles - Use agent profiles to control what the agent can access, how it behaves, and where it can act, including file access, comma…”

   proof ↗⚑ flag

   iTerm2—none0/10

   iTerm2 has an AI chat plugin and Python scripting API, but no evidence anywhere in the pack of MCP server integration or ability to plug in MCP tools. This is a plausible axis for a terminal with AI features, but absent evidence it defaults to none.

   ⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round to Warp
   Warp✓fullclaimed8/10

   Warp ships multiple official CLIs — the standalone Warp Agent CLI usable in any terminal/SSH (warp-docs-23, warp-docs-41, warp-docs-59, warp-docs-69) and the Oz CLI for managing cloud agents in scripts/CI (warp-docs-22, warp-docs-37, warp-docs-52) — both extensively documented as first-party, agent-native tooling with API key auth for headless use (warp-docs-63). Missing for 10: independent/hands-on community corroboration specifically validating the CLI's real-world reliability (community evidence covers the desktop app, not the CLI).

   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline.”
   • [claimed-docs] “The Warp Agent CLI lets you switch directories while in an agent session, and even run agents on remote machines without installing remote b…”
   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline. Use it to start …”
   • [claimed-docs] “The Warp Agent is now available as a standalone CLI that you can use anywhere – Ghostty, iTerm 2, VS Code, built-in Windows and Mac Terminal…”
   • [claimed-docs] “With the Oz CLI, you can: Run agents locally for development and debugging, Run agents on remote machines, Connect agents to MCP servers lik…”
   • [claimed-docs] “Because it’s a regular command-line program, it works in any terminal emulator, including over SSH.”
   • [claimed-docs] “API Keys - Create and manage API keys to authenticate the Oz CLI without human interaction, ideal for CI pipelines, headless servers, and co…”
   • [claimed-docs] “It creates and maintains its own pseudoterminal (PTY), which lets you and the agent execute commands and interact with running processes thr…”

   proof ↗⚑ flag

   iTerm2~partialprobed4/10

   iTerm2 ships official automation surfaces — a Python scripting API and AppleScript support (iterm2-docs-13, iterm2-docs-14, iterm2-gh-15) — and community reports mention bundled command-line utilities like imgcat and it2dl for scripting terminal interactions (iterm2-comm-5, iterm2-comm-6), which could serve AI-native/agentic automation. However none of this constitutes a dedicated, documented 'official CLI' tool designed for agentic/AI-native control (e.g., no `iterm2` command-line binary with subcommands is described), and probes for machine-readable API docs (llms.txt, openapi.json) all 404 (iterm2-probe-1, iterm2-probe-3). Missing for 10: a first-party CLI binary/tool explicitly documented for scripting/automation, official docs framing it for AI-agent use, and independent confirmation of CLI-driven agentic workflows.

   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”
   • [claimed-docs] “iTerm2 has sophisticated AppleScript support allowing one to write stand-alone scripts to launch the application and open multiple sessions …”
   • [github] “Python Scripting API - Full automation and customization via Python. Create custom status bar components, triggers, menu items, or entirely …”
   • [community] “"imgcat: you can view images without leaving your terminal. Somehow this works even across SSH connections… Python scripting API: basically …”
   • [community] “"Along with imgcat there's it2dl. Downloads a file from the remote system browser-style. It's much more convenient than scp, especially when…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://iterm2.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://iterm2.com/openapi.json, https://iterm2.com/swagger.json, https://iterm2.com/api/openapi.jso…”

   proof ↗⚑ flag

5. ai-native userDrive the product through a documented public API

   weight 3 · round drawn
   Warp✓fullprobed8/10

   Warp explicitly advertises an 'API, CLI, SDK and MCP' platform (warp-docs-42), and a live probe confirms a real OpenAPI spec is served at docs.warp.dev/openapi.json (warp-probe-2), backed by a documented CLI reference (warp-probe-3) and API-key based headless auth for the Oz CLI (warp-docs-63) plus scriptable agent control (warp-docs-22, warp-docs-37, warp-docs-52). Missing for 10: independent/third-party corroboration of API usage and more detailed public API reference content beyond the openapi.json existence check.

   • [claimed-docs] “API, CLI, SDK and MCP built as a platform, not a vertical product or AI teammate.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.warp.dev/openapi.json — contains "openapi" key”
   • [probe] “official CLI documented at https://docs.warp.dev/reference/cli”
   • [claimed-docs] “API Keys - Create and manage API keys to authenticate the Oz CLI without human interaction, ideal for CI pipelines, headless servers, and co…”
   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline.”
   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline. Use it to start …”
   • [claimed-docs] “With the Oz CLI, you can: Run agents locally for development and debugging, Run agents on remote machines, Connect agents to MCP servers lik…”

   proof ↗⚑ flag

   iTerm2✓fullprobed8/10

   iTerm2 documents a full Python API (iterm2 package) for scripting/controlling the app, plus AppleScript support, both with dedicated documentation pages and community corroboration of hands-on use (imgcat, it2dl, Python scripting praised as far superior to AppleScript). This constitutes a documented public API for programmatic/agentic control, though it's not a modern REST/OpenAPI-style API and no llms.txt/OpenAPI spec exists. Missing for 10: a formal OpenAPI/REST-style spec or llms.txt discoverability layer, and no evidence of AI-agent-specific SDK usage beyond scripting.

   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”
   • [claimed-docs] “iTerm2 has sophisticated AppleScript support allowing one to write stand-alone scripts to launch the application and open multiple sessions …”
   • [claimed-docs] “iTerm2 has sophisticated AppleScript support allowing one to write stand-alone scripts to launch the application and open multiple sessions …”
   • [github] “Python Scripting API - Full automation and customization via Python. Create custom status bar components, triggers, menu items, or entirely …”
   • [community] “"imgcat: you can view images without leaving your terminal. Somehow this works even across SSH connections… Python scripting API: basically …”
   • [probe] “PROBE llms.txt: HTTP 404 at https://iterm2.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://iterm2.com/openapi.json, https://iterm2.com/swagger.json, https://iterm2.com/api/openapi.jso…”

   proof ↗⚑ flag

6. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round to Warp
   Warp~partialclaimed6/10

   Warp's docs describe API Keys for authenticating the Oz CLI headlessly (warp-docs-63) and Agent Profiles that constrain what an agent can access (file access, command execution, MCP server usage) plus admin-level controls over agent autonomy (warp-docs-64, warp-docs-66), which together approximate least-privilege scoping for agent credentials/access. However, there's no explicit documentation of per-credential scopes/permissions tied to individual API keys (e.g., read-only vs write, resource-level restrictions) or independent confirmation this works as a formal least-privilege credential system. Missing for 10: explicit scoped-permission API key documentation, examples of granular credential scoping, and independent/hands-on verification.

   • [claimed-docs] “API Keys - Create and manage API keys to authenticate the Oz CLI without human interaction, ideal for CI pipelines, headless servers, and co…”
   • [claimed-docs] “Agent Profiles - Use agent profiles to control what the agent can access, how it behaves, and where it can act, including file access, comma…”
   • [claimed-docs] “The Admin Panel gives team administrators centralized control over organization-wide Warp settings, including agent autonomy, privacy contro…”

   proof ↗⚑ flag

   iTerm2—none0/10

   iTerm2 has a Python scripting API and an optional AI plugin, but there is no evidence of any mechanism for issuing scoped or least-privilege API credentials for agents; no auth/permission-scoping model is documented, and openapi/API-key probes return 404.

   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”
   • [claimed-docs] “This is an optional component you can install to enable generative AI features in iTerm2.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://iterm2.com/openapi.json, https://iterm2.com/swagger.json, https://iterm2.com/api/openapi.jso…”

   proof ↗⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round to iTerm2
   Warp~partialprobed3/10

   Warp markets itself as 'API, CLI, SDK and MCP built as a platform' (warp-docs-42) and a live OpenAPI spec is confirmed (warp-probe-2), showing some real API surface, but there is no dedicated SDK documentation, language-specific client libraries, install instructions, or code samples anywhere in the evidence. missing for 10: dedicated SDK docs/reference, language bindings (e.g. Python/JS packages), code samples, versioning/changelog for an SDK.

   • [claimed-docs] “API, CLI, SDK and MCP built as a platform, not a vertical product or AI teammate.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.warp.dev/openapi.json — contains "openapi" key”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.warp.dev/llms.txt # Warp > Documentation for Warp, the agentic development environment. Covers the…”

   proof ↗⚑ flag

   iTerm2~partialprobed6/10

   iTerm2 ships an official, documented Python API for scripting and automating the terminal (create triggers, status bar components, menu items, full control), which an AI-native builder could use to construct agentic integrations, and this is corroborated by community praise for the API's flexibility. However, there's no dedicated 'AI SDK' or agent-specific developer kit — the AI feature (docs-15) is a plugin/toggle for chat, not an SDK — and probes show no llms.txt, machine-readable docs, or OpenAPI spec. Missing for 10: AI/agent-specific SDK or API, multi-language SDK support, official developer docs/examples framed around AI-agent integration.

   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”
   • [github] “Python Scripting API - Full automation and customization via Python. Create custom status bar components, triggers, menu items, or entirely …”
   • [community] “"imgcat: you can view images without leaving your terminal. Somehow this works even across SSH connections… Python scripting API: basically …”
   • [claimed-docs] “This is an optional component you can install to enable generative AI features in iTerm2.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://iterm2.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://iterm2.com/openapi.json, https://iterm2.com/swagger.json, https://iterm2.com/api/openapi.jso…”

   proof ↗⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round to Warp
   Warp~partialclaimed4/10

   Warp's automation platform docs mention 'Triggers: React to events from Slack, Linear, GitHub, or custom webhooks' and cloud agents 'triggered by... integrations like Slack and GitHub,' indicating webhook-based triggering exists, but this describes Warp consuming/reacting to inbound webhooks to kick off agents rather than a documented outbound webhook subscription mechanism for external systems to receive Warp's own events. Missing for 10: explicit documentation of an outbound webhook/event-subscription API, payload schema, or delivery guarantees, and independent confirmation of this feature working.

   • [claimed-docs] “Triggers: React to events from Slack, Linear, GitHub, or custom webhooks”
   • [claimed-docs] “Cloud agents are autonomous, background agents that run on Warp’s cloud infrastructure or your own, triggered by system events, schedules, o…”

   proof ↗⚑ flag

   iTerm2—none0/10

   No evidence of any webhook subscription mechanism; iTerm2 offers triggers and a Python scripting API for local automation but nothing about outbound webhook events or subscriptions is documented.

   ⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to Warp
   Warp✓fullclaimed8/10

   Warp provides extensive AI-generated insights and suggestions inline: AI command suggestions via '#', error explanation via 'Ask Warp AI', agent-driven code writing/debugging/multi-step task execution, and context-aware suggestions pulled via MCP integrations from databases/APIs/docs. This is well documented across multiple first-party sources. missing for 10: independent/hands-on corroboration specifically validating the quality or accuracy of the AI insights/suggestions (community evidence focuses on terminal stability/privacy issues, not on insight quality).

   • [claimed-docs] “Describe what you want to build and let Warp's built‑in agent handle the rest — writing code, running commands, and iterating until the task…”
   • [claimed-docs] “Connect Warp AI to any tool via the Model Context Protocol. Pull context from databases, APIs, docs, and internal services so the AI underst…”
   • [claimed-docs] “Type '#' on your command line and start describing the command you want to run using natural language. Warp will load AI Command Suggestions…”
   • [claimed-docs] “Right‑click and 'Ask Warp AI' to explain any error in your command output.”
   • [claimed-docs] “Write and refactor code across your codebase * Debug issues and fix errors * Run commands and interpret results * Plan and execute mul…”
   • [claimed-docs] “Generate (Legacy) turns natural language queries into precise terminal commands or contextual suggestions inside interactive CLI tools. Type…”
   • [claimed-docs] “Right‑click and 'Ask Warp AI' to explain any error in your command output. Warp AI can demystify opaque error messages and identify missing …”

   proof ↗⚑ flag

   iTerm2~partialcommunity6/10

   iTerm2 ships an optional AI plugin providing a built-in LLM chat window that can be linked to sessions for context-aware help, command suggestions, and annotated explanations of terminal output (iterm2-docs-15, iterm2-gh-6), directly matching the 'AI-generated insights from data inside the product' story. However, the feature is opt-in, requires a user-supplied OpenAI key, and community reports noted the enable/disable toggle behaved unexpectedly (any text, even a stray space, activated data-sending), raising real caveats about robustness/trust rather than core functionality. Missing for 10: deeper first-party documentation of the AI feature's capabilities/limits, independent hands-on validation of insight quality, and confirmation the toggle bug was fully resolved.

   • [claimed-docs] “This is an optional component you can install to enable generative AI features in iTerm2.”
   • [github] “Built-in LLM chat window that can optionally interact with terminal contents. Link sessions to get context-aware help, run commands on your …”
   • [community] “Users reported that iTerm2's new AI feature wasn't a true disabled toggle: "Put anything in the box for the OpenAI key, valid or not, and th…”
   • [community] “Some users called the backlash overblown: "a feature that is inactive by default, consumes no processing power, memory or anything else" sti…”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round to Warp
   Warp✓fullclaimed8/10

   Warp's Automation Platform explicitly supports cloud agents that run autonomously in the background, triggered by schedules, webhooks, or integrations like Slack/GitHub/Linear (warp-docs-4, warp-docs-5, warp-docs-60), with observability/audit trails (warp-docs-53, warp-docs-61) and CLI/API control via Oz CLI for headless/CI use (warp-docs-22, warp-docs-37, warp-docs-63). missing for 10: independent/hands-on verification of autonomous background runs actually completing unattended, and more detail on failure handling/reliability at scale.

   • [claimed-docs] “Triggers: React to events from Slack, Linear, GitHub, or custom webhooks”
   • [claimed-docs] “Schedules: Run recurring tasks like dependency updates or dead code removal”
   • [claimed-docs] “Cloud agents are autonomous, background agents that run on Warp’s cloud infrastructure or your own, triggered by system events, schedules, o…”
   • [claimed-docs] “open the run transcript; inspect the prompt, plan, commands, logs, and output; and share the session link with teammates for review.”
   • [claimed-docs] “Observability: Every run is tracked, auditable, and shareable with your team”
   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline.”
   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline. Use it to start …”
   • [claimed-docs] “API Keys - Create and manage API keys to authenticate the Oz CLI without human interaction, ideal for CI pipelines, headless servers, and co…”
   • [claimed-docs] “With the Oz CLI, you can: Run agents locally for development and debugging, Run agents on remote machines, Connect agents to MCP servers lik…”

   proof ↗⚑ flag

   iTerm2~partialcommunity5/10

   iTerm2 supports regex-based Triggers that autonomously fire actions (highlighting, running commands, notifications, invoking Python scripts) when patterns appear, and offers a full Python scripting API for background automation and custom features [iterm2-docs-16, iterm2-gh-2, iterm2-docs-13, iterm2-gh-15]. This provides generic background automation but isn't framed around AI-agent workflows specifically. missing for 10: evidence of AI-driven or agentic automations running unattended, scheduling/cron-like persistent background tasks tied to AI features, and independent confirmation that these automations run reliably without user oversight.

   • [claimed-docs] “iTerm2 supports user-defined triggers, which are actions that run when text matching a regular expression is received.”
   • [github] “Triggers - Regex patterns that fire actions when matched: highlight text, run commands, send notifications, open password manager, set marks…”
   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”
   • [github] “Python Scripting API - Full automation and customization via Python. Create custom status bar components, triggers, menu items, or entirely …”
   • [community] “"imgcat: you can view images without leaving your terminal. Somehow this works even across SSH connections… Python scripting API: basically …”

   proof ↗⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round to Warp
   Warp✓fullcommunity9/10

   Warp ships a built-in AI agent that writes code, runs commands, iterates on tasks, handles multi-turn conversations, supports model switching, and integrates with natural-language command generation—well documented across first-party docs (warp-docs-6, warp-docs-8, warp-docs-44, warp-docs-13, warp-docs-14). This is corroborated by community mentions of AI-generated commands being a standout feature (warp-comm-8). Missing for 10: independent hands-on validation specifically of the built-in agent's task completion quality (most community commentary focuses on terminal UX/telemetry rather than the assistant's task delegation itself).

   • [claimed-docs] “Describe what you want to build and let Warp's built‑in agent handle the rest — writing code, running commands, and iterating until the task…”
   • [claimed-docs] “Type '#' on your command line and start describing the command you want to run using natural language. Warp will load AI Command Suggestions…”
   • [claimed-docs] “Write and refactor code across your codebase * Debug issues and fix errors * Run commands and interpret results * Plan and execute mul…”
   • [claimed-docs] “By default, if you ask an AI query immediately after interacting in Agent Mode, your query is sent as a **follow-up** to the current convers…”
   • [claimed-docs] “Conversations are tied to sessions and you can run multiple Agent Mode conversations simultaneously in different windows, tabs, or panes.”
   • [claimed-docs] “Warp supports Claude Sonnet and Opus, GPT, and Gemini Pro — and adds new models as they launch. Pick the model that fits your task, or let W…”
   • [community] “Warp is great - I use it as my daily terminal. The best features are being able to edit commands, chunking the output into blocks and AI gen…”

   proof ↗⚑ flag

   iTerm2~partialcommunity6/10

   iTerm2 ships an optional AI plugin providing a built-in LLM chat window that can read terminal context, run commands on the user's behalf, and explain output (iterm2-docs-15, iterm2-gh-6), which matches the story of delegating tasks to an in-app assistant. However, it's an opt-in add-on requiring the user's own API key rather than a fully integrated default assistant, and community reports flagged a bug where the 'disabled' toggle didn't actually stop data being sent (iterm2-comm-2), raising real trust/reliability caveats. Missing for 10: first-party documentation of task-delegation scope/limits, independent hands-on validation that the assistant reliably executes delegated actions, and confirmation the toggle issue was resolved.

   • [claimed-docs] “This is an optional component you can install to enable generative AI features in iTerm2.”
   • [github] “Built-in LLM chat window that can optionally interact with terminal contents. Link sessions to get context-aware help, run commands on your …”
   • [community] “"It takes much less effort for me to simply switch back to Terminal.app." (reacting to iTerm2 adding an opt-in OpenAI-based AI feature)”
   • [community] “Users reported that iTerm2's new AI feature wasn't a true disabled toggle: "Put anything in the box for the OpenAI key, valid or not, and th…”
   • [community] “Some users called the backlash overblown: "a feature that is inactive by default, consumes no processing power, memory or anything else" sti…”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round to Warp
   Warp✓fullclaimed8/10

   Warp offers extensive natural-language interfaces: typing '#' for AI command suggestions, Agent Mode conversations for multi-step tasks, right-click 'Ask Warp AI' to explain errors, and a built-in agent that writes code, runs commands, and iterates based on natural-language descriptions. This spans terminal, CLI, and cloud agent surfaces (warp-docs-6,8,9,44,54). missing for 10: independent hands-on validation specifically of NL command accuracy/reliability (community evidence focuses on general product issues rather than NL-command quality).

   • [claimed-docs] “Describe what you want to build and let Warp's built‑in agent handle the rest — writing code, running commands, and iterating until the task…”
   • [claimed-docs] “Type '#' on your command line and start describing the command you want to run using natural language. Warp will load AI Command Suggestions…”
   • [claimed-docs] “Right‑click and 'Ask Warp AI' to explain any error in your command output.”
   • [claimed-docs] “Write and refactor code across your codebase * Debug issues and fix errors * Run commands and interpret results * Plan and execute mul…”
   • [claimed-docs] “Generate (Legacy) turns natural language queries into precise terminal commands or contextual suggestions inside interactive CLI tools. Type…”
   • [claimed-docs] “Terminal and Agent modes: Switch between a clean terminal for commands and a dedicated conversation view for multi-turn agent workflows.”
   • [claimed-docs] “By default, if you ask an AI query immediately after interacting in Agent Mode, your query is sent as a **follow-up** to the current convers…”

   proof ↗⚑ flag

   iTerm2~partialcommunity6/10

   iTerm2 ships an optional AI plugin/LLM chat window that can be linked to terminal sessions to provide context-aware help, explain output, and run commands on the user's behalf based on natural-language input (iterm2-docs-15, iterm2-gh-6). This is a genuine but optional, opt-in add-on requiring configuration (e.g., an OpenAI key) rather than a fully native, always-on NL interface, and community discussion flagged an early bug where the 'disabled' toggle didn't fully prevent data transmission (iterm2-comm-2), raising trust caveats without contradicting the core NL-command capability. Missing for 10: first-party documentation detailing the range/reliability of natural-language commands it can execute, independent hands-on reports confirming accurate command execution, and confirmation the toggle bug was fully resolved.

   • [claimed-docs] “This is an optional component you can install to enable generative AI features in iTerm2.”
   • [github] “Built-in LLM chat window that can optionally interact with terminal contents. Link sessions to get context-aware help, run commands on your …”
   • [community] “Users reported that iTerm2's new AI feature wasn't a true disabled toggle: "Put anything in the box for the OpenAI key, valid or not, and th…”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round drawn
   Warp—none0/10

   Warp does expose an OpenAPI spec (warp-probe-2) and API/CLI reference docs (warp-docs-63, warp-probe-3), so the axis of an API reference applies given Warp's platform ambitions (warp-docs-42). However, there is no evidence of an interactive reference UI with runnable/'try it out' examples — the pack only shows a raw openapi.json file and static CLI reference pages, not an interactive explorer.

   • [probe] “PROBE openapi: HTTP 200 at https://docs.warp.dev/openapi.json — contains "openapi" key”
   • [probe] “official CLI documented at https://docs.warp.dev/reference/cli”
   • [claimed-docs] “API Keys - Create and manage API keys to authenticate the Oz CLI without human interaction, ideal for CI pipelines, headless servers, and co…”
   • [claimed-docs] “API, CLI, SDK and MCP built as a platform, not a vertical product or AI teammate.”

   proof ↗⚑ flag

   iTerm2—none0/10

   iTerm2 does have a Python scripting API (iterm2-docs-13) so this axis is plausible, but there's no evidence of an interactive API reference with runnable examples—probes confirm no OpenAPI/swagger docs, no llms.txt, and no docs-as-markdown endpoint, and no community or docs evidence describes an interactive/executable API playground.

   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://iterm2.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://iterm2.com/documentation.html.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://iterm2.com/openapi.json, https://iterm2.com/swagger.json, https://iterm2.com/api/openapi.jso…”

   proof ↗⚑ flag

2. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round to Warp
   Warp✓fullprobed8/10

   A probe directly confirms an OpenAPI JSON spec is served at docs.warp.dev/openapi.json returning a valid 'openapi' key, and docs reference an API/CLI/SDK/MCP platform with API key management, corroborating a machine-readable spec exists. Missing for 10: no independent/third-party confirmation of spec completeness or versioning, and no docs page walking through consuming the spec.

   • [probe] “PROBE openapi: HTTP 200 at https://docs.warp.dev/openapi.json — contains "openapi" key”
   • [claimed-docs] “API, CLI, SDK and MCP built as a platform, not a vertical product or AI teammate.”
   • [claimed-docs] “API Keys - Create and manage API keys to authenticate the Oz CLI without human interaction, ideal for CI pipelines, headless servers, and co…”

   proof ↗⚑ flag

   iTerm2—none0/10

   iTerm2 offers a Python scripting API but no evidence of a downloadable OpenAPI/machine-readable API spec; explicit probes for llms.txt, docs-md, and openapi.json all returned 404.

   • [probe] “PROBE llms.txt: HTTP 404 at https://iterm2.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://iterm2.com/documentation.html.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://iterm2.com/openapi.json, https://iterm2.com/swagger.json, https://iterm2.com/api/openapi.jso…”
   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”

   proof ↗⚑ flag

3. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Warp—none0/10

   Warp exposes an API, CLI, SDK, and MCP platform (warp-docs-42, warp-probe-2 openapi.json), so API versioning is a fair axis, but no evidence pack item documents API version numbers, a changelog, or any formal deprecation policy for these interfaces.

   • [claimed-docs] “API, CLI, SDK and MCP built as a platform, not a vertical product or AI teammate.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.warp.dev/openapi.json — contains "openapi" key”
   • [probe] “official CLI documented at https://docs.warp.dev/reference/cli”

   proof ↗⚑ flag

   iTerm2—none0/10

   There is no evidence of a versioned API contract or documented deprecation policy; the Python API docs exist but no version/deprecation policy is mentioned, and probes for API discovery artifacts (llms.txt, openapi.json) all 404.

   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://iterm2.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://iterm2.com/documentation.html.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://iterm2.com/openapi.json, https://iterm2.com/swagger.json, https://iterm2.com/api/openapi.jso…”

   proof ↗⚑ flag

Ai agent

1. ai-native userDelegate terminal tasks to a built-in AI agent that plans and executes commands with my approval

   weight 3 · round to Warp
   Warp✓fullcommunity9/10

   Warp's built-in Agent Mode is extensively documented to plan and execute multi-step terminal tasks (writing code, running commands, controlling interactive/full-screen apps, iterating) while keeping the user in the loop via conversation view, follow-ups, and approval/steering ('watch, steer, and hand off runs'). This is corroborated across many first-party docs and independent community mentions of using it as a daily driver for AI-assisted terminal work, though some hands-on complaints exist about unrelated reliability/telemetry issues rather than the core delegate-and-approve workflow itself. Missing for 10: independent hands-on verification specifically of the approval/plan-then-execute step (vs. general agent usage), and confirmation the community complaints don't touch this exact workflow.

   • [claimed-docs] “Describe what you want to build and let Warp's built‑in agent handle the rest — writing code, running commands, and iterating until the task…”
   • [claimed-docs] “Write and refactor code across your codebase * Debug issues and fix errors * Run commands and interpret results * Plan and execute mul…”
   • [claimed-docs] “the Warp Agent can now run and control long-running or full-screen terminal applications. The agent can provide input when prompted, navigat…”
   • [claimed-docs] “By default, if you ask an AI query immediately after interacting in Agent Mode, your query is sent as a **follow-up** to the current convers…”
   • [claimed-docs] “Conversations are tied to sessions and you can run multiple Agent Mode conversations simultaneously in different windows, tabs, or panes.”
   • [claimed-docs] “any surface — watch, steer, and hand off runs from web, mobile, terminal, or IDE.”
   • [community] “Warp is great - I use it as my daily terminal. The best features are being able to edit commands, chunking the output into blocks and AI gen…”
   • [community] “My daily driver for a few months now, even after trying Rio/Ghostty/Wezterm... Favorite feature is the notification when a long running comm…”

   proof ↗⚑ flag

   iTerm2~partialcommunity5/10

   iTerm2 ships an optional AI plugin providing a built-in LLM chat that can be linked to a session to give context-aware help, explain output, and 'run commands on your behalf' (iterm2-docs-15, iterm2-gh-6), which is a real but thin form of AI-agent delegation. However, there's no documented explicit plan-then-approve workflow (e.g., showing a command and requiring confirmation before execution), and community reports raise concerns that the AI toggle's off/on state was ambiguous, undermining confidence in a clean approval gate (iterm2-comm-1, iterm2-comm-2). Missing for 10: documented step-by-step approval/confirmation UI before command execution, evidence of autonomous multi-step planning, and independent hands-on validation that the agent respects user approval before running commands.

   • [claimed-docs] “This is an optional component you can install to enable generative AI features in iTerm2.”
   • [github] “Built-in LLM chat window that can optionally interact with terminal contents. Link sessions to get context-aware help, run commands on your …”
   • [community] “"It takes much less effort for me to simply switch back to Terminal.app." (reacting to iTerm2 adding an opt-in OpenAI-based AI feature)”
   • [community] “Users reported that iTerm2's new AI feature wasn't a true disabled toggle: "Put anything in the box for the OpenAI key, valid or not, and th…”

   proof ↗⚑ flag

Ai commands

1. ai-native userGet AI explanations and suggested fixes when a command fails

   weight 2 · round to Warp
   Warp✓fullclaimed8/10

   Warp explicitly documents right-clicking to 'Ask Warp AI' to explain error output and identify missing dependencies, plus '#' natural-language command suggestions and AI-driven debugging as core Agent capabilities. Missing for 10: independent/hands-on verification that error explanations are accurate or reliably surfaced (community evidence focuses on other issues, not this feature specifically).

   • [claimed-docs] “Right‑click and 'Ask Warp AI' to explain any error in your command output.”
   • [claimed-docs] “Right‑click and 'Ask Warp AI' to explain any error in your command output. Warp AI can demystify opaque error messages and identify missing …”
   • [claimed-docs] “Write and refactor code across your codebase * Debug issues and fix errors * Run commands and interpret results * Plan and execute mul…”
   • [claimed-docs] “Type '#' on your command line and start describing the command you want to run using natural language. Warp will load AI Command Suggestions…”

   proof ↗⚑ flag

   iTerm2~partialclaimed5/10

   iTerm2 ships an optional AI plugin with a built-in LLM chat window that can link to a session, view terminal contents, and 'explain output with annotations' or run commands on your behalf, which is generic AI assistance but not documented as a specific 'command failed → suggested fix' workflow. missing for 10: explicit documentation of automatic failure detection, error-specific explanations, and suggested command fixes; independent hands-on evidence of this exact use case working.

   • [claimed-docs] “This is an optional component you can install to enable generative AI features in iTerm2.”
   • [github] “Built-in LLM chat window that can optionally interact with terminal contents. Link sessions to get context-aware help, run commands on your …”

   proof ↗⚑ flag

2. ai-native userType natural language and get the right shell command generated in place

   weight 2 · round to Warp
   Warp✓fullclaimed9/10

   Warp explicitly documents typing '#' plus natural language to get AI Command Suggestions generated in place in the command line (warp-docs-8, warp-docs-54), with real-time suggestion loading and even contextual suggestions inside interactive CLI tools. This is corroborated by multiple docs pages describing the same 'Generate' feature. Missing for 10: no independent/hands-on community confirmation specifically of this in-place suggestion feature (community evidence focuses on other AI/terminal issues, not this specific flow).

   • [claimed-docs] “Type '#' on your command line and start describing the command you want to run using natural language. Warp will load AI Command Suggestions…”
   • [claimed-docs] “Generate (Legacy) turns natural language queries into precise terminal commands or contextual suggestions inside interactive CLI tools. Type…”
   • [claimed-docs] “Right‑click and 'Ask Warp AI' to explain any error in your command output. Warp AI can demystify opaque error messages and identify missing …”

   proof ↗⚑ flag

   iTerm2~partialcommunity5/10

   iTerm2 ships an optional AI plugin and a built-in LLM chat window that can be linked to a session to 'run commands on your behalf' or explain output (iterm2-docs-15, iterm2-gh-6), which supports natural-language-to-command generation, but this is a separate opt-in chat pane requiring an API key rather than inline generation directly at the shell prompt. Community commentary focuses on privacy/toggle concerns (iterm2-comm-1, iterm2-comm-2) rather than confirming accuracy or in-place command insertion. Missing for 10: evidence of commands being generated and inserted directly into the terminal prompt (not just a chat window), and independent verification of command-generation quality/reliability.

   • [claimed-docs] “This is an optional component you can install to enable generative AI features in iTerm2.”
   • [github] “Built-in LLM chat window that can optionally interact with terminal contents. Link sessions to get context-aware help, run commands on your …”
   • [community] “"It takes much less effort for me to simply switch back to Terminal.app." (reacting to iTerm2 adding an opt-in OpenAI-based AI feature)”
   • [community] “Users reported that iTerm2's new AI feature wasn't a true disabled toggle: "Put anything in the box for the OpenAI key, valid or not, and th…”

   proof ↗⚑ flag

Ai privacy

1. ai-native userUse or fully disable AI features with clear control over what session data leaves my machine, without a forced login

   weight 2 · round to iTerm2
   Warp!disputedcontradicted4/10

   Warp docs promise granular control (secret redaction, no training use, telemetry opt-out on paid plans, ZDR for Business/Enterprise) and note telemetry can be monitored/disabled, but this is undercut by concrete community reports: one HN thread describes Warp silently sending terminal session data to LLMs via 'Prompt Suggestions'/'Next Command' without explicit consent (warp-comm-1), and multiple independent users report being confronted with a mandatory login prompt and uninstalling immediately (warp-comm-5, warp-comm-6, warp-comm-16), even though a Warp co-founder claims the login requirement was removed (warp-comm-7). Docs also admit telemetry must stay on to use AI on the Free plan (warp-docs-33), meaning full AI use without any data leaving isn't unconditional. missing for 10: a documented explicit toggle to fully disable AI without any account/login step on the free tier, and resolution of the community claim of undisclosed data transmission.

   • [claimed-docs] “Warp does not allow OpenAI or Anthropic to use your data for model training. Our "hands off" approach also means your terminal input and out…”
   • [claimed-docs] “Monitor telemetry in real-time with Warp’s native Network Log. Opt out of telemetry at any time”
   • [claimed-docs] “Telemetry must be enabled to use AI features on the Free plan, while paid plans can opt out at any time and continue using Warp, including A…”
   • [claimed-docs] “Business and Enterprise plans are covered by our Zero Data Retention (ZDR) agreement. No AI interaction or console data is ever collected.”
   • [claimed-docs] “Read a complete list of all the telemetry events that get sent for app analytics ... Opt out of telemetry at any time”
   • [claimed-docs] “Warp unconditionally applies Secret Redaction in all AI interactions to ensure that any sensitive data is _never_ collected or sent to third…”
   • [community] “Warp silently sends terminal session data to LLMs via 'Prompt Suggestions' and 'Next Command' features without explicit consent, discovered …”
   • [community] “I tried Warp once... it showed me a login prompt. Perhaps I mistakenly downloaded a login prompt app instead of a terminal app? I promptly u…”
   • [community] “I remember seeing this terminal emulator, deciding to give it a shot, and being asked to sign in. I have never uninstalled a program faster …”
   • [community] “Warp co-founder: fair criticism, and this is the reason we removed the login requirement... the point of the login is that we have features …”
   • [community] “They have also innovated by requiring login (into a console!!)... Today they have heaps of telemetry, so a privacy nightmare. This is a term…”

   proof ↗⚑ flag

   iTerm2!disputedcontradicted5/10

   iTerm2 ships AI chat as an optional, install-only plugin with no forced login (iterm2-docs-15, iterm2-gh-6), suggesting users can ignore or avoid it entirely. However, hands-on community reports concretely contradict 'clear control': a user found that merely putting any text (even a stray space) in the API key field silently activates data-sending to OpenAI, with no reliable way to see the feature is actually disabled (iterm2-comm-2), and another reacted by switching terminals entirely over trust concerns (iterm2-comm-1). Missing for 10: no documentation on exactly what session data leaves the machine when AI chat is enabled, no fix/acknowledgment of the toggle bug, and no independent verification that the issue was resolved.

   • [claimed-docs] “This is an optional component you can install to enable generative AI features in iTerm2.”
   • [github] “Built-in LLM chat window that can optionally interact with terminal contents. Link sessions to get context-aware help, run commands on your …”
   • [community] “"It takes much less effort for me to simply switch back to Terminal.app." (reacting to iTerm2 adding an opt-in OpenAI-based AI feature)”
   • [community] “Users reported that iTerm2's new AI feature wasn't a true disabled toggle: "Put anything in the box for the OpenAI key, valid or not, and th…”
   • [community] “Some users called the backlash overblown: "a feature that is inactive by default, consumes no processing power, memory or anything else" sti…”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Warp
   Warp~partialclaimed6/10

   Warp supports running many agents concurrently across repos/tasks (warp-docs-28), cloud agents triggered by schedules/webhooks at scale (warp-docs-4, warp-docs-5, warp-docs-60), and a 'software factory' pattern coordinating a fleet of agents into mergeable PRs (warp-docs-68), which together support bulk/parallel operations across many items. However, there is no explicit documentation of a UI or command for batch-selecting many items (files, repos, tasks) and applying one operation across all of them in a single bulk action, nor independent/hands-on evidence confirming this scales well in practice. missing for 10: concrete bulk-selection/batch-apply UI or command, first-party docs quantifying scale limits, independent verification that parallel/bulk agent runs work reliably at scale.

   • [claimed-docs] “Parallelism: Run many agents concurrently across repos or tasks”
   • [claimed-docs] “Cloud agents are autonomous, background agents that run on Warp’s cloud infrastructure or your own, triggered by system events, schedules, o…”
   • [claimed-docs] “A software factory takes in requests (bug reports, feature specs, support escalations), and a coordinated fleet of agents works them into a …”
   • [claimed-docs] “Triggers: React to events from Slack, Linear, GitHub, or custom webhooks”
   • [claimed-docs] “Schedules: Run recurring tasks like dependency updates or dead code removal”
   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline.”

   proof ↗⚑ flag

   iTerm2~partialclaimed5/10

   iTerm2 exposes a Python scripting API and AppleScript that can programmatically iterate over sessions/tabs, and Global Search lets users search across all tabs at once, which together imply some bulk-automation capability. However, there is no direct evidence of a dedicated bulk-operation feature (e.g., broadcast-to-all-panes) or hands-on proof that AI-driven bulk actions across many items actually work reliably. Missing for 10: explicit bulk-command/broadcast feature documentation, concrete examples of Python API performing multi-session bulk operations, independent confirmation of scale/performance.

   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”
   • [github] “Python Scripting API - Full automation and customization via Python. Create custom status bar components, triggers, menu items, or entirely …”
   • [claimed-docs] “Search all your tabs at once with Global Search.”
   • [claimed-docs] “iTerm2 has sophisticated AppleScript support allowing one to write stand-alone scripts to launch the application and open multiple sessions …”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round drawn
   Warp✓fullclaimed8/10

   Warp's Automation Platform explicitly supports Triggers reacting to events from Slack, Linear, GitHub, or custom webhooks, plus Schedules for recurring tasks, and cloud agents described as 'triggered by system events, schedules, or integrations like Slack and GitHub' with full observability/audit trails. This directly matches the story of defining rules that trigger automatic actions on events. Missing for 10: independent/hands-on verification of the trigger system in practice (community evidence focuses on core terminal/agent issues, not the automation/trigger feature specifically).

   • [claimed-docs] “Triggers: React to events from Slack, Linear, GitHub, or custom webhooks”
   • [claimed-docs] “Schedules: Run recurring tasks like dependency updates or dead code removal”
   • [claimed-docs] “Cloud agents are autonomous, background agents that run on Warp’s cloud infrastructure or your own, triggered by system events, schedules, o…”
   • [claimed-docs] “open the run transcript; inspect the prompt, plan, commands, logs, and output; and share the session link with teammates for review.”
   • [claimed-docs] “Observability: Every run is tracked, auditable, and shareable with your team”

   proof ↗⚑ flag

   iTerm2✓fullclaimed8/10

   iTerm2 supports user-defined Triggers that fire on regex matches from terminal output, enabling automatic actions like highlighting, running commands, sending notifications, invoking Python scripts, or opening a password manager — a documented rules-on-event automation system, further extensible via the Python API for custom triggers/behaviors. missing for 10: no independent hands-on validation of complex trigger chains, and no evidence of AI-specific event-triggering beyond generic regex triggers.

   • [claimed-docs] “iTerm2 supports user-defined triggers, which are actions that run when text matching a regular expression is received.”
   • [github] “Triggers - Regex patterns that fire actions when matched: highlight text, run commands, send notifications, open password manager, set marks…”
   • [github] “Python Scripting API - Full automation and customization via Python. Create custom status bar components, triggers, menu items, or entirely …”
   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round to Warp
   Warp✓fullclaimed8/10

   Warp documents explicit 'Schedules' functionality for cloud agents ('Run recurring tasks like dependency updates or dead code removal') alongside 'Triggers' for event-based automation, plus cloud agents described as 'triggered by system events, schedules, or integrations' and managed via the Oz CLI for scripting/CI. This directly matches the story of scheduling recurring jobs/workflows. Missing for 10: independent/hands-on confirmation of the scheduling feature working reliably, and more detail on scheduling configuration (cron-like syntax, frequency options).

   • [claimed-docs] “Triggers: React to events from Slack, Linear, GitHub, or custom webhooks”
   • [claimed-docs] “Schedules: Run recurring tasks like dependency updates or dead code removal”
   • [claimed-docs] “Cloud agents are autonomous, background agents that run on Warp’s cloud infrastructure or your own, triggered by system events, schedules, o…”
   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline.”
   • [claimed-docs] “With the Oz CLI, you can: Run agents locally for development and debugging, Run agents on remote machines, Connect agents to MCP servers lik…”

   proof ↗⚑ flag

   iTerm2—none0/10

   iTerm2 offers triggers, Python scripting API, and AppleScript automation, but there is no evidence of a scheduler or mechanism for recurring/cron-like jobs or workflows; automation is event-triggered or manually scripted, not scheduled.

   ⚑ flag

4. ai-native userVersion, review, and roll back my automations

   weight 1 · round to Warp
   Warp~partialclaimed4/10

   Warp provides strong review/observability for automations (run transcripts showing prompt, plan, commands, logs, shareable for team review) and lets you save/share workflows via Warp Drive, but there is no documented versioning or rollback mechanism for automations (e.g., no version history, diffing, or revert capability for schedules/triggers/workflows). missing for 10: explicit version history for saved automations, ability to roll back to a prior automation version, changelog/diff view for automation edits.

   • [claimed-docs] “Warp lets you save your most important workflows in Warp Drive so you can run them on‑demand or share with your team.”
   • [claimed-docs] “Observability: Every run is tracked, auditable, and shareable with your team”
   • [claimed-docs] “open the run transcript; inspect the prompt, plan, commands, logs, and output; and share the session link with teammates for review.”
   • [claimed-docs] “Warp lets you save your most important workflows in Warp Drive so you can run them on‑demand or share with your team. Let Warp AI handle the…”
   • [claimed-docs] “Cloud agents are autonomous, background agents that run on Warp’s cloud infrastructure or your own, triggered by system events, schedules, o…”

   proof ↗⚑ flag

   iTerm2—none0/10

   No evidence of any version control, review, or rollback mechanism for automations (triggers, Python scripts, profiles). iTerm2 supports scripting and triggers, but nothing in the evidence pack shows versioning, diffing, review workflows, or rollback of these automations.

   ⚑ flag

Dotfiles

1. power-userKeep the terminal's full configuration as plain-text files in my dotfiles and sync it across machines

   weight 3 · round to Warp
   Warp~partialclaimed4/10

   Warp's open-source announcement mentions shipping a new settings file explicitly for 'programmatic control over settings and easy portability between devices' (warp-docs-40), which speaks directly to the dotfiles/sync use case, but this is a single passing mention with no documentation of its format, scope, or actual dotfiles-style workflow. Other config-adjacent features (theme OS-sync, session restoration) are separate app-state features, not plain-text portable config. Missing for 10: dedicated docs on the settings file format/location, confirmation it covers full app config (keybindings, workflows, themes), and independent/community corroboration of dotfiles-style syncing across machines.

   • [claimed-docs] “we are shipping a (long-overdue) settings file so that users and agents get programmatic control over settings and easy portability between …”
   • [claimed-docs] “Warp supports synchronizing your theme with the OS’s light and dark themes.”
   • [claimed-docs] “Restore your windows, tabs, panes, and recent Blocks automatically when you relaunch Warp.”

   proof ↗⚑ flag

   iTerm2—none0/10

   The evidence pack contains no mention of iTerm2's preferences file format, exporting/importing settings as plain-text/plist files, or any dotfiles-style sync workflow across machines. Without evidence for this specific capability, it cannot be credited even though it is a plausible axis for a terminal emulator.

   ⚑ flag

Fonts

1. developerUse programming fonts with ligatures, fallback fonts, and fine-grained font tuning

   weight 2 · round drawn
   Warp—none0/10

   No evidence in the pack mentions font configuration, ligatures, fallback fonts, or font tuning of any kind; documentation focuses on themes, appearance sync, and agent features, not typography settings.

   ⚑ flag

   iTerm2—none0/10

   The evidence pack contains no mention of font rendering, ligature support, fallback fonts, or font-tuning settings anywhere in iTerm2's docs, GitHub feature list, or community discussion; only general 'mind-boggling number of options' and color-mode claims are present, which don't address fonts specifically. Missing for 10: any mention of font selection, ligature support, fallback font configuration, or font-size/spacing tuning options.

   ⚑ flag

Theming

1. power-userApply color schemes and themes, including automatic light/dark mode switching

   weight 2 · round to Warp
   Warp✓fullclaimed8/10

   Warp's docs explicitly support custom themes, auto-generating themes from a background image, and syncing theme with OS light/dark mode (warp-docs-19, warp-docs-20), directly matching the story. Missing for 10: independent/community corroboration of theming reliability and more detail on breadth of built-in theme palette.

   • [claimed-docs] “Automatically create new themes based on a background image.”
   • [claimed-docs] “Warp supports synchronizing your theme with the OS’s light and dark themes.”

   proof ↗⚑ flag

   iTerm2—none0/10

   The evidence pack contains no mention of color schemes, themes, or automatic light/dark mode switching for iTerm2 despite this being a plausible and well-known capability for a terminal emulator; no docs, GitHub, or community citations address theming at all. missing for 10: any documentation or mention of color scheme/theme support, dark mode toggling, or automatic OS appearance syncing.

   ⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round drawn
   Warp~partialprobed6/10

   Warp explicitly positions itself as 'API, CLI, SDK and MCP built as a platform,' with the Oz CLI enabling agent creation, monitoring, MCP connections, and authentication without the desktop app, and a live OpenAPI spec — showing substantial API/CLI parity for agent workflows. But the story demands full UI-equivalent capability, and evidence doesn't confirm parity for many UI-only features (theming, session restoration, conversation UI, code editor) nor is there independent verification that the API surface is fully complete. missing for 10: independent confirmation of full feature parity, evidence that UI-specific features (themes, editor, session restore) are also API-accessible

   • [claimed-docs] “API, CLI, SDK and MCP built as a platform, not a vertical product or AI teammate.”
   • [claimed-docs] “any surface — watch, steer, and hand off runs from web, mobile, terminal, or IDE.”
   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline.”
   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline. Use it to start …”
   • [claimed-docs] “With the Oz CLI, you can: Run agents locally for development and debugging, Run agents on remote machines, Connect agents to MCP servers lik…”
   • [claimed-docs] “API Keys - Create and manage API keys to authenticate the Oz CLI without human interaction, ideal for CI pipelines, headless servers, and co…”
   • [claimed-docs] “Agent Profiles - Use agent profiles to control what the agent can access, how it behaves, and where it can act, including file access, comma…”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.warp.dev/openapi.json — contains "openapi" key”
   • [probe] “official CLI documented at https://docs.warp.dev/reference/cli”

   proof ↗⚑ flag

   iTerm2~partialprobed6/10

   iTerm2's Python API is documented as controlling and extending iTerm2 behavior (custom status bar, triggers, menu items, session control), and a community hands-on review calls it able to 'touch pretty much everything' via scripting, which supports broad API-driven control. However, there's no evidence of a formal claim or documentation of full UI/API parity — no explicit list mapping every UI feature (e.g. AI chat, browser profiles, tmux integration) to API equivalents, and probes show no OpenAPI spec or llms.txt for verifying coverage. Missing for 10: explicit parity documentation, API coverage for newer UI features (AI chat, browser profiles), and independent verification that all UI actions are scriptable.

   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”
   • [github] “Python Scripting API - Full automation and customization via Python. Create custom status bar components, triggers, menu items, or entirely …”
   • [community] “"imgcat: you can view images without leaving your terminal. Somehow this works even across SSH connections… Python scripting API: basically …”
   • [probe] “PROBE openapi: all candidate paths 404 (https://iterm2.com/openapi.json, https://iterm2.com/swagger.json, https://iterm2.com/api/openapi.jso…”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round to Warp
   Warp~partialclaimed3/10

   Warp documents a settings file for 'programmatic control over settings and easy portability between devices' and open-sources its client code, but there's no documented feature for exporting conversation history, Warp Drive workflows, or agent run data in open formats for full user data portability. missing for 10: explicit full data export tooling, open-format export of conversation/session history, Warp Drive workflow export, independent confirmation users can fully migrate away with their data.

   • [claimed-docs] “we are shipping a (long-overdue) settings file so that users and agents get programmatic control over settings and easy portability between …”
   • [claimed-docs] “Read and audit Warp’s client source code at warpdotdev/warp, open source under AGPL v3”
   • [claimed-docs] “Warp’s source code is now available at github.com/warpdotdev/warp with an AGPL license.”

   proof ↗⚑ flag

   iTerm2—none0/10

   No evidence of any data export feature or open-format export for iTerm2's own data (settings, session history, paste history, profiles); the evidence pack instead shows probes for llms.txt/openapi returning 404s and no mention of export/portability tooling. missing for 10: documented export of preferences/profiles/history in open formats, data portability guarantees, migration/export tooling.

   • [probe] “PROBE llms.txt: HTTP 404 at https://iterm2.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://iterm2.com/documentation.html.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://iterm2.com/openapi.json, https://iterm2.com/swagger.json, https://iterm2.com/api/openapi.jso…”

   proof ↗⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round to Warp
   Warp✓fullclaimed8/10

   Warp explicitly published its client source code on GitHub under the AGPL v3 open-source license, documented in both its privacy docs and a dedicated blog post announcing the move to open source. missing for 10: independent/third-party confirmation of the full scope of open-sourced code (e.g., whether cloud/server-side agent components are also included) and any hands-on community audit of the repository beyond the vendor's own announcement.

   • [claimed-docs] “Read and audit Warp’s client source code at warpdotdev/warp, open source under AGPL v3”
   • [claimed-docs] “Warp’s source code is now available at github.com/warpdotdev/warp with an AGPL license.”
   • [claimed-docs] “Read and audit Warp’s client source code at `warpdotdev/warp`, open source under AGPL v3”

   proof ↗⚑ flag

   iTerm2~partialclaimed6/10

   The evidence repeatedly cites a public GitHub repository (github.com/gnachman/iTerm2) as the canonical source for iTerm2's features, indicating the source code is publicly hosted and readable. However, none of the evidence explicitly states or links to a specific open-source license (e.g., GPL) or license file, so the 'open license' claim is not directly confirmed. Missing for 10: explicit license identification/text, documentation page confirming licensing terms, independent confirmation of license compliance.

   • [github] “Browser profiles integrate web browsing into iTerm2's window/tab/pane hierarchy. Copy mode, triggers, AI chat, and other terminal features w…”
   • [github] “Session Restoration - Sessions run in long-lived server processes. If iTerm2 crashes or upgrades, your shells keep running. When iTerm2 rest…”
   • [github] “Python Scripting API - Full automation and customization via Python. Create custom status bar components, triggers, menu items, or entirely …”

   proof ↗⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round to Warp
   Warp~partialcommunity4/10

   Warp's client is open-sourced under AGPL v3 (warpdotdev/warp) so the terminal client itself can be inspected and self-hosted/built from source, and cloud agents are described as able to run 'on Warp's cloud infrastructure or your own,' suggesting some self-hosting of agent execution. However, there's no documented path to self-host the full core product—AI model routing, backend services, and account/login (required per warp-comm-6/7) remain tied to Warp's proprietary cloud, and no deployment/on-prem guide is evidenced. Missing for 10: a documented self-hosted backend/server deployment, evidence that AI/model-routing works without Warp's cloud, and independent confirmation of a working self-hosted setup.

   • [claimed-docs] “Read and audit Warp’s client source code at warpdotdev/warp, open source under AGPL v3”
   • [claimed-docs] “Warp’s source code is now available at github.com/warpdotdev/warp with an AGPL license.”
   • [claimed-docs] “Cloud agents are autonomous, background agents that run on Warp’s cloud infrastructure or your own, triggered by system events, schedules, o…”
   • [community] “Warp co-founder: fair criticism, and this is the reason we removed the login requirement... the point of the login is that we have features …”

   proof ↗⚑ flag

   iTerm2—none0/10

   The axis applies to terminal emulators as a kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/terminals-na-harmonize.ts.)

   ⚑ flag

Multiplexing

1. developerSplit windows into panes and organize work across tabs without an external multiplexer

   weight 3 · round to iTerm2
   Warp~partialclaimed6/10

   Docs confirm panes exist alongside tabs and windows as first-class session units (agent conversations run in "windows, tabs, or panes" and session restoration recreates "windows, tabs, and panes"), showing built-in multiplexing without needing tmux. However the pack lacks any detail on pane-splitting mechanics, keyboard shortcuts, or layout management, and no independent/hands-on account discusses pane usage specifically. Missing for 10: dedicated documentation on split/pane creation and navigation, independent user confirmation of pane workflow.

   • [claimed-docs] “Conversations are tied to sessions and you can run multiple Agent Mode conversations simultaneously in different windows, tabs, or panes.”
   • [claimed-docs] “Restore your windows, tabs, panes, and recent Blocks automatically when you relaunch Warp.”
   • [claimed-docs] “Continue previous threads with follow-ups, manage conversation history, attach context from blocks and files, and run multiple conversations…”

   proof ↗⚑ flag

   iTerm2✓fullclaimed9/10

   iTerm2 natively supports splitting tabs into multiple panes (vertical/horizontal) and organizing sessions across tabs and windows, directly replacing the need for tmux/screen for basic pane-and-tab workflows, with session restoration and profile-based organization further supporting this. missing for 10: independent hands-on verification specifically of pane-splitting workflow (community evidence focuses on other features like imgcat/scripting rather than confirming multiplexing usability directly).

   • [claimed-docs] “Divide a tab up into multiple panes, each one showing a different session. You can slice vertically and horizontally”
   • [claimed-docs] “Divide a tab up into multiple panes, each one showing a different session.”
   • [github] “Session Restoration - Sessions run in long-lived server processes. If iTerm2 crashes or upgrades, your shells keep running. When iTerm2 rest…”
   • [claimed-docs] “iTerm2 provides a taggable and searchable profiles database so you can easily find the profile you're looking for.”
   • [claimed-docs] “you can define a profile that's always used when you ssh to some hostname. Or when your username is root. Or even when you're in a particula…”

   proof ↗⚑ flag

Quick access

1. power-userSummon the terminal instantly with a global hotkey or quake-style dropdown window

   weight 1 · round to iTerm2
   Warp—none0/10

   No evidence in the pack mentions a global hotkey or quake-style dropdown/instant-summon window feature; Warp's docs focus on session restoration, panes/tabs, and AI agent features, not a system-wide invocation shortcut.

   ⚑ flag

   iTerm2✓fullclaimed9/10

   Docs explicitly describe a global hotkey to bring iTerm2 to the foreground from any app, and GitHub evidence confirms a quake-style dropdown that slides down from a screen edge, even over fullscreen apps. Missing for 10: independent hands-on user testimonial specifically praising the hotkey/dropdown window feature.

   • [claimed-docs] “Register a hotkey that brings iTerm2 to the foreground when you're in another application. A terminal is always a keypress away.”
   • [claimed-docs] “Register a hotkey that brings iTerm2 to the foreground when you're in another application.”
   • [github] “System-wide hotkey summons a terminal that slides down from the top of the screen (or any edge), even over fullscreen apps.”

   proof ↗⚑ flag

Sessions

1. developerRestore my windows, tabs, and working directories after a restart or crash

   weight 2 · round drawn
   Warp✓fullclaimed8/10

   Warp's docs explicitly describe session restoration that restores windows, tabs, panes, and recent Blocks automatically on relaunch, directly matching the story. Missing for 10: independent/hands-on corroboration of restore reliability after crashes (only vendor docs cited), and no detail on working-directory restoration specifics.

   • [claimed-docs] “Restore your windows, tabs, panes, and recent Blocks automatically when you relaunch Warp.”
   • [claimed-docs] “Session restoration allows you to quickly pick up where you left off in your previous terminal session.”
   • [claimed-docs] “Sometimes, you may want to prevent a sensitive Block from being saved on your computer, or you may want to clear blocks from a machine entir…”

   proof ↗⚑ flag

   iTerm2✓fullclaimed8/10

   Session restoration via long-lived server processes reconnects shells (including working directories via shell integration) after crash/restart, and tmux -CC integration persists windows/tabs/panes even when iTerm2 or the SSH session drops. Missing for 10: no independent/hands-on confirmation of restoring exact tab/pane layout after a full app crash, only vendor/docs claims.

   • [github] “Session Restoration - Sessions run in long-lived server processes. If iTerm2 crashes or upgrades, your shells keep running. When iTerm2 rest…”
   • [github] “Sessions run in long-lived server processes. If iTerm2 crashes or upgrades, your shells keep running. When iTerm2 restarts, it reconnects to…”
   • [github] “Sessions run in long-lived server processes. If iTerm2 crashes or upgrades, your shells keep running.”
   • [claimed-docs] “When you run "tmux -CC", a new tmux session is created. An iTerm2 window opens and it acts like a normal iTerm2 window. The difference is th…”
   • [claimed-docs] “When iTerm2 quits or the ssh session is lost, tmux keeps running. You can return to the host you were ssh'ed into and run "tmux -CC attach" …”
   • [claimed-docs] “iTerm2 may be integrated with the unix shell so that it can keep track of your command history, current working directory, host name, and mo…”
   • [claimed-docs] “iTerm2 can integrate with your shell so it knows where your shell prompt is, what commands you're entering, which host you are on, and what …”

   proof ↗⚑ flag

Benchmarks

1. power-userSee published benchmarks or measured latency/throughput numbers backing the terminal's performance claims

   weight 2 · round drawn
   Warp—none0/10

   No published benchmarks, latency, or throughput figures appear anywhere in the evidence pack; documentation focuses on features and privacy, while community posts mention performance complaints but no measured numbers. missing for 10: published benchmark data, latency/throughput measurements, any comparative performance testing.

   ⚑ flag

   iTerm2—none0/10

   No evidence pack item presents published benchmarks, latency/throughput numbers, or any measured performance data for iTerm2; the material covers features (panes, tmux integration, scripting) and unrelated community discussion (AI feature controversy, a security disclosure) with no performance metrics whatsoever.

   ⚑ flag

Rendering

1. developerRely on GPU-accelerated rendering that stays fast and responsive under heavy output

   weight 3 · round drawn
   Warp—none0/10

   The evidence pack contains no first-party documentation claiming GPU-accelerated rendering or describing rendering performance under heavy output; instead, community reports describe UI glitches, broken behavior, and instability during heavy use (e.g., 'horribly broken... UI glitches', 'random failures, stopping of agents'), and one commenter notes the terminal is 'just Alacritty' with no Warp-specific performance claims. Since no vendor documentation asserts this capability, there's nothing concrete to substantiate 'full' or 'partial', and the negative community signals reinforce a 'none' verdict rather than a dispute of an explicit claim.

   • [community] “Warp is so horribly broken right now and has been for weeks. Multiple github issues on consistent issue writing file. On top of that UI glit…”
   • [community] “I've been a Pro user for several months (use < 1000 credits a month) - but I've noticed a real reduction in quality over the past month or s…”
   • [community] “Warp is a terrible product, and I have nothing nice to say about them. But look at modern terminals like Kitty or Ghostty... mouse support t…”
   • [community] “Their terminal is just Alacritty... The terminal emulator was never their selling point, the AI wrapper was.”

   proof ↗⚑ flag

   iTerm2—none0/10

   No evidence in the pack mentions GPU acceleration, rendering architecture, or performance under heavy output/scrollback; the docs and community items cover features like panes, triggers, search, and scripting but nothing about rendering performance or GPU usage.

   ⚑ flag

1. ai-native userPrevent my data from being used to train AI models

   weight 3 · round to Warp
   Warp~partialcommunity7/10

   Warp explicitly states it prohibits OpenAI/Anthropic from using terminal data to train models, and paid plans get a Zero Data Retention agreement plus telemetry opt-out; these are strong first-party privacy commitments (warp-docs-12, warp-docs-34, warp-docs-17/51). However, Free-plan users must keep telemetry enabled to use AI features (warp-docs-33), and community reports allege some AI-adjacent features silently send terminal data to LLMs without explicit consent (warp-comm-1), showing the anti-training guarantee isn't paired with full data-flow transparency for all users. Missing for 10: independent verification of the no-training claim, clarity on Free-tier data handling, and resolution of the consent complaint.

   • [claimed-docs] “Warp does not allow OpenAI or Anthropic to use your data for model training. Our "hands off" approach also means your terminal input and out…”
   • [claimed-docs] “Business and Enterprise plans are covered by our Zero Data Retention (ZDR) agreement. No AI interaction or console data is ever collected.”
   • [claimed-docs] “Monitor telemetry in real-time with Warp’s native Network Log. Opt out of telemetry at any time”
   • [claimed-docs] “Telemetry must be enabled to use AI features on the Free plan, while paid plans can opt out at any time and continue using Warp, including A…”
   • [claimed-docs] “Opt out of telemetry at any time”
   • [community] “Warp silently sends terminal session data to LLMs via 'Prompt Suggestions' and 'Next Command' features without explicit consent, discovered …”

   proof ↗⚑ flag

   iTerm2!disputedcontradicted4/10

   iTerm2's AI features are documented as optional/opt-in (an installable plugin and an LLM chat window that 'optionally' interacts with terminal contents), implying a way to keep AI features off, but hands-on community reports show the opt-in control was broken: entering any value (even a space) in the API-key field activated data-sending to OpenAI regardless of intent, meaning users could not reliably prevent their terminal data from being sent to a third-party AI provider. There is no vendor documentation addressing training-data usage or an explicit training opt-out policy at all. missing for 10: explicit training-data opt-out/privacy statement, evidence the opt-in toggle was fixed and verified reliable, independent corroboration beyond the single HN thread.

   • [claimed-docs] “This is an optional component you can install to enable generative AI features in iTerm2.”
   • [github] “Built-in LLM chat window that can optionally interact with terminal contents. Link sessions to get context-aware help, run commands on your …”
   • [community] “"It takes much less effort for me to simply switch back to Terminal.app." (reacting to iTerm2 adding an opt-in OpenAI-based AI feature)”
   • [community] “Users reported that iTerm2's new AI feature wasn't a true disabled toggle: "Put anything in the box for the OpenAI key, valid or not, and th…”
   • [community] “Some users called the backlash overblown: "a feature that is inactive by default, consumes no processing power, memory or anything else" sti…”

   proof ↗⚑ flag

2. ai-native userControl data retention and deletion

   weight 2 · round to Warp
   Warp~partialcommunity6/10

   Warp documents concrete retention/deletion controls: no OpenAI/Anthropic model training on user data, ZDR agreements for Business/Enterprise (no AI or console data collected), ability to clear/delete sensitive Blocks from a machine, secret redaction on all AI interactions, and telemetry opt-out for paid plans, plus open-source client code for audit (warp-docs-12, warp-docs-34, warp-docs-36, warp-docs-56, warp-docs-17/46/51, warp-docs-25/47). However, ZDR is limited to Business/Enterprise tiers, Free-plan users must keep telemetry on to use AI features (warp-docs-33), and community reports allege terminal/session data being sent to LLMs without explicit consent on lower tiers (warp-comm-1, warp-comm-16), undercutting full user control for non-enterprise users. missing for 10: universal (non-enterprise) ZDR/opt-out guarantees, independent verification that free/pro-tier data isn't retained, and resolution of the community consent complaints.

   • [claimed-docs] “Warp does not allow OpenAI or Anthropic to use your data for model training. Our "hands off" approach also means your terminal input and out…”
   • [claimed-docs] “Business and Enterprise plans are covered by our Zero Data Retention (ZDR) agreement. No AI interaction or console data is ever collected.”
   • [claimed-docs] “Sometimes, you may want to prevent a sensitive Block from being saved on your computer, or you may want to clear blocks from a machine entir…”
   • [claimed-docs] “Warp unconditionally applies Secret Redaction in all AI interactions to ensure that any sensitive data is _never_ collected or sent to third…”
   • [claimed-docs] “Monitor telemetry in real-time with Warp’s native Network Log. Opt out of telemetry at any time”
   • [claimed-docs] “Telemetry must be enabled to use AI features on the Free plan, while paid plans can opt out at any time and continue using Warp, including A…”
   • [claimed-docs] “Read and audit Warp’s client source code at warpdotdev/warp, open source under AGPL v3”
   • [community] “Warp silently sends terminal session data to LLMs via 'Prompt Suggestions' and 'Next Command' features without explicit consent, discovered …”
   • [community] “They have also innovated by requiring login (into a console!!)... Today they have heaps of telemetry, so a privacy nightmare. This is a term…”

   proof ↗⚑ flag

   iTerm2!disputedcontradicted3/10

   iTerm2's AI plugin is opt-in and framed as controllable (docs-15), but hands-on community reports show the 'disable' toggle for sending data to OpenAI is not reliable — any non-empty (even accidental whitespace) API key field activates data transmission, undermining claimed control over what data leaves the machine (comm-2). No documentation addresses retention windows, deletion of stored chat/AI data, or data lifecycle policies at all. missing for 10: explicit data retention/deletion settings, documentation on how long AI chat context or API data is stored, independent confirmation that the toggle issue was fixed.

   • [claimed-docs] “This is an optional component you can install to enable generative AI features in iTerm2.”
   • [community] “Users reported that iTerm2's new AI feature wasn't a true disabled toggle: "Put anything in the box for the OpenAI key, valid or not, and th…”
   • [community] “"It takes much less effort for me to simply switch back to Terminal.app." (reacting to iTerm2 adding an opt-in OpenAI-based AI feature)”
   • [community] “Some users called the backlash overblown: "a feature that is inactive by default, consumes no processing power, memory or anything else" sti…”

   proof ↗⚑ flag

3. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round to Warp
   Warp~partialcommunity7/10

   Warp's docs explicitly describe a telemetry opt-out and a Network Log to monitor telemetry in real time, and state paid plans can opt out at any time while still using AI. However, the Free plan requires telemetry to be enabled to use AI features, meaning opt-out isn't universal, and community commentary (warp-comm-1, warp-comm-16) raises concerns about undisclosed data sharing and 'heaps of telemetry,' which tempers full confidence though it doesn't concretely disprove the opt-out mechanism itself. missing for 10: independent verification that opt-out fully works with no residual telemetry, and free-tier parity for full opt-out.

   • [claimed-docs] “Monitor telemetry in real-time with Warp’s native Network Log. Opt out of telemetry at any time”
   • [claimed-docs] “Telemetry must be enabled to use AI features on the Free plan, while paid plans can opt out at any time and continue using Warp, including A…”
   • [claimed-docs] “Read a complete list of all the telemetry events that get sent for app analytics ... Opt out of telemetry at any time”
   • [claimed-docs] “Opt out of telemetry at any time”
   • [claimed-docs] “Monitor telemetry in real-time with Warp’s native Network Log * Opt out of telemetry at any time”
   • [community] “They have also innovated by requiring login (into a console!!)... Today they have heaps of telemetry, so a privacy nightmare. This is a term…”

   proof ↗⚑ flag

   iTerm2!disputedcontradicted5/10

   iTerm2's AI feature is documented as an optional, install-only component (iterm2-docs-15), implying users can opt out of any AI-related data sharing by not installing/enabling it. However, hands-on community reports directly contradict this: users found that entering any text (even a stray space) in the OpenAI API key field silently activated data-sending, meaning the feature wasn't truly opt-out/disabled as claimed [iterm2-comm-2], while other users defended the feature as inactive-by-default [iterm2-comm-3]. Missing for 10: no general telemetry/usage-tracking opt-out setting is documented at all (the evidence only covers the AI plugin's data flow to OpenAI, not broader telemetry), and no vendor response addressing the toggle bug is provided.

   • [claimed-docs] “This is an optional component you can install to enable generative AI features in iTerm2.”
   • [community] “"It takes much less effort for me to simply switch back to Terminal.app." (reacting to iTerm2 adding an opt-in OpenAI-based AI feature)”
   • [community] “Users reported that iTerm2's new AI feature wasn't a true disabled toggle: "Put anything in the box for the OpenAI key, valid or not, and th…”
   • [community] “Some users called the backlash overblown: "a feature that is inactive by default, consumes no processing power, memory or anything else" sti…”

   proof ↗⚑ flag

Graphics

1. developerDisplay inline images and rich graphics via a documented terminal graphics protocol

   weight 2 · round to iTerm2
   Warp—none0/10

   No evidence in the pack mentions a terminal graphics protocol (e.g., Sixel, Kitty graphics protocol, iTerm2 inline images) or inline image/rich graphics rendering in Warp's terminal. Evidence only covers AI agents, MCP, telemetry, themes, and session restoration.

   ⚑ flag

   iTerm2✓fullcommunity8/10

   iTerm2 documents a custom escape sequence for inline image display (including animated GIFs), and community hands-on evidence corroborates real-world use via imgcat working over SSH. missing for 10: a formal protocol specification page/name (e.g. explicit 'inline images protocol' spec doc) and broader third-party adoption/compatibility discussion beyond one HN thread.

   • [claimed-docs] “iTerm2 has a custom escape sequence to display images right in the terminal. Even animated GIFs!”
   • [community] “"imgcat: you can view images without leaving your terminal. Somehow this works even across SSH connections… Python scripting API: basically …”

   proof ↗⚑ flag

Platforms

1. developerRun the same terminal with the same config on macOS, Linux, and Windows

   weight 2 · round to Warp
   Warp~partialcommunity5/10

   Evidence shows Warp exposes platform-specific keybindings for macOS, Windows, and Linux (docs-49), a settings file enabling config portability across devices (docs-40), and CLI/agent components that work over SSH in any terminal (docs-59), implying cross-platform availability. However, there is no explicit doc confirming identical native app experience on all three OSes, and community reports describe Warp being broken specifically under WSL/Windows-via-SSH scenarios (warp-comm-10), undercutting a seamless 'same terminal, same config' experience. missing for 10: explicit first-party confirmation of feature parity across macOS/Linux/Windows, documented config-sync mechanism beyond a settings file, and independent corroboration that the same setup truly works identically on all three platforms.

   • [claimed-docs] “Open the **Conversations menu** (`⌘+Y` on macOS, `Ctrl+Shift+Y` on Windows/Linux), select a conversation, and then enter your query.”
   • [claimed-docs] “we are shipping a (long-overdue) settings file so that users and agents get programmatic control over settings and easy portability between …”
   • [claimed-docs] “Because it’s a regular command-line program, it works in any terminal emulator, including over SSH.”
   • [community] “Warp is so horribly broken right now and has been for weeks. Multiple github issues on consistent issue writing file. On top of that UI glit…”

   proof ↗⚑ flag

   iTerm2—none0/10

   iTerm2 is a macOS-only application; no evidence pack item claims Linux or Windows support, and a community source explicitly notes the lack of a comparable replacement on Windows or Linux, confirming it does not run cross-platform.

   • [community] “"I'm a little jealous of iTerm, not going to lie. The UX is pretty nice from what I've seen, but I can't find a like for like replacement fo…”
   • [claimed-docs] “iTerm2 is a replacement for Terminal and the successor to iTerm.”

   proof ↗⚑ flag

Ssh

1. developerSSH to remote hosts with the terminal's own integration carrying my terminfo, shell integration, and config along

   weight 2 · round to iTerm2
   Warp—none0/10

   Warp's docs mention running the `warp` agent CLI over SSH (warp-docs-3) but that's about launching an agent conversation, not the terminal itself carrying terminfo, shell integration, and config when SSHing into remote hosts. No evidence describes Warp's terminal propagating its shell integration/terminfo to remote hosts, and community reports (warp-comm-10, warp-comm-14) note broken functionality (file/diff explorer, code indexing) specifically over SSH connections, further indicating the core integration doesn't extend cleanly to remote sessions.

   • [claimed-docs] “Run the `warp` command to start a conversation in whichever terminal you already use, over SSH, or on a machine where Warp isn’t installed.”
   • [community] “Warp is so horribly broken right now and has been for weeks. Multiple github issues on consistent issue writing file. On top of that UI glit…”
   • [community] “Nearly everything about the experience of a terminal is better than iTerm though? Very nice having the terminal treated like a text file. It…”

   proof ↗⚑ flag

   iTerm2✓fullcommunity8/10

   iTerm2 documents shell integration explicitly designed to work 'even over ssh', tracking command history, cwd, and hostname (iterm2-docs-8, iterm2-docs-31), plus automatic profile switching keyed to SSH hostname/user (iterm2-docs-10, iterm2-docs-32) and tmux -CC integration that persists sessions across SSH drops (iterm2-docs-12, iterm2-docs-19, iterm2-docs-23). Community hands-on reports corroborate SSH-aware features working in practice, e.g. imgcat rendering images 'even across SSH connections' and it2dl for remote file downloads (iterm2-comm-5, iterm2-comm-6). Missing for 10: explicit documentation of terminfo propagation itself and independent benchmarking of config/profile carry-over reliability across varied SSH setups.

   • [claimed-docs] “iTerm2 may be integrated with the unix shell so that it can keep track of your command history, current working directory, host name, and mo…”
   • [claimed-docs] “iTerm2 can integrate with your shell so it knows where your shell prompt is, what commands you're entering, which host you are on, and what …”
   • [claimed-docs] “you can have iTerm2 switch profiles depending on what you're doing. For example, you can define a profile that's always used when you ssh to…”
   • [claimed-docs] “you can define a profile that's always used when you ssh to some hostname. Or when your username is root. Or even when you're in a particula…”
   • [claimed-docs] “When you run "tmux -CC", a new tmux session is created. An iTerm2 window opens and it acts like a normal iTerm2 window. The difference is th…”
   • [claimed-docs] “When iTerm2 quits or the ssh session is lost, tmux keeps running. You can return to the host you were ssh'ed into and run "tmux -CC attach" …”
   • [claimed-docs] “iTerm2 is integrated with tmux, allowing you to enjoy a native user interface with all the benefits of tmux's persistence.”
   • [community] “"imgcat: you can view images without leaving your terminal. Somehow this works even across SSH connections… Python scripting API: basically …”
   • [community] “"Along with imgcat there's it2dl. Downloads a file from the remote system browser-style. It's much more convenient than scp, especially when…”

   proof ↗⚑ flag

Tmux

1. developerUse tmux inside the terminal, or a documented native tmux integration/control mode

   weight 2 · round to iTerm2
   Warp—none0/10

   The evidence pack contains no mention of tmux support, tmux control mode, or any documented native tmux integration in Warp's docs or community discussion — Warp's session/pane features (blocks, session restoration) are its own proprietary system, not tmux. Since terminal emulators are a fair category for this axis, absence of evidence yields 'none'.

   ⚑ flag

   iTerm2✓fullclaimed9/10

   iTerm2 has a well-documented native tmux control mode (tmux -CC) that integrates tmux sessions natively into iTerm2's window/pane UI while preserving persistence across SSH disconnects and app restarts, plus standard tmux-in-terminal usage is naturally supported. Missing for 10: independent hands-on corroboration specifically of tmux -CC mode (community evidence covers other features, not tmux integration directly).

   • [claimed-docs] “When you run "tmux -CC", a new tmux session is created. An iTerm2 window opens and it acts like a normal iTerm2 window. The difference is th…”
   • [claimed-docs] “When iTerm2 quits or the ssh session is lost, tmux keeps running. You can return to the host you were ssh'ed into and run "tmux -CC attach" …”
   • [claimed-docs] “iTerm2 is integrated with tmux, allowing you to enjoy a native user interface with all the benefits of tmux's persistence.”
   • [claimed-docs] “iTerm2's tmux integration solves these problems... A terminal window opens and it acts like a normal iTerm2 window.”

   proof ↗⚑ flag

Agent control

1. ai-native userLet a coding agent programmatically drive the terminal itself — create panes, run commands, read output — through a documented control protocol or API

   weight 3 · round to iTerm2
   Warp~partialprobed6/10

   Warp exposes a genuine programmatic surface — an OpenAPI spec (confirmed live at docs.warp.dev/openapi.json), an Oz CLI with API keys for headless/CI control, MCP as a plugin interface, and a documented Warp Agent CLI that spins up its own PTY so an agent can run commands, provide input, and control full-screen apps (warp-docs-69, warp-docs-24, warp-docs-32). This supports agent-driven terminal automation, but the evidence never documents a protocol/API specifically for creating or managing Warp's terminal panes/windows or reading raw pane output — the API/CLI focus is on running and orchestrating agents rather than exposing the terminal UI itself as a controllable surface. Missing for 10: documented pane-creation/window-management API, explicit read-output API distinct from agent conversation transcripts, and independent/hands-on confirmation of external programmatic terminal control.

   • [claimed-docs] “API, CLI, SDK and MCP built as a platform, not a vertical product or AI teammate.”
   • [claimed-docs] “API Keys - Create and manage API keys to authenticate the Oz CLI without human interaction, ideal for CI pipelines, headless servers, and co…”
   • [claimed-docs] “With the Oz CLI, you can: Run agents locally for development and debugging, Run agents on remote machines, Connect agents to MCP servers lik…”
   • [claimed-docs] “It creates and maintains its own pseudoterminal (PTY), which lets you and the agent execute commands and interact with running processes thr…”
   • [claimed-docs] “You can run full-screen and interactive terminal apps like sqlite and python through the agent session. Warp Agent can also control those ap…”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.warp.dev/openapi.json — contains "openapi" key”
   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline. Use it to start …”

   proof ↗⚑ flag

   iTerm2✓fullcommunity8/10

   iTerm2 ships a documented Python API explicitly for programmatic control — creating/manipulating sessions, panes, tabs, windows, reading and sending text, and building custom automation — plus AppleScript scripting, both well documented and corroborated by independent community praise calling the Python API 'basically AppleScript... but lets you touch pretty much everything.' This directly satisfies an agent programmatically driving panes/commands/output. missing for 10: no explicit example of an AI agent using the API end-to-end, and no independent hands-on report of agent-driven automation specifically (only general scripting use).

   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”
   • [claimed-docs] “iTerm2 has sophisticated AppleScript support allowing one to write stand-alone scripts to launch the application and open multiple sessions …”
   • [claimed-docs] “iTerm2 has sophisticated AppleScript support allowing one to write stand-alone scripts to launch the application and open multiple sessions …”
   • [github] “Python Scripting API - Full automation and customization via Python. Create custom status bar components, triggers, menu items, or entirely …”
   • [community] “"imgcat: you can view images without leaving your terminal. Somehow this works even across SSH connections… Python scripting API: basically …”

   proof ↗⚑ flag

Extensibility

1. developerExtend the terminal with scripts or plugins in a real language (Lua, Python, kittens) beyond built-in options

   weight 2 · round to iTerm2
   Warp—none0/10

   Warp's extensibility is centered on MCP servers (for extending AI agent tool access) and a settings file, not a general-purpose scripting/plugin language like Lua or Python for customizing terminal behavior (e.g., kitty-style 'kittens'). No evidence pack item documents a scripting API, plugin SDK, or embedded language runtime for extending the terminal itself.

   • [claimed-docs] “MCP servers extend Warp’s local agents in a modular, flexible way by exposing custom tools or data sources through a standardized interface …”
   • [claimed-docs] “we are shipping a (long-overdue) settings file so that users and agents get programmatic control over settings and easy portability between …”

   proof ↗⚑ flag

   iTerm2✓fullcommunity8/10

   iTerm2 offers a documented Python API for full automation/customization (custom status bar components, triggers, menu items, new features), plus AppleScript scripting and trigger-invoked Python scripts, with community hands-on praise calling it 'basically AppleScript... but not soul-crushing to write' and noting real-world tools like imgcat/it2dl built on it. This covers 'real language' scripting well beyond built-in options, though there's no mention of Lua or 'kittens' (a kitty-terminal concept) support specifically. Missing for 10: Lua scripting support, kitten-style plugin format, independent third-party plugin ecosystem showcase.

   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”
   • [claimed-docs] “iTerm2 has sophisticated AppleScript support allowing one to write stand-alone scripts to launch the application and open multiple sessions …”
   • [claimed-docs] “iTerm2 has sophisticated AppleScript support allowing one to write stand-alone scripts to launch the application and open multiple sessions …”
   • [github] “Python Scripting API - Full automation and customization via Python. Create custom status bar components, triggers, menu items, or entirely …”
   • [github] “Triggers - Regex patterns that fire actions when matched: highlight text, run commands, send notifications, open password manager, set marks…”
   • [community] “"imgcat: you can view images without leaving your terminal. Somehow this works even across SSH connections… Python scripting API: basically …”

   proof ↗⚑ flag

Layouts

1. power-userDefine startup sessions and window layouts in config or scripts so a project workspace opens in one command

   weight 2 · round to iTerm2
   Warp—none0/10

   Warp documents automatic session restoration (windows/tabs/panes reopened on relaunch) but this is a global auto-restore behavior, not a user-authored config/script that defines named per-project startup layouts launchable via one command. No evidence of a project-workspace/layout definition file or CLI flag to open a specific named session.

   • [claimed-docs] “Restore your windows, tabs, panes, and recent Blocks automatically when you relaunch Warp.”
   • [claimed-docs] “Session restoration allows you to quickly pick up where you left off in your previous terminal session.”

   proof ↗⚑ flag

   iTerm2✓fullcommunity8/10

   iTerm2's AppleScript scripting explicitly supports launching the app and opening multiple sessions with profiles into new tabs/windows (a scripted workspace startup), and the Python API/triggers offer additional automation of session/window setup; profiles themselves can also be tied to directories/hosts for one-command workspace opening. missing for 10: no first-party example of a saved 'window arrangement' config file format or direct hands-on community confirmation of a single-command full-layout launch.

   • [claimed-docs] “iTerm2 has sophisticated AppleScript support allowing one to write stand-alone scripts to launch the application and open multiple sessions …”
   • [claimed-docs] “iTerm2 has sophisticated AppleScript support allowing one to write stand-alone scripts to launch the application and open multiple sessions …”
   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”
   • [claimed-docs] “you can define a profile that's always used when you ssh to some hostname. Or when your username is root. Or even when you're in a particula…”
   • [community] “"imgcat: you can view images without leaving your terminal. Somehow this works even across SSH connections… Python scripting API: basically …”

   proof ↗⚑ flag

Remote control

1. developerScript and control the terminal from the command line — open windows, send text, query state — via a documented CLI or IPC interface

   weight 3 · round to iTerm2
   Warp~partialclaimed5/10

   Warp ships documented CLI/IPC surfaces — the standalone Warp Agent CLI (works in any terminal, over SSH, creates its own PTY, can run/control full-screen apps) and the Oz CLI for running/managing cloud agents from scripts or CI with API-key auth — giving real command-line scriptability of agent sessions. However, the evidence is agent-centric (starting conversations, running commands, controlling processes) rather than direct terminal-window primitives like opening/arranging windows or querying pane/window state as the story literally describes (tmux/iTerm2-style control). Missing for 10: explicit documented commands to open/manage Warp windows or panes, send raw text to a specific pane, or query terminal UI state independent of an agent session; independent hands-on confirmation of such scripting.

   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline.”
   • [claimed-docs] “The Oz CLI is the command-line tool for running and managing Warp’s cloud agents from any terminal, script, or CI pipeline. Use it to start …”
   • [claimed-docs] “With the Oz CLI, you can: Run agents locally for development and debugging, Run agents on remote machines, Connect agents to MCP servers lik…”
   • [claimed-docs] “API Keys - Create and manage API keys to authenticate the Oz CLI without human interaction, ideal for CI pipelines, headless servers, and co…”
   • [claimed-docs] “Because it’s a regular command-line program, it works in any terminal emulator, including over SSH.”
   • [claimed-docs] “It creates and maintains its own pseudoterminal (PTY), which lets you and the agent execute commands and interact with running processes thr…”
   • [claimed-docs] “The Warp Agent CLI lets you switch directories while in an agent session, and even run agents on remote machines without installing remote b…”
   • [claimed-docs] “The Warp Agent is now available as a standalone CLI that you can use anywhere – Ghostty, iTerm 2, VS Code, built-in Windows and Mac Terminal…”

   proof ↗⚑ flag

   iTerm2✓fullcommunity8/10

   iTerm2 documents a robust Python API for scripting/controlling the terminal (open sessions, send text, query state) and AppleScript support for launching/controlling sessions, with independent community corroboration praising the Python API's power over AppleScript. missing for 10: no evidence of a CLI-only (non-Python/AppleScript) IPC socket documentation, and no hands-on demonstration of specific 'query state' calls beyond general docs.

   • [claimed-docs] “iTerm2 offers a Python package which makes it easy to write Python scripts that control iTerm2 and extend its behavior.”
   • [claimed-docs] “iTerm2 has sophisticated AppleScript support allowing one to write stand-alone scripts to launch the application and open multiple sessions …”
   • [claimed-docs] “iTerm2 has sophisticated AppleScript support allowing one to write stand-alone scripts to launch the application and open multiple sessions …”
   • [github] “Python Scripting API - Full automation and customization via Python. Create custom status bar components, triggers, menu items, or entirely …”
   • [community] “"imgcat: you can view images without leaving your terminal. Somehow this works even across SSH connections… Python scripting API: basically …”

   proof ↗⚑ flag

Command tracking

1. developerI get command-aware features from shell integration, like exit status, duration, and notifications when long commands finish

   weight 2 · round to iTerm2
   Warp~partialcommunity4/10

   Only evidence is a community anecdote naming notifications on long-running command completion as a favorite feature; there is no first-party documentation confirming exit status display, command duration tracking, or notification configuration as shell-integration features (the docs pack is dominated by AI/agent capabilities instead). missing for 10: official docs on exit status indicators, duration display, and notification settings; independent corroboration beyond a single forum comment.

   • [community] “My daily driver for a few months now, even after trying Rio/Ghostty/Wezterm... Favorite feature is the notification when a long running comm…”

   proof ↗⚑ flag

   iTerm2✓fullclaimed8/10

   iTerm2's shell integration docs confirm tracking of command history, prompts, directories, and hostnames, plus notifications for job completion/bells/activity and prompt navigation shortcuts. missing for 10: explicit documentation citing per-command exit status/duration display and independent hands-on confirmation of the notification-on-completion behavior.

   • [claimed-docs] “iTerm2 may be integrated with the unix shell so that it can keep track of your command history, current working directory, host name, and mo…”
   • [claimed-docs] “iTerm2 can integrate with your shell so it knows where your shell prompt is, what commands you're entering, which host you are on, and what …”
   • [claimed-docs] “You can choose to receive notifications of activity, bells, job completion, and more.”
   • [claimed-docs] “you can easily navigate to previous shell prompts with ⇧⌘↑ and ⇧⌘↓”
   • [claimed-docs] “you can enable shell integration by enabling **Load shell integration automatically** in **Settings > Profiles > General**”

   proof ↗⚑ flag

Marks

1. developerJump between prompts and command marks in my scrollback thanks to shell integration

   weight 2 · round to iTerm2
   Warp—none0/10

   The evidence pack references Warp's 'Blocks' concept (grouping commands and output) and session restoration of blocks, but never documents a shell-integration feature for jumping/navigating between prompt marks or command blocks in scrollback via keyboard shortcuts. Missing for 10: explicit documentation of prompt/command mark navigation shortcuts, scrollback jump-to-previous/next-prompt functionality, and any shell-integration-specific navigation UI.

   • [claimed-docs] “Restore your windows, tabs, panes, and recent Blocks automatically when you relaunch Warp.”
   • [claimed-docs] “Session restoration allows you to quickly pick up where you left off in your previous terminal session.”
   • [claimed-docs] “Sometimes, you may want to prevent a sensitive Block from being saved on your computer, or you may want to clear blocks from a machine entir…”

   proof ↗⚑ flag

   iTerm2✓fullclaimed9/10

   iTerm2's shell integration explicitly tracks prompts and sets marks at each command, and docs describe navigating between previous shell prompts with ⇧⌘↑/⇧⌘↓, corroborated by GitHub feature list mentioning marks at each prompt and copy mode working with marks to jump between prompts. Missing for 10: no independent hands-on account specifically confirming the prompt-jump keybinding in practice beyond docs/GitHub summaries.

   • [claimed-docs] “iTerm2 may be integrated with the unix shell so that it can keep track of your command history, current working directory, host name, and mo…”
   • [claimed-docs] “you can easily navigate to previous shell prompts with ⇧⌘↑ and ⇧⌘↓”
   • [claimed-docs] “iTerm2 can integrate with your shell so it knows where your shell prompt is, what commands you're entering, which host you are on, and what …”
   • [claimed-docs] “you can enable shell integration by enabling **Load shell integration automatically** in **Settings > Profiles > General**”
   • [github] “Enables click-to-download files via SCP, drag-and-drop uploads, command history per host, recent directories by "frecency," and marks at eac…”
   • [github] “Vim-like keyboard selection. Navigate and select text without touching the mouse. Works with marks to jump between command prompts.”

   proof ↗⚑ flag

Discoverability

1. power-userDiscover and run terminal actions from a searchable command palette

   weight 1 · round to Warp
   Warp~partialclaimed5/10

   Warp Drive lets users save workflows and run them 'on-demand' (warp-docs-11, warp-docs-30), and AI Command Suggestions via '#' provide natural-language command discovery (warp-docs-8), which together approximate a command-palette-style workflow, but no evidence explicitly describes a searchable palette UI for discovering and running arbitrary terminal actions. Missing for 10: explicit documentation of a dedicated command palette (e.g., Cmd+P style fuzzy search across commands/workflows), independent/community confirmation of this specific feature, and clarity on scope (built-in commands vs only saved workflows).

   • [claimed-docs] “Warp lets you save your most important workflows in Warp Drive so you can run them on‑demand or share with your team.”
   • [claimed-docs] “Warp lets you save your most important workflows in Warp Drive so you can run them on‑demand or share with your team. Let Warp AI handle the…”
   • [claimed-docs] “Type '#' on your command line and start describing the command you want to run using natural language. Warp will load AI Command Suggestions…”

   proof ↗⚑ flag

   iTerm2~partialclaimed4/10

   iTerm2's 'Open Quickly' (Cmd-Shift-O) is a searchable palette, but evidence describes it only as a search across sessions by tab title, command, hostname, directory, or badge — not a general command palette for discovering and invoking arbitrary terminal actions/menu commands. Missing for 10: evidence of listing/searching actual app commands or actions (not just sessions), evidence of executing arbitrary actions from the palette, and independent confirmation of this behaving like a true command palette.

   • [github] “Open Quickly - Cmd-Shift-O opens a search across all sessions by tab title, command, hostname, directory, or badge. Navigate large session c…”
   • [github] “Cmd-Shift-O opens a search across all sessions by tab title, command, hostname, directory, or badge. Navigate large session collections inst…”
   • [github] “Open Quickly - Cmd-Shift-O opens a search across all sessions by tab title, command, hostname, directory, or badge.”
   • [claimed-docs] “Just type the start of any word that has ever appeared in your window and then Cmd-; will pop open a window with suggestions.”

   proof ↗⚑ flag

Hyperlinks

1. developerOpen URLs and file paths from output by clicking them or selecting them from the keyboard

   weight 2 · round to iTerm2
   Warp—none0/10

   The evidence pack contains no documentation or community mention of clickable URLs/file paths, keyboard-selectable links, or similar output-navigation features in Warp's terminal Blocks. This is a fair ergonomics question for a terminal product but nothing in the pack confirms it ships.

   ⚑ flag

   iTerm2✓fullcommunity9/10

   Smart Selection with quad-click and Cmd-click to open URLs/paths, plus keyboard-based selection (Copy Mode/vim-like navigation), are documented and corroborated by community hands-on reports (Semantic History opening files in editor via Cmd+Click). missing for 10: no independent verification of full keyboard-only 'select and open' flow beyond selection, only Cmd-click for opening.

   • [github] “Smart Selection - Quad-click selects semantic objects (URLs, file paths, email addresses, quoted strings). Right-click for context actions. …”
   • [claimed-docs] “iTerm2 can perform "smart selection" to highlight URLs, email addresses, filenames, and more by recognizing what is under the cursor”
   • [claimed-docs] “iTerm2 can perform "smart selection" to highlight URLs, email addresses, filenames, and more by recognizing what is under the cursor.”
   • [github] “Vim-like keyboard selection. Navigate and select text without touching the mouse. Works with marks to jump between command prompts.”
   • [github] “Copy Mode - Vim-like keyboard selection. Navigate and select text without touching the mouse.”
   • [community] “"Semantic History is pretty handy and not well-known. It lets you Command+Click on a path to open it in your editor (or associated applicati…”
   • [claimed-docs] “Use the keyboard to make and modify selections.”

   proof ↗⚑ flag

Scrollback

1. developerSearch my scrollback quickly and jump between matches

   weight 2 · round to iTerm2
   Warp—none0/10

   The evidence pack covers Warp's AI/agent features, session restoration, theming, and telemetry, but contains no mention of scrollback search or match navigation functionality, despite this being a reasonable and expected axis for any terminal emulator.

   ⚑ flag

   iTerm2✓fullclaimed8/10

   Docs describe a robust find-on-page feature with instant highlighting of all matches and regex support, plus Global Search across all tabs, directly matching the story of searching scrollback and jumping between matches. Missing for 10: independent hands-on confirmation of match-jump behavior (next/prev match navigation) and details on keyboard shortcuts for cycling matches.

   • [claimed-docs] “iTerm2 comes with a robust find-on-page feature. The UI stays out of the way. All matches are immediately highlighted. Even regular expressi…”
   • [claimed-docs] “iTerm2 comes with a robust find-on-page feature... Even regular expression support is offered!”
   • [claimed-docs] “Search all your tabs at once with Global Search.”

   proof ↗⚑ flag