Skip to content

AI Assistants Arena

AI Assistants arenaBuyer checklist

Every requirement we judge ai assistants products against, as a ready-to-send RFP checklist — with each item's priority, why it matters, and how the top-ranked products score on it today.

52 requirements · 12 themes · verdicts for 9 products · updated 2026-09-16 · priorities mirror the story weights our scoring uses (methodology)

Procurement report →
Show the markdown export
# AI Assistants — buyer checklist (RFP)

Derived from ProductArena's evidence-graded user-story taxonomy for AI Assistants: 52 judged requirements. Priorities mirror story weights (3 = must-have, 2 = should-have, 1 = nice-to-have).

## Agenticness

- [ ] **[must-have]** Plug MCP servers into this product so it can use their tools
- [ ] **[must-have]** Connect an agent via an official MCP server
- [ ] **[must-have]** Drive the product through a documented public API
- [ ] **[must-have]** Delegate tasks to a built-in AI assistant inside the product
- [ ] **[should-have]** Point an agent at llms.txt or agent-oriented docs
- [ ] **[should-have]** Run the product headlessly / in CI for automation
- [ ] **[should-have]** Use an official CLI
- [ ] **[should-have]** Issue scoped/least-privilege API credentials for an agent
- [ ] **[should-have]** Build against official SDKs
- [ ] **[should-have]** Subscribe to events via webhooks
- [ ] **[should-have]** Get AI-generated insights and suggestions from my data inside the product
- [ ] **[should-have]** Set up automations that run autonomously in the background
- [ ] **[should-have]** Operate the product with natural-language commands
- [ ] **[should-have]** Explore an interactive API reference with runnable examples
- [ ] **[should-have]** Download a machine-readable API spec (OpenAPI or equivalent)
- [ ] **[should-have]** Rely on versioned APIs with a documented deprecation policy
- [ ] **[nice-to-have]** Test against a sandbox environment without touching production data

## Agents tasks

- [ ] **[must-have]** Delegate a multi-step task that the assistant works on autonomously in the background and returns for my review
- [ ] **[must-have]** Have the assistant operate a web browser on my behalf to research and complete tasks on websites
- [ ] **[should-have]** Let the assistant see and operate applications on my computer to complete work
- [ ] **[should-have]** Schedule recurring or one-off tasks that run automatically and come back to me with results

## Apps devices

- [ ] **[should-have]** Use an official desktop app with OS-level shortcuts and access to what is on my screen
- [ ] **[should-have]** Use full-featured official mobile apps for iOS and Android
- [ ] **[should-have]** Build and share custom assistants with their own instructions and knowledge

## Automation depth

- [ ] **[must-have]** Define rules that trigger actions automatically on events
- [ ] **[should-have]** Perform bulk operations across many items at once
- [ ] **[should-have]** Schedule recurring jobs or workflows
- [ ] **[nice-to-have]** Version, review, and roll back my automations

## Connectors apps

- [ ] **[must-have]** Connect my cloud drive, email, and calendar so the assistant can search and use them in answers
- [ ] **[should-have]** Browse a directory of third-party apps and connectors and add them to the assistant

## Files analysis

- [ ] **[must-have]** Have the assistant write and run code on my data to produce charts, computed answers, and downloadable files
- [ ] **[must-have]** Upload documents, spreadsheets, and PDFs and get accurate analysis of their contents
- [ ] **[should-have]** Have the assistant create and iteratively edit documents, presentations, and other files I can export

## Memory context

- [ ] **[must-have]** Have the assistant remember relevant context from previous chats and apply it in new conversations
- [ ] **[should-have]** Organize related chats and files into a project or space that shares context and instructions
- [ ] **[nice-to-have]** Set persistent custom instructions and preferences that shape every response

## Multimodal

- [ ] **[should-have]** Generate and edit images from natural-language prompts
- [ ] **[should-have]** Share screenshots and photos and have the assistant accurately interpret what is in them
- [ ] **[should-have]** Have a natural, real-time voice conversation with the assistant

## Openness

- [ ] **[must-have]** Export all of my data in open formats and leave
- [ ] **[must-have]** Self-host the core product
- [ ] **[should-have]** Do everything through the API that I can do in the UI
- [ ] **[should-have]** Read the product's source under an open license

## Privacy posture

- [ ] **[must-have]** Prevent my data from being used to train AI models
- [ ] **[should-have]** Choose where my data is stored (region/residency)
- [ ] **[should-have]** Control data retention and deletion
- [ ] **[should-have]** Opt out of telemetry and usage tracking

## Research answers

- [ ] **[must-have]** Launch a deep research run that autonomously searches many sources and returns a cited report
- [ ] **[should-have]** Get answers grounded in current web results with citations back to the sources

## Trust controls

- [ ] **[must-have]** Control whether my conversations are used to train models
- [ ] **[should-have]** Manage members, permissions, and data policies for my organization's workspace
- [ ] **[nice-to-have]** Export my complete chat history and account data

---

Source: https://ultrametric.ai/productarena/arena/ai-assistants (evidence-graded verdicts for 9 products) · methodology: https://ultrametric.ai/productarena/methodology

Chips show the top 5 ranked products' current verdict on each requirement — ✓ full · ~ partial · ! disputed · — none · n/a not applicable.

Agenticness — how well agents can access and operate the productAgenticness· 17 items

How well agents can access and operate the product

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

    Core requirement — weighs 3× in arena scoring · 4 of 9 products fully deliver this today

    must-have
  • ai-native userConnect an agent via an official MCP server

    Core requirement — weighs 3× in arena scoring · all 2 products fully deliver this today

    must-have
  • ai-native userDrive the product through a documented public API

    Core requirement — weighs 3× in arena scoring · 2 of 9 products fully deliver this today

    must-have
  • ai-native userDelegate tasks to a built-in AI assistant inside the product

    Core requirement — weighs 3× in arena scoring · 6 of 9 products fully deliver this today

    must-have
  • ai-native userPoint an agent at llms.txt or agent-oriented docs

    Important, not disqualifying — weighs 2× in arena scoring · 5 of 8 products fully deliver this today

    should-have
  • ai-native userRun the product headlessly / in CI for automation

    Important, not disqualifying — weighs 2× in arena scoring · 2 of 6 products fully deliver this today

    should-have
  • ai-native userUse an official CLI

    Important, not disqualifying — weighs 2× in arena scoring · 2 of 8 products fully deliver this today

    should-have
  • ai-native userIssue scoped/least-privilege API credentials for an agent

    Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet

    should-have
  • ai-native userBuild against official SDKs

    Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet

    should-have
  • ai-native userSubscribe to events via webhooks

    Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet

    should-have
  • ai-native userGet AI-generated insights and suggestions from my data inside the product

    Important, not disqualifying — weighs 2× in arena scoring · 3 of 9 products fully deliver this today

    should-have
  • ai-native userSet up automations that run autonomously in the background

    Important, not disqualifying — weighs 2× in arena scoring · 3 of 9 products fully deliver this today

    should-have
  • ai-native userOperate the product with natural-language commands

    Important, not disqualifying — weighs 2× in arena scoring · 6 of 9 products fully deliver this today

    should-have
  • ai-native userExplore an interactive API reference with runnable examples

    Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet

    should-have
  • ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

    Important, not disqualifying — weighs 2× in arena scoring · 2 of 8 products fully deliver this today

    should-have
  • ai-native userRely on versioned APIs with a documented deprecation policy

    Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet

    should-have
  • ai-native userTest against a sandbox environment without touching production data

    Differentiator, not a dealbreaker — weighs 1× in arena scoring · no product fully delivers this yet

    nice-to-have

Agents tasks — stories about agents tasks in this arenaAgents tasks· 4 items

Stories about agents tasks in this arena

  • power-userDelegate a multi-step task that the assistant works on autonomously in the background and returns for my review

    Core requirement — weighs 3× in arena scoring · 2 of 9 products fully deliver this today

    must-have
  • power-userHave the assistant operate a web browser on my behalf to research and complete tasks on websites

    Core requirement — weighs 3× in arena scoring · 2 of 9 products fully deliver this today

    must-have
  • power-userLet the assistant see and operate applications on my computer to complete work

    Important, not disqualifying — weighs 2× in arena scoring · 2 of 9 products fully deliver this today

    should-have
  • power-userSchedule recurring or one-off tasks that run automatically and come back to me with results

    Important, not disqualifying — weighs 2× in arena scoring · 2 of 9 products fully deliver this today

    should-have

Apps devices — stories about apps devices in this arenaApps devices· 3 items

Stories about apps devices in this arena

  • power-userUse an official desktop app with OS-level shortcuts and access to what is on my screen

    Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet

    should-have
  • knowledge-workerUse full-featured official mobile apps for iOS and Android

    Important, not disqualifying — weighs 2× in arena scoring · 3 of 9 products fully deliver this today

    should-have
  • power-userBuild and share custom assistants with their own instructions and knowledge

    Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet

    should-have

Automation depth — how much of the product can run unattendedAutomation depth· 4 items

How much of the product can run unattended

Connectors apps — stories about connectors apps in this arenaConnectors apps· 2 items

Stories about connectors apps in this arena

  • knowledge-workerConnect my cloud drive, email, and calendar so the assistant can search and use them in answers

    Core requirement — weighs 3× in arena scoring · 4 of 9 products fully deliver this today

    must-have
  • power-userBrowse a directory of third-party apps and connectors and add them to the assistant

    Important, not disqualifying — weighs 2× in arena scoring · 3 of 9 products fully deliver this today

    should-have

Files analysis — stories about files analysis in this arenaFiles analysis· 3 items

Stories about files analysis in this arena

  • power-userHave the assistant write and run code on my data to produce charts, computed answers, and downloadable files

    Core requirement — weighs 3× in arena scoring · 2 of 8 products fully deliver this today

    must-have
  • knowledge-workerUpload documents, spreadsheets, and PDFs and get accurate analysis of their contents

    Core requirement — weighs 3× in arena scoring · 3 of 9 products fully deliver this today

    must-have
  • knowledge-workerHave the assistant create and iteratively edit documents, presentations, and other files I can export

    Important, not disqualifying — weighs 2× in arena scoring · 2 of 8 products fully deliver this today

    should-have

Memory context — stories about memory context in this arenaMemory context· 3 items

Stories about memory context in this arena

  • power-userHave the assistant remember relevant context from previous chats and apply it in new conversations

    Core requirement — weighs 3× in arena scoring · 3 of 9 products fully deliver this today

    must-have
  • knowledge-workerOrganize related chats and files into a project or space that shares context and instructions

    Important, not disqualifying — weighs 2× in arena scoring · 3 of 8 products fully deliver this today

    should-have
  • power-userSet persistent custom instructions and preferences that shape every response

    Differentiator, not a dealbreaker — weighs 1× in arena scoring · 1 of 9 products fully deliver this today

    nice-to-have

Multimodal — stories about multimodal in this arenaMultimodal· 3 items

Stories about multimodal in this arena

  • knowledge-workerGenerate and edit images from natural-language prompts

    Important, not disqualifying — weighs 2× in arena scoring · 3 of 8 products fully deliver this today

    should-have
  • knowledge-workerShare screenshots and photos and have the assistant accurately interpret what is in them

    Important, not disqualifying — weighs 2× in arena scoring · 3 of 9 products fully deliver this today

    should-have
  • knowledge-workerHave a natural, real-time voice conversation with the assistant

    Important, not disqualifying — weighs 2× in arena scoring · 5 of 9 products fully deliver this today

    should-have

Openness — open source, data portability, and self-hosting storiesOpenness· 4 items

Open source, data portability, and self-hosting stories

Privacy posture — data-handling and privacy storiesPrivacy posture· 4 items

Data-handling and privacy stories

Research answers — stories about research answers in this arenaResearch answers· 2 items

Stories about research answers in this arena

  • knowledge-workerLaunch a deep research run that autonomously searches many sources and returns a cited report

    Core requirement — weighs 3× in arena scoring · 2 of 9 products fully deliver this today

    must-have
  • knowledge-workerGet answers grounded in current web results with citations back to the sources

    Important, not disqualifying — weighs 2× in arena scoring · 2 of 9 products fully deliver this today

    should-have

Trust controls — stories about trust controls in this arenaTrust controls· 3 items

Stories about trust controls in this arena

  • knowledge-workerControl whether my conversations are used to train models

    Core requirement — weighs 3× in arena scoring · 2 of 9 products fully deliver this today

    must-have
  • team-adminManage members, permissions, and data policies for my organization's workspace

    Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet

    should-have
  • knowledge-workerExport my complete chat history and account data

    Differentiator, not a dealbreaker — weighs 1× in arena scoring · 1 of 9 products fully deliver this today

    nice-to-have

Full evidence behind every verdict lives on the arena page and each product page — chips above deep-link straight to the judged story.