Rank #5 of 9 in AI Assistants

Poke

Name: Poke
Author: Cognition (The Interaction Company)

Built-in AI assistant

Cognition (The Interaction Company) · commercial

poke.com ↗Try it →

PA Score24/100 AGENT-READY42/100 BUILT-IN AI56/100 API0/100

MCP✓CLI~API~

no public signals

ArenasAI Assistants#5/9

Access

Open app ↗API docs ↗MCP docs ↗

Compare head-to-head

vs ChatGPT

vs Claude

vs Gemini

vs Perplexity vs Microsoft Copilot

vs Grok

vs Muse

vs Martin

Alternatives to Poke →

Try itExperimental

See what an agent can do with Poke before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).

$curl -si -X POST https://poke.com/api/v1/inbound/api-message -H 'Content-Type: application/json' -d '{"message":"ping"}'

recorded session — replayed, not live

▋

recorded 2026-09-14 · exit 0 · captured verbatim by our probe harness, secrets redacted · pure-HTTP probe — ▶ run live re-runs it from our edge

Verified integrations

No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.

By theme — the product's score on each story themeBy theme

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

36.9/100

Agents tasks — stories about agents tasks in this arenaAgents tasksevidence →

Stories about agents tasks in this arena

9.0/100

Apps devices — stories about apps devices in this arenaApps devicesevidence →

Stories about apps devices in this arena

15.0/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

11.3/100

Connectors apps — stories about connectors apps in this arenaConnectors appsevidence →

Stories about connectors apps in this arena

38.8/100

Files analysis — stories about files analysis in this arenaFiles analysisevidence →

Stories about files analysis in this arena

15.7/100

Memory context — stories about memory context in this arenaMemory contextevidence →

Stories about memory context in this arena

18.0/100

Multimodal — stories about multimodal in this arenaMultimodalevidence →

Stories about multimodal in this arena

10.0/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

4.8/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

0.0/100

Research answers — stories about research answers in this arenaResearch answersevidence →

Stories about research answers in this arena

0.0/100

Trust controls — stories about trust controls in this arenaTrust controlsevidence →

Stories about trust controls in this arena

0.0/100

Story verdicts — every judged story with its evidenceStory verdicts

Sorted by importance (agentic first) (high → low) · 52/52 stories · click a row’s chevron for the rationale and evidence


Delegate tasks to a built-in AI assistant inside the product G Agentic features	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	3	full	8/10	T probed
Plug MCP servers into this product so it can use their tools G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	3	full	8/10	T probed
Drive the product through a documented public API G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	3	partial	6/10	T probed
Connect an agent via an official MCP server G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	3	n/a	untested		none yet
Operate the product with natural-language commands G Agentic features	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	full	8/10	T probed
Point an agent at llms.txt or agent-oriented docs G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	full	8/10	T probed
Run the product headlessly / in CI for automation G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	partial	6/10	T probed
Use an official CLI G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	partial	6/10	C claimed
Set up automations that run autonomously in the background G Agentic features	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	partial	5/10	T probed
Build against official SDKs G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	partial	4/10	T probed
Get AI-generated insights and suggestions from my data inside the product G Agentic features	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	partial	4/10	C claimed
Subscribe to events via webhooks G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	partial	4/10	C claimed
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	none	0/10
Explore an interactive API reference with runnable examples G Api quality	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	none	0/10
Rely on versioned APIs with a documented deprecation policy G Api quality	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	none	0/10
Issue scoped/least-privilege API credentials for an agent G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	none	untested		none yet
Test against a sandbox environment without touching production data G Api quality	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	1	none	untested		none yet
Define rules that trigger actions automatically on events G	ai-native user	Automation depth — how much of the product can run unattendedAutomation depth	3	partial	5/10	C claimed
Delegate a multi-step task that the assistant works on autonomously in the background and returns for my review C Agent mode	power-user	Agents tasks — stories about agents tasks in this arenaAgents tasks	3	partial	5/10	T probed
Have the assistant remember relevant context from previous chats and apply it in new conversations C Memory	power-user	Memory context — stories about memory context in this arenaMemory context	3	partial	5/10	C claimed
Have the assistant write and run code on my data to produce charts, computed answers, and downloadable files C Analysis	power-user	Files analysis — stories about files analysis in this arenaFiles analysis	3	partial	4/10	C claimed
Connect my cloud drive, email, and calendar so the assistant can search and use them in answers C Connectors	knowledge-worker	Connectors apps — stories about connectors apps in this arenaConnectors apps	3	partial	3/10	C claimed
Upload documents, spreadsheets, and PDFs and get accurate analysis of their contents C Files	knowledge-worker	Files analysis — stories about files analysis in this arenaFiles analysis	3	partial	3/10	C claimed
Have the assistant operate a web browser on my behalf to research and complete tasks on websites C Agent mode	power-user	Agents tasks — stories about agents tasks in this arenaAgents tasks	3	none	0/10
Control whether my conversations are used to train models C Data controls	knowledge-worker	Trust controls — stories about trust controls in this arenaTrust controls	3	none	untested		none yet
Export all of my data in open formats and leave G	ai-native user	Openness — open source, data portability, and self-hosting storiesOpenness	3	none	untested		none yet
Launch a deep research run that autonomously searches many sources and returns a cited report C Research	knowledge-worker	Research answers — stories about research answers in this arenaResearch answers	3	none	untested		none yet
Prevent my data from being used to train AI models G	ai-native user	Privacy posture — data-handling and privacy storiesPrivacy posture	3	none	untested		none yet
Self-host the core product G	ai-native user	Openness — open source, data portability, and self-hosting storiesOpenness	3	none	untested		none yet
Browse a directory of third-party apps and connectors and add them to the assistant C Connectors	power-user	Connectors apps — stories about connectors apps in this arenaConnectors apps	2	full	7/10	C claimed
Build and share custom assistants with their own instructions and knowledge C Custom bots	power-user	Apps devices — stories about apps devices in this arenaApps devices	2	partial	5/10	C claimed
Share screenshots and photos and have the assistant accurately interpret what is in them C Images	knowledge-worker	Multimodal — stories about multimodal in this arenaMultimodal	2	partial	5/10	C claimed
Do everything through the API that I can do in the UI G	ai-native user	Openness — open source, data portability, and self-hosting storiesOpenness	2	partial	4/10	T probed
Have the assistant create and iteratively edit documents, presentations, and other files I can export G Artifacts	knowledge-worker	Files analysis — stories about files analysis in this arenaFiles analysis	2	none	0/10
Let the assistant see and operate applications on my computer to complete work C Agent mode	power-user	Agents tasks — stories about agents tasks in this arenaAgents tasks	2	none	0/10
Schedule recurring jobs or workflows G	ai-native user	Automation depth — how much of the product can run unattendedAutomation depth	2	none	0/10
Schedule recurring or one-off tasks that run automatically and come back to me with results C Tasks	power-user	Agents tasks — stories about agents tasks in this arenaAgents tasks	2	none	0/10
Use full-featured official mobile apps for iOS and Android C Apps	knowledge-worker	Apps devices — stories about apps devices in this arenaApps devices	2	none	0/10
Choose where my data is stored (region/residency) G	ai-native user	Privacy posture — data-handling and privacy storiesPrivacy posture	2	none	untested		none yet
Control data retention and deletion G	ai-native user	Privacy posture — data-handling and privacy storiesPrivacy posture	2	none	untested		none yet
Generate and edit images from natural-language prompts C Images	knowledge-worker	Multimodal — stories about multimodal in this arenaMultimodal	2	none	untested		none yet
Get answers grounded in current web results with citations back to the sources C Research	knowledge-worker	Research answers — stories about research answers in this arenaResearch answers	2	none	untested		none yet
Have a natural, real-time voice conversation with the assistant C Voice	knowledge-worker	Multimodal — stories about multimodal in this arenaMultimodal	2	none	untested		none yet
Manage members, permissions, and data policies for my organization's workspace C Admin	team-admin	Trust controls — stories about trust controls in this arenaTrust controls	2	n/a	untested		none yet
Opt out of telemetry and usage tracking G	ai-native user	Privacy posture — data-handling and privacy storiesPrivacy posture	2	none	untested		none yet
Organize related chats and files into a project or space that shares context and instructions C Projects	knowledge-worker	Memory context — stories about memory context in this arenaMemory context	2	none	untested		none yet
Perform bulk operations across many items at once G	ai-native user	Automation depth — how much of the product can run unattendedAutomation depth	2	none	untested		none yet
Read the product's source under an open license G	ai-native user	Openness — open source, data portability, and self-hosting storiesOpenness	2	none	untested		none yet
Use an official desktop app with OS-level shortcuts and access to what is on my screen C Apps	power-user	Apps devices — stories about apps devices in this arenaApps devices	2	n/a	untested		none yet
Set persistent custom instructions and preferences that shape every response C Memory	power-user	Memory context — stories about memory context in this arenaMemory context	1	partial	3/10	C claimed
Export my complete chat history and account data G Data controls	knowledge-worker	Trust controls — stories about trust controls in this arenaTrust controls	1	none	untested		none yet
Version, review, and roll back my automations G	ai-native user	Automation depth — how much of the product can run unattendedAutomation depth	1	none	untested		none yet

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 44 stories with headroom

What would move Poke’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.

Agents tasks — stories about agents tasks in this arenaHave the assistant operate a web browser on my behalf to research and complete tasks on websites
nonemoves PA Scoreimpact 30
Missing: any mention of browser automation, web navigation, or headless browsing capability.
Research answers — stories about research answers in this arenaLaunch a deep research run that autonomously searches many sources and returns a cited report
nonemoves PA Scoreimpact 30
Poke's evidence pack covers messaging integrations, MCP tool extensibility, recipes, and various assistant features, but nothing describes an autonomous multi-source deep research capability that returns a cited report.
Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave
nonemoves PA Scoreimpact 30
No evidence of any data export feature or open-format data portability in Poke's docs; the pack covers messaging API, MCP servers, integrations, and account merging but nothing about exporting user data (memory, conversation history, recipes) in open formats or account closure/data takeout.
Openness — open source, data portability, and self-hosting storiesSelf-host the core product
nonemoves PA Scoreimpact 30
Poke is a hosted SaaS assistant with no evidence of any self-hostable core product, open-source release, or on-prem deployment option; all docs describe a cloud service accessed via API/integrations/MCP.
Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models
nonemoves PA Scoreimpact 30
No evidence in the pack addresses data-training opt-out or privacy controls regarding AI model training; the docs focus on messaging, integrations, MCP, and recipes with no mention of data usage policies or opt-out settings.
Trust controls — stories about trust controls in this arenaControl whether my conversations are used to train models
nonemoves PA Scoreimpact 30
Missing: any privacy/data-training policy page, opt-out toggle, or enterprise data-use agreement.
Agenticness — how well agents can access and operate the productIssue scoped/least-privilege API credentials for an agent
nonemoves agent-readyimpact 30
Evidence shows Poke supports API access, integrations, and MCP servers, but there's no mention of scoped or least-privilege API credential/key issuance for agents — no API key management, permission scoping, or token-based access control documentation.
Agenticness — how well agents can access and operate the productExplore an interactive API reference with runnable examples
nonemoves API qualityimpact 30
No evidence of an interactive API reference or runnable examples; probes for OpenAPI/Swagger specs and docs.md all returned 404, and only basic prose docs about the messaging API exist.

Showing the top 8 of 44 — every none/partial verdict in the story verdicts table is headroom.

Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map3 surfaces · 22 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

docs22 stories

Point an agent at llms.txt or agent-oriented docs
Run the product headlessly / in CI for automation
Plug MCP servers into this product so it can use their tools
Use an official CLI
Drive the product through a documented public API
Build against official SDKs
Subscribe to events via webhooks
Get AI-generated insights and suggestions from my data inside the product
Set up automations that run autonomously in the background
Delegate tasks to a built-in AI assistant inside the product
Operate the product with natural-language commands
Delegate a multi-step task that the assistant works on autonomously in the background and returns for my review
Build and share custom assistants with their own instructions and knowledge
Define rules that trigger actions automatically on events
Browse a directory of third-party apps and connectors and add them to the assistant
Connect my cloud drive, email, and calendar so the assistant can search and use them in answers
Have the assistant write and run code on my data to produce charts, computed answers, and downloadable files
Upload documents, spreadsheets, and PDFs and get accurate analysis of their contents
Have the assistant remember relevant context from previous chats and apply it in new conversations
Set persistent custom instructions and preferences that shape every response
Share screenshots and photos and have the assistant accurately interpret what is in them
Do everything through the API that I can do in the UI

llms.txt5 stories

Point an agent at llms.txt or agent-oriented docs
Set up automations that run autonomously in the background
Delegate tasks to a built-in AI assistant inside the product
Operate the product with natural-language commands
Delegate a multi-step task that the assistant works on autonomously in the background and returns for my review

OpenAPI spec5 stories

Point an agent at llms.txt or agent-oriented docs
Run the product headlessly / in CI for automation
Drive the product through a documented public API
Build against official SDKs
Do everything through the API that I can do in the UI

Probe proofs — replayable recordings from the probe harnessProbe proofs

Replayable recordings from our probe harness — see the Prove-It protocol to submit one.

$curl -si -X POST https://poke.com/api/v1/inbound/api-message -H 'Content-Type: application/json' -d '{"message":"ping"}'

reproduced

$ curl -si -X POST https://poke.com/api/v1/inbound/api-message -H 'Content-Type: application/json' -d '{"message":"ping"}'
HTTP/2 401

access-control-allow-[redacted]

cache-control: no-store, private, max-age=0, no-cache, must-revalidate

{"error":"Unauthorized"}

proves: Drive the product through a documented public APIrecorded 2026-09-14

$curl -s https://poke.com/docs/api | grep -o 'api/v1/inbound/api-message'; curl -s https://poke.com/docs/mcp-servers | grep -io 'mcp server'

reproduced

$ curl -s https://poke.com/docs/api | grep -o 'api/v1/inbound/api-message'; curl -s https://poke.com/docs/mcp-servers | grep -io 'mcp server'
api/v1/inbound/api-message
api/v1/inbound/api-message
MCP Server
MCP server

proves: Drive the product through a documented public API proves: Plug MCP servers into this product so it can use their toolsrecorded 2026-09-14

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

2 of 5 testable claims verified · 0 contradicted → integrity 40/100

14 distinct capability claims found in Poke’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

Verified

Unverified

Contradicted

Undersold

Verified (2)

“Send messages programmatically via a documented public API”
Drive the product through a documented public API partial proof ↗
“Supports MCP servers so Poke can be extended with custom tools and data sources”
Plug MCP servers into this product so it can use their tools full proof ↗

Unverified (4)

“External services like GitHub, CI/CD, and monitoring tools can trigger Poke via webhooks/events”
Subscribe to events via webhooks partial proof ↗
“Official CLI lets you log in and tunnel a local MCP server for development”
Use an official CLI partial proof ↗
“Connect third-party apps and services (integrations) so Poke can access info and act across them via conversation”
Browse a directory of third-party apps and connectors and add them to the assistant full proof ↗
“Integrates with Webflow for visual website design and deployment”
Browse a directory of third-party apps and connectors and add them to the assistant full proof ↗

Undersold (17)

Point an agent at llms.txt or agent-oriented docs full proof ↗
Run the product headlessly / in CI for automation partial proof ↗
Build against official SDKs partial proof ↗
Get AI-generated insights and suggestions from my data inside the product partial proof ↗
Set up automations that run autonomously in the background partial proof ↗
Delegate tasks to a built-in AI assistant inside the product full proof ↗
Operate the product with natural-language commands full proof ↗
Delegate a multi-step task that the assistant works on autonomously in the background and returns for my review partial proof ↗
Build and share custom assistants with their own instructions and knowledge partial proof ↗
Define rules that trigger actions automatically on events partial proof ↗
Connect my cloud drive, email, and calendar so the assistant can search and use them in answers partial proof ↗
Have the assistant write and run code on my data to produce charts, computed answers, and downloadable files partial proof ↗
Upload documents, spreadsheets, and PDFs and get accurate analysis of their contents partial proof ↗
Have the assistant remember relevant context from previous chats and apply it in new conversations partial proof ↗
Set persistent custom instructions and preferences that shape every response partial proof ↗
Share screenshots and photos and have the assistant accurately interpret what is in them partial proof ↗
Do everything through the API that I can do in the UI partial proof ↗

Claims outside our story set (8)

Real capability claims found in Poke’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.

“Creators earn revenue when users install and use their MCP recipes”
source ↗
“Can merge two separate accounts into one”
source ↗
“Users can purchase additional usage credits to restore full limits”
source ↗
“Can dispatch real human workers to complete real-world tasks like reservations, calls, and orders”
source ↗
“Can create and deploy websites hosted at a personal yourname.poke.com subdomain”
source ↗
“Users can set up a dedicated @poke.com email address linked to their primary account”
source ↗
“Verified AI product available natively inside Apple Messages”
source ↗
“Available on Telegram as an alternative messaging channel to WhatsApp”
source ↗

Suggest a story for these →

Business model

free-tiersubscription-flat

Free tier with no card required; Pro and Ultra are flat monthly subscriptions that unlock frontier models and background automations, with pay-as-you-go usage on Ultra.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Score23 (Sep 14 '26)24 (Sep 16 '26)

Agent-ready40 (Sep 14 '26)42 (Sep 16 '26)

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

This page as markdown /llms.txt

Data

Evidence (JSON)Verdicts (JSON)

Poke

Try itExperimental

Verified integrations

By theme — the product's score on each story themeBy theme

Story verdicts — every judged story with its evidenceStory verdicts

🤖Agenticness — how well agents can access and operate the productAgenticness

🤖Agents tasks — stories about agents tasks in this arenaAgents tasks

🔌Apps devices — stories about apps devices in this arenaApps devices

⚙️Automation depth — how much of the product can run unattendedAutomation depth

🔌Connectors apps — stories about connectors apps in this arenaConnectors apps

🔎Files analysis — stories about files analysis in this arenaFiles analysis

🧠Memory context — stories about memory context in this arenaMemory context

✨Multimodal — stories about multimodal in this arenaMultimodal

🔓Openness — open source, data portability, and self-hosting storiesOpenness

🔒Privacy posture — data-handling and privacy storiesPrivacy posture

🔎Research answers — stories about research answers in this arenaResearch answers

⚖️Trust controls — stories about trust controls in this arenaTrust controls

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 44 stories with headroom

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map3 surfaces · 22 covered stories

Probe proofs — replayable recordings from the probe harnessProbe proofs

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

Business model

Score trend

Agenticness — how well agents can access and operate the productAgenticness

Agents tasks — stories about agents tasks in this arenaAgents tasks

Apps devices — stories about apps devices in this arenaApps devices

Automation depth — how much of the product can run unattendedAutomation depth

Connectors apps — stories about connectors apps in this arenaConnectors apps

Files analysis — stories about files analysis in this arenaFiles analysis

Memory context — stories about memory context in this arenaMemory context

Multimodal — stories about multimodal in this arenaMultimodal

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

Privacy posture — data-handling and privacy storiesPrivacy posture

Research answers — stories about research answers in this arenaResearch answers

Trust controls — stories about trust controls in this arenaTrust controls