Try itExperimental
See what an agent can do with Loops before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; the live MCP handshake runs real requests from our edge, right now — including, where the server allows it, one real read-only tool call (bring your own key for auth-gated servers); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).
$curl -si 'https://app.loops.so/api/v1/contacts/find?email=probe@example.com' | head -3 # documented REST API, keyless → 401recorded session — replayed, not liveVerified 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
Analytics attribution — stories about analytics attribution in this arenaAnalytics attributionevidence →
Stories about analytics attribution in this arena
Audience segmentation — stories about audience segmentation in this arenaAudience segmentationevidence →
Stories about audience segmentation in this arena
Automation depth — how much of the product can run unattendedAutomation depthevidence →
How much of the product can run unattended
Campaign sending — stories about campaign sending in this arenaCampaign sendingevidence →
Stories about campaign sending in this arena
Deliverability domains — stories about deliverability domains in this arenaDeliverability domainsevidence →
Stories about deliverability domains in this arena
Integrations webhooks — stories about integrations webhooks in this arenaIntegrations webhooksevidence →
Stories about integrations webhooks in this arena
Lifecycle automation — stories about lifecycle automation in this arenaLifecycle automationevidence →
Stories about lifecycle automation in this arena
List portability — stories about list portability in this arenaList portabilityevidence →
Stories about list portability in this arena
Marketing data access — stories about marketing data access in this arenaMarketing data accessevidence →
Stories about marketing data access in this arena
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Template content — stories about template content in this arenaTemplate contentevidence →
Stories about template content in this arena
Transactional sending — stories about transactional sending in this arenaTransactional sendingevidence →
Stories about transactional sending in this arena
Story verdicts — every judged story with its evidenceStory verdicts
Follow the green: where the map greys out is where Loops stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
API surface
Drive the product through a documented public API
✓9/10
unlocks → Webhooks · Scoped API keys · API sandbox · Full data export · Connect the platform to my existing stack — Stripe or Shopify, a CDP like Segment, my product database — with maintained first-party integrations · Subscribe webhooks to delivery and engagement events — sends, opens, clicks, bounces, unsubscribes — with a documented, signed payload
Subscribe to events via webhooks
—0/10
Build against official SDKs
✓8/10
Issue scoped/least-privilege API credentials for an agent
—0/10
Connect an agent via an official MCP server
✓8/10
Download a machine-readable API spec (OpenAPI or equivalent)
✓9/10
Rely on versioned APIs with a documented deprecation policy
~3/10
Test against a sandbox environment without touching production data
—–
Explore an interactive API reference with runnable examples
~4/10
Docs for agents
Point an agent at llms.txt or agent-oriented docs
✓9/10
Agentic features
Delegate tasks to a built-in AI assistant inside the product
—0/10
Operate the product with natural-language commands
~6/10
Plug MCP servers into this product so it can use their tools
n/an/a
Get AI-generated insights and suggestions from my data inside the product
—0/10
Set up automations that run autonomously in the background
✓6/10
Analytics attribution — stories about analytics attribution in this arenaAnalytics attribution
Stories about analytics attribution in this arena
Audience segmentation — stories about audience segmentation in this arenaAudience segmentation
Stories about audience segmentation in this arena
An agent can translate a plain-language audience description into a real segment via the platform's programmatic surface
—0/10
Create, update, and suppress contacts with custom properties through the API at production scale
~4/10
Create and update segments, tags, or lists programmatically and read back exactly who is in them
~4/10
Build audience segments from profile attributes, tags, and behavioral events, and they stay live as data changes
~5/10
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
Automation depth
Define rules that trigger actions automatically on events
~6/10
unlocks → Versioned workflows · See where any individual person sits inside an automation and pull or re-enter them without breaking the flow
Schedule recurring jobs or workflows
~4/10
unlocks → Versioned workflows
Perform bulk operations across many items at once
—0/10
Version, review, and roll back my automations
—–
Campaign sending — stories about campaign sending in this arenaCampaign sending
Stories about campaign sending in this arena
An agent can draft a campaign against a segment and leave it scheduled or queued for a human to approve before send
~6/10
Create and schedule a campaign or broadcast entirely through a documented public API, without touching the dashboard
~4/10
Compose an email campaign, pick its audience, and send or schedule it — the arena's table-stakes loop
✓7/10
A/B test subject lines or content variants and have the winner picked from real engagement
—–
Deliverability domains — stories about deliverability domains in this arenaDeliverability domains
Stories about deliverability domains in this arena
See bounce, complaint, and blocklist signals per send and get actionable guidance when deliverability degrades
—0/10
Authenticate my own sending domain — SPF, DKIM, DMARC alignment — with guided DNS setup and verification
—0/10
Unsubscribes, bounces, and spam complaints are suppressed automatically and honored across every send type — CAN-SPAM/GDPR hygiene by default
—0/10
Integrations webhooks — stories about integrations webhooks in this arenaIntegrations webhooks
Stories about integrations webhooks in this arena
Lifecycle automation — stories about lifecycle automation in this arenaLifecycle automation
Stories about lifecycle automation in this arena
Build multi-step lifecycle automations — welcome series, onboarding, winback — with branches, delays, and exit rules
~5/10
Fire a custom event from my product and have it trigger an automation for exactly that person
✓8/10
See where any individual person sits inside an automation and pull or re-enter them without breaking the flow
—0/10
List portability — stories about list portability in this arenaList portability
Stories about list portability in this arena
Marketing data access — stories about marketing data access in this arenaMarketing data access
Stories about marketing data access in this arena
An agent can pull my whole email program — audiences, live automations, recent campaign results — programmatically and report on what's working
~5/10
Read per-person engagement history — what was sent, opened, clicked — through the API for any contact
—0/10
Mint scoped or read-only API credentials so an agent or contractor can read analytics without the power to send
—0/10
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Template content — stories about template content in this arenaTemplate content
Stories about template content in this arena
Have the platform's built-in AI draft or refine subject lines and email copy from a brief, inside the composer
—0/10
Design on-brand emails with a visual editor, reusable templates, and personalization tokens that render correctly across clients
~6/10
Manage email templates as code — HTML/MJML or API-managed templates with variable substitution — under version control
~6/10
Transactional sending — stories about transactional sending in this arenaTransactional sending
Stories about transactional sending in this arena
Send one-to-one transactional email — receipts, magic links, notifications — through the same platform's API alongside marketing sends
✓8/10
Transactional email is kept separate from marketing — its own templates, suppression rules, and reputation — so a receipt still delivers to an unsubscribed contact
~4/10
Sorted by importance (agentic first) (high → low) · 58/58 stories · click a row’s chevron for the rationale and evidence
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 | full | 9/10 | Tprobed | |
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 | full | 8/10 | Tprobed | |
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 | none | 0/10 | ||
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 | n/a | 0/10 | ||
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 | full | 9/10 | Tprobed | |
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 | 9/10 | Tprobed | |
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Cclaimed | |
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 6/10 | Tprobed | |
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 | Tprobed | |
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 | full | 6/10 | Cclaimed | |
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 | partial | 4/10 | Tprobed | |
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 | partial | 3/10 | Tprobed | |
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 | 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 | 0/10 | ||
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
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 | |
Fire a custom event from my product and have it trigger an automation for exactly that person C Event triggers | developer | Lifecycle automation — stories about lifecycle automation in this arenaLifecycle automation | 3 | full | 8/10 | Tprobed | |
Send one-to-one transactional email — receipts, magic links, notifications — through the same platform's API alongside marketing sends C Transactional api | developer | Transactional sending — stories about transactional sending in this arenaTransactional sending | 3 | full | 8/10 | Tprobed | |
Compose an email campaign, pick its audience, and send or schedule it — the arena's table-stakes loop C Campaign core | marketer | Campaign sending — stories about campaign sending in this arenaCampaign sending | 3 | full | 7/10 | Cclaimed | |
An agent can draft a campaign against a segment and leave it scheduled or queued for a human to approve before send C Agent campaigns | ai-native user | Campaign sending — stories about campaign sending in this arenaCampaign sending | 3 | partial | 6/10 | Cclaimed | |
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 | 6/10 | Cclaimed | |
Build audience segments from profile attributes, tags, and behavioral events, and they stay live as data changes C Segment core | marketer | Audience segmentation — stories about audience segmentation in this arenaAudience segmentation | 3 | partial | 5/10 | Cclaimed | |
Build multi-step lifecycle automations — welcome series, onboarding, winback — with branches, delays, and exit rules C Automation core | marketer | Lifecycle automation — stories about lifecycle automation in this arenaLifecycle automation | 3 | partial | 5/10 | Cclaimed | |
Create and schedule a campaign or broadcast entirely through a documented public API, without touching the dashboard C Api campaigns | developer | Campaign sending — stories about campaign sending in this arenaCampaign sending | 3 | partial | 4/10 | Cclaimed | |
Create and update segments, tags, or lists programmatically and read back exactly who is in them C Api segments | developer | Audience segmentation — stories about audience segmentation in this arenaAudience segmentation | 3 | partial | 4/10 | Tprobed | |
Create, update, and suppress contacts with custom properties through the API at production scale C Api contacts | developer | Audience segmentation — stories about audience segmentation in this arenaAudience segmentation | 3 | partial | 4/10 | Tprobed | |
Authenticate my own sending domain — SPF, DKIM, DMARC alignment — with guided DNS setup and verification C Domain auth | ops user | Deliverability domains — stories about deliverability domains in this arenaDeliverability domains | 3 | none | 0/10 | ||
Export my entire audience — contacts, custom fields, tags, engagement history, and suppression list — in an open format, self-serve C Export | founder | List portability — stories about list portability in this arenaList portability | 3 | none | 0/10 | ||
Read opens, clicks, unsubscribes, and conversions per campaign and per automation step, over time C Reporting core | marketer | Analytics attribution — stories about analytics attribution in this arenaAnalytics attribution | 3 | none | 0/10 | ||
Read per-person engagement history — what was sent, opened, clicked — through the API for any contact C Api access | developer | Marketing data access — stories about marketing data access in this arenaMarketing data access | 3 | none | 0/10 | ||
Unsubscribes, bounces, and spam complaints are suppressed automatically and honored across every send type — CAN-SPAM/GDPR hygiene by default C Suppression | ops user | Deliverability domains — stories about deliverability domains in this arenaDeliverability domains | 3 | none | 0/10 | ||
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 | |
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 | n/a | untested | none yet | |
Subscribe webhooks to delivery and engagement events — sends, opens, clicks, bounces, unsubscribes — with a documented, signed payload C Webhooks | developer | Integrations webhooks — stories about integrations webhooks in this arenaIntegrations webhooks | 3 | none | untested | none yet | |
Design on-brand emails with a visual editor, reusable templates, and personalization tokens that render correctly across clients C Editor | marketer | Template content — stories about template content in this arenaTemplate content | 2 | partial | 6/10 | Xcommunity | |
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 | 6/10 | Tprobed | |
Manage email templates as code — HTML/MJML or API-managed templates with variable substitution — under version control C Templates as code | developer | Template content — stories about template content in this arenaTemplate content | 2 | partial | 6/10 | Xcommunity | |
An agent can pull my whole email program — audiences, live automations, recent campaign results — programmatically and report on what's working C Agent access | ai-native user | Marketing data access — stories about marketing data access in this arenaMarketing data access | 2 | partial | 5/10 | Tprobed | |
Attribute signups or revenue to specific emails and flows, not just opens and clicks C Attribution | founder | Analytics attribution — stories about analytics attribution in this arenaAnalytics attribution | 2 | partial | 5/10 | Cclaimed | |
Migrate in from another email platform with guided list import that preserves tags, custom fields, and unsubscribe state C Import migration | marketer | List portability — stories about list portability in this arenaList portability | 2 | partial | 5/10 | Cclaimed | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | partial | 4/10 | Cclaimed | |
Transactional email is kept separate from marketing — its own templates, suppression rules, and reputation — so a receipt still delivers to an unsubscribed contact C Transactional hygiene | ops user | Transactional sending — stories about transactional sending in this arenaTransactional sending | 2 | partial | 4/10 | Cclaimed | |
An agent can translate a plain-language audience description into a real segment via the platform's programmatic surface C Agent segments | ai-native user | Audience segmentation — stories about audience segmentation in this arenaAudience segmentation | 2 | none | 0/10 | ||
Have the platform's built-in AI draft or refine subject lines and email copy from a brief, inside the composer C Ai content | marketer | Template content — stories about template content in this arenaTemplate content | 2 | none | 0/10 | ||
Mint scoped or read-only API credentials so an agent or contractor can read analytics without the power to send C Scoped access | ops user | Marketing data access — stories about marketing data access in this arenaMarketing data access | 2 | none | 0/10 | ||
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 | 0/10 | ||
Pull campaign and flow performance metrics through the API into my own warehouse or dashboards C Api metrics | developer | Analytics attribution — stories about analytics attribution in this arenaAnalytics attribution | 2 | none | 0/10 | ||
See bounce, complaint, and blocklist signals per send and get actionable guidance when deliverability degrades C Deliverability signals | marketer | Deliverability domains — stories about deliverability domains in this arenaDeliverability domains | 2 | none | 0/10 | ||
See where any individual person sits inside an automation and pull or re-enter them without breaking the flow C Flow operations | ops user | Lifecycle automation — stories about lifecycle automation in this arenaLifecycle automation | 2 | none | 0/10 | ||
A/B test subject lines or content variants and have the winner picked from real engagement C Experiments | marketer | Campaign sending — stories about campaign sending in this arenaCampaign sending | 2 | none | untested | none yet | |
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 | |
Connect the platform to my existing stack — Stripe or Shopify, a CDP like Segment, my product database — with maintained first-party integrations C First party integrations | ops user | Integrations webhooks — stories about integrations webhooks in this arenaIntegrations webhooks | 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 | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 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 | |
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 46 stories with headroom
What would move Loops’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.
Agenticness — how well agents can access and operate the productDelegate tasks to a built-in AI assistant inside the product
nonemoves Built-in AIimpact 45
Loops' 'agents' materials describe APIs/MCP/CLI/skills that let external coding agents (Claude, Cursor, etc.) act on Loops on the user's behalf — this is Loops being consumed by an agent, not a built-in AI assistant living inside the Loops product that a user delegates tasks to.
Analytics attribution — stories about analytics attribution in this arenaRead opens, clicks, unsubscribes, and conversions per campaign and per automation step, over time
nonemoves PA Scoreimpact 30
Missing: any analytics/reporting endpoint or dashboard docs showing per-campaign/per-step metrics, time-series breakdowns, or conversion attribution.
Deliverability domains — stories about deliverability domains in this arenaAuthenticate my own sending domain — SPF, DKIM, DMARC alignment — with guided DNS setup and verification
nonemoves PA Scoreimpact 30
Missing: dNS setup guide, SPF/DKIM/DMARC record instructions, verification status UI or API, any deliverability-domain documentation.
Marketing data access — stories about marketing data access in this arenaRead per-person engagement history — what was sent, opened, clicked — through the API for any contact
nonemoves PA Scoreimpact 30
The evidence pack documents contact creation, event sending, campaign drafting, and transactional email APIs, but nowhere shows an endpoint or documentation for retrieving per-contact engagement history (sends, opens, clicks) via the API.
List portability — stories about list portability in this arenaExport my entire audience — contacts, custom fields, tags, engagement history, and suppression list — in an open format, self-serve
nonemoves PA Scoreimpact 30
Missing: a documented export/download API or dashboard feature, evidence of tags/engagement/suppression data being included in any export, and confirmation of an open file format (CSV/JSON) for full audience export.
Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave
nonemoves PA Scoreimpact 30
Evidence shows API endpoints for creating/writing contacts and events, migration guides for moving data INTO Loops from other providers, and an OpenAPI spec, but nothing documents a bulk export feature or open-format data portability for users wanting to leave Loops with their data.
Integrations webhooks — stories about integrations webhooks in this arenaSubscribe webhooks to delivery and engagement events — sends, opens, clicks, bounces, unsubscribes — with a documented, signed payload
nonemoves PA Scoreimpact 30
Missing: any webhook subscription endpoint, event types list, and payload signing/verification documentation.
Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models
nonemoves PA Scoreimpact 30
Missing: any privacy policy statement, opt-out mechanism, or documentation about AI training data usage.
Showing the top 8 of 46 — 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 map6 surfaces · 29 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
Agents docs23 stories
- Point an agent at llms.txt or agent-oriented docs
- Run the product headlessly / in CI for automation
- Connect an agent via an official MCP server
- Drive the product through a documented public API
- Set up automations that run autonomously in the background
- Operate the product with natural-language commands
- Explore an interactive API reference with runnable examples
- Create, update, and suppress contacts with custom properties through the API at production scale
- Create and update segments, tags, or lists programmatically and read back exactly who is in them
- Build audience segments from profile attributes, tags, and behavioral events, and they stay live as data changes
- Define rules that trigger actions automatically on events
- Schedule recurring jobs or workflows
- An agent can draft a campaign against a segment and leave it scheduled or queued for a human to approve before send
- Create and schedule a campaign or broadcast entirely through a documented public API, without touching the dashboard
- Compose an email campaign, pick its audience, and send or schedule it — the arena's table-stakes loop
- Build multi-step lifecycle automations — welcome series, onboarding, winback — with branches, delays, and exit rules
- Fire a custom event from my product and have it trigger an automation for exactly that person
- An agent can pull my whole email program — audiences, live automations, recent campaign results — programmatically and report on what's working
- Do everything through the API that I can do in the UI
- Design on-brand emails with a visual editor, reusable templates, and personalization tokens that render correctly across clients
- Manage email templates as code — HTML/MJML or API-managed templates with variable substitution — under version control
- Send one-to-one transactional email — receipts, magic links, notifications — through the same platform's API alongside marketing sends
- Transactional email is kept separate from marketing — its own templates, suppression rules, and reputation — so a receipt still delivers to an unsubscribed contact
OpenAPI spec13 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
- Explore an interactive API reference with runnable examples
- Download a machine-readable API spec (OpenAPI or equivalent)
- Rely on versioned APIs with a documented deprecation policy
- Create, update, and suppress contacts with custom properties through the API at production scale
- Create and update segments, tags, or lists programmatically and read back exactly who is in them
- Fire a custom event from my product and have it trigger an automation for exactly that person
- An agent can pull my whole email program — audiences, live automations, recent campaign results — programmatically and report on what's working
- Do everything through the API that I can do in the UI
- Send one-to-one transactional email — receipts, magic links, notifications — through the same platform's API alongside marketing sends
docs11 stories
- Run the product headlessly / in CI for automation
- Use an official CLI
- Drive the product through a documented public API
- Build against official SDKs
- Operate the product with natural-language commands
- Explore an interactive API reference with runnable examples
- Download a machine-readable API spec (OpenAPI or equivalent)
- Create, update, and suppress contacts with custom properties through the API at production scale
- Compose an email campaign, pick its audience, and send or schedule it — the arena's table-stakes loop
- Fire a custom event from my product and have it trigger an automation for exactly that person
- Design on-brand emails with a visual editor, reusable templates, and personalization tokens that render correctly across clients
loops.so11 stories
- Set up automations that run autonomously in the background
- Attribute signups or revenue to specific emails and flows, not just opens and clicks
- Create, update, and suppress contacts with custom properties through the API at production scale
- Create and update segments, tags, or lists programmatically and read back exactly who is in them
- Build audience segments from profile attributes, tags, and behavioral events, and they stay live as data changes
- Define rules that trigger actions automatically on events
- Schedule recurring jobs or workflows
- Compose an email campaign, pick its audience, and send or schedule it — the arena's table-stakes loop
- Build multi-step lifecycle automations — welcome series, onboarding, winback — with branches, delays, and exit rules
- An agent can pull my whole email program — audiences, live automations, recent campaign results — programmatically and report on what's working
- Design on-brand emails with a visual editor, reusable templates, and personalization tokens that render correctly across clients
llms.txt10 stories
- Point an agent at llms.txt or agent-oriented docs
- Drive the product through a documented public API
- An agent can draft a campaign against a segment and leave it scheduled or queued for a human to approve before send
- Create and schedule a campaign or broadcast entirely through a documented public API, without touching the dashboard
- Compose an email campaign, pick its audience, and send or schedule it — the arena's table-stakes loop
- Migrate in from another email platform with guided list import that preserves tags, custom fields, and unsubscribe state
- Design on-brand emails with a visual editor, reusable templates, and personalization tokens that render correctly across clients
- Manage email templates as code — HTML/MJML or API-managed templates with variable substitution — under version control
- Send one-to-one transactional email — receipts, magic links, notifications — through the same platform's API alongside marketing sends
- Transactional email is kept separate from marketing — its own templates, suppression rules, and reputation — so a receipt still delivers to an unsubscribed contact
Hacker News4 stories
- Rely on versioned APIs with a documented deprecation policy
- Design on-brand emails with a visual editor, reusable templates, and personalization tokens that render correctly across clients
- Manage email templates as code — HTML/MJML or API-managed templates with variable substitution — under version control
- Send one-to-one transactional email — receipts, magic links, notifications — through the same platform's API alongside marketing sends
Probe proofs — replayable recordings from the probe harnessProbe proofs
Replayable recordings from our probe harness — see the Prove-It protocol to submit one.
$curl -si 'https://app.loops.so/api/v1/contacts/find?email=probe@example.com' | head -3 # documented REST API, keyless → 401reproduced$ curl -si 'https://app.loops.so/api/v1/contacts/find?email=probe@example.com' | head -3 # documented REST API, [redacted]less → 401 HTTP/2 401 date: Mon, 14 Sep 2026 23:52:28 GMT content-type: application/json
$curl -si -X POST https://mcp.loops.so -H 'Content-Type: application/json' -d '<jsonrpc initialize>' # the hosted MCP server from loops.so/agents/mcpreproduced$ curl -si -X POST https://mcp.loops.so -H 'Content-Type: application/json' -d '<jsonrpc initialize>' # the hosted MCP server from loops.so/agents/mcp HTTP/2 401 access-control-expose-headers: Mcp-Session-Id, Mcp-Protocol-Version, WWW-Authenticate www-authenticate: Bearer resource_metadata="https://mcp.loops.so/.well-known/oauth-protected-resource", scope="mcp"
$curl -sL https://loops.so/llms.txt | head -6reproduced$ curl -sL https://loops.so/llms.txt | head -6 # Loops > Loops is an email platform for software companies. Send transactional and marketing email from one API, one contact model, and a no-code visual editor, with a free tier that doesn't expire. Built for engineers and lifecycle teams who want both developer-grade APIs and marketer-friendly tools in one place. - Website: https://loops.so - Docs: https://loops.so/docs
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
7 of 13 testable claims verified · 0 contradicted → integrity 54/100
18 distinct capability claims found in Loops’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
7
Verified
6
Unverified
0
Contradicted
16
Undersold
Verified (8)
“Send one-to-one transactional emails with dynamic data variables directly from your backend”
Send one-to-one transactional email — receipts, magic links, notifications — through the same platform's API alongside marketing sendsfullproof ↗
“Send a custom event via API to trigger a workflow for that person”
Fire a custom event from my product and have it trigger an automation for exactly that personfullproof ↗
“Create/add contacts to your audience via API”
Create, update, and suppress contacts with custom properties through the API at production scalepartialproof ↗
“Connect an agent to Loops over an official MCP server to read/write contacts, events, and content”
“Official SDKs let you add Loops to your application quickly”
“Author campaign content in code via the Content API while still editable visually in Loops”
Manage email templates as code — HTML/MJML or API-managed templates with variable substitution — under version controlpartialproof ↗
“Set brand colors, type, and spacing once and have every email automatically use them”
Design on-brand emails with a visual editor, reusable templates, and personalization tokens that render correctly across clientspartialproof ↗
“Visual editor for crafting on-brand emails”
Design on-brand emails with a visual editor, reusable templates, and personalization tokens that render correctly across clientspartialproof ↗
Unverified (7)
“Create draft campaigns (including content) via API, then review and send from the dashboard”
An agent can draft a campaign against a segment and leave it scheduled or queued for a human to approve before sendpartialproof ↗
“Official CLI lets you manage contacts, send events, and test transactional email from the terminal”
“Install the CLI and agent skills with one command so a coding agent can operate Loops”
“Automated migration scans codebase for sends, templates, webhooks, maps them to Loops and rebuilds templates via API”
Migrate in from another email platform with guided list import that preserves tags, custom fields, and unsubscribe statepartialproof ↗
“Set up lifecycle automations like onboarding, activation, upgrade, and winback emails once and iterate over time”
Build multi-step lifecycle automations — welcome series, onboarding, winback — with branches, delays, and exit rulespartialproof ↗
“See which emails lead to upgrades, reduce churn, and drive revenue”
Attribute signups or revenue to specific emails and flows, not just opens and clickspartialproof ↗
“Segments are dynamic and update automatically as contact properties change”
Build audience segments from profile attributes, tags, and behavioral events, and they stay live as data changespartialproof ↗
Undersold (16)
Point an agent at llms.txt or agent-oriented docsfullproof ↗
Run the product headlessly / in CI for automationpartialproof ↗
Drive the product through a documented public APIfullproof ↗
Set up automations that run autonomously in the backgroundfullproof ↗
Operate the product with natural-language commandspartialproof ↗
Explore an interactive API reference with runnable examplespartialproof ↗
Download a machine-readable API spec (OpenAPI or equivalent)fullproof ↗
Rely on versioned APIs with a documented deprecation policypartialproof ↗
Create and update segments, tags, or lists programmatically and read back exactly who is in thempartialproof ↗
Define rules that trigger actions automatically on eventspartialproof ↗
Create and schedule a campaign or broadcast entirely through a documented public API, without touching the dashboardpartialproof ↗
Compose an email campaign, pick its audience, and send or schedule it — the arena's table-stakes loopfullproof ↗
An agent can pull my whole email program — audiences, live automations, recent campaign results — programmatically and report on what's workingpartialproof ↗
Do everything through the API that I can do in the UIpartialproof ↗
Transactional email is kept separate from marketing — its own templates, suppression rules, and reputation — so a receipt still delivers to an unsubscribed contactpartialproof ↗
Claims outside our story set (3)
Real capability claims found in Loops’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.
“API authentication uses an API key as a Bearer token in the Authorization header”
source ↗“Unified platform for marketing, lifecycle, and transactional email, can keep existing transactional provider during migration”
source ↗“Run Guardian checks on an email message before sending”
source ↗
Business model
Free tier that doesn't expire (1,000 contacts, 4,000 sends/month, all features); paid plans scale by contact count.
pricing ↗Score trend
How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.
Try Experimental
Run it in the microterminal →Recorded agent sessions — and a live MCP handshake where the vendor ships one.
Flag
⚑ Flag a verdictThink a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.
For agents
