Decagon vs Pylon

Actions

1. developerThe agent takes real actions through my APIs — refunds, order changes, subscription updates — with scoped auth per action

   weight 3 · round to Decagon
   Decagon~partialclaimed6/10

   Decagon documents scoped, short-lived JWT access for agent actions across customer systems and integrations 'with no custom code required,' plus explicit mention of agents adjusting 'refund logic,' supporting real action-taking with scoped auth. However there's no detailed documentation of per-action granularity (e.g., separate refund vs subscription-update scopes), no audit trail examples, and no independent/hands-on verification of actual API action execution — missing for 10: per-action scope definitions, action audit logging, and third-party verification of real transactional actions.

   • [claimed-docs] “Short-lived JWT tokens give AI agents real-time access to customer systems, scoped for minimal privilege and discarded after each session.”
   • [claimed-docs] “no custom code required”
   • [claimed-docs] “with no custom code required”
   • [claimed-docs] “Whether you’re refining tone, adjusting refund logic, or trialing a new onboarding experience, experimentation makes it safe to test, learn,…”
   • [claimed-docs] “lets your Decagon agent access and complete tasks inside systems where there isn’t a traditional integration available”

   proof ↗⚑ flag

   Pylon~partialprobed5/10

   Pylon documents that AI agents can 'take action' and that admins can define Custom API tools so agents can hit internal or third-party API endpoints (e.g., a company's own refund/order APIs), and that Pylon's own API/MCP integration uses OAuth authentication for issues/accounts/contacts. However, there's no concrete example or documentation of granular, action-level scoped auth (e.g., distinct permission scopes for 'refund' vs 'subscription update') — the OAuth scoping described applies to Pylon's own data objects, not to arbitrary external business APIs the agent might call. Missing for 10: explicit examples of refunds/order/subscription actions being executed, and documentation of per-action auth scoping for custom API tools beyond general OAuth.

   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”
   • [claimed-docs] “Using a combination of Webhooks, API, and/or Pylon MCP, you can connect your agent to ticketing workflows in Pylon.”
   • [claimed-docs] “If a system does not provide an MCP server, an administrator can define a Custom API tool that agents can use to hit internal or third party…”
   • [claimed-docs] “AI tools authenticate with your Pylon account via OAuth and can read and update issues, accounts, and contacts within the data you can see i…”
   • [probe] “PROBE runtime (recorded 2026-09-10): the public REST API at api.usepylon.com is live and cleanly auth-gated — a keyless GET returned HTTP 40…”
   • [probe] “PROBE runtime (recorded 2026-09-10): the first-party MCP server is live — a keyless JSON-RPC initialize POST to https://mcp.usepylon.com ans…”

   proof ↗⚑ flag

Procedures

1. support ops leadI encode standard operating procedures the agent follows step-by-step for known issue types, with deterministic branching

   weight 2 · round to Decagon
   Decagon✓fullclaimed7/10

   Decagon explicitly ships 'Agent Operating Procedures (AOPs)' described as letting teams 'define agent behavior in natural language, the same way you train human agents with SOPs,' with Duet auto-generating and iterating these procedures from real interactions. This directly matches encoding step-by-step SOPs for known issue types. Missing for 10: concrete technical detail on how branching logic/decision trees are structured and enforced deterministically, and independent/hands-on corroboration beyond vendor docs.

   • [claimed-docs] “you can define agent behavior in natural language, the same way you train human agents with SOPs”
   • [claimed-docs] “Analyze past customer interactions to automatically generate Agent Operating Procedures (AOPs) rooted in actual customer needs.”
   • [claimed-docs] “Non-technical teams can architect and iterate on agent logic with Agent Operating Procedures (AOPs) and Duet”
   • [claimed-docs] “Non-technical teams can architect and iterate on agent logic with Agent Operating Procedures (AOPs) and Duet, while technical teams retain f…”
   • [claimed-docs] “As conversations reveal gaps and new opportunities, Duet automatically iterates on your agent, from the first launch through every improveme…”

   proof ↗⚑ flag

   Pylon~partialclaimed6/10

   Pylon's Runbooks feature lets ops leads write natural-language, step-by-step instructions for the AI Support Agent to follow for specific scenarios, and Skills provide reusable instructions for consistent handling of known workflows — directly matching the SOP-encoding need. However, the docs describe these as natural-language guidance rather than an explicit deterministic branching/decision-tree engine, and Triggers/automations are a separate rule system not tied to agent SOPs. Missing for 10: explicit conditional/branching logic constructs within runbooks, and evidence of deterministic (non-LLM-interpreted) path selection.

   • [claimed-docs] “Write instructions in natural language to help your AI Agent handle specific scenarios.”
   • [claimed-docs] “Skills are reusable instructions that teach Pylon agents how to handle specific workflows consistently.”
   • [claimed-docs] “Build your swarm of AI Agents to help augment your team.”
   • [claimed-docs] “Set up complex workflows and automations to execute your business processes”

   proof ↗⚑ flag

Agent access

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

   weight 2 · round to Pylon
   Decagon~partialprobed6/10

   The probe confirms Decagon serves a working llms.txt file at decagon.ai/llms.txt (HTTP 200) with structured product description, showing the product is discoverable by AI agents pointed at agent-oriented docs. However, there's no evidence of broader agent-oriented documentation (e.g., structured API docs, OpenAPI spec which 404'd) or first-party guidance encouraging users to point agents at this file. missing for 10: OpenAPI/API-level machine-readable docs (404s confirmed), first-party documentation explicitly promoting llms.txt usage for AI agents, and independent corroboration of an agent successfully consuming the file.

   • [probe] “PROBE llms.txt: HTTP 200 at https://decagon.ai/llms.txt # Decagon Decagon is an enterprise-grade AI platform revolutionizing customer suppo…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://decagon.ai/openapi.json, https://decagon.ai/swagger.json, https://decagon.ai/api/openapi.jso…”

   proof ↗⚑ flag

   Pylon✓fullprobed8/10

   Probes confirm a live llms.txt index at docs.usepylon.com/llms.txt and working per-page .md mirrors (e.g. pylon-mcp.md), so an agent can be pointed at agent-oriented docs and consume them directly. missing for 10: independent third-party confirmation beyond the vendor's own probe, and some per-page md endpoints (e.g. pylon-docs.md) 404 showing coverage is inconsistent.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.usepylon.com/llms.txt # Pylon ## Pylon - [Introduction](https://docs.usepylon.com/pylon-docs/gett…”
   • [probe] “PROBE runtime (recorded 2026-09-10): Pylon's docs are agent-legible — https://docs.usepylon.com/pylon-docs/llms.txt serves a live '# Pylon' …”
   • [probe] “PROBE docs-md: HTTP 200 at https://docs.usepylon.com/pylon-docs.md # Page Not Found The URL `pylon-docs` does not exist. This page may have…”

   proof ↗⚑ flag

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

   weight 2 · round to Pylon
   Decagon—none0/10

   Decagon is a SaaS conversational-AI platform for customer support with no-code configuration (AOPs, Duet, integrations 'no custom code required'); there is no documented CLI, headless mode, or CI-automation interface, and the openapi probe returned 404s, indicating no public API spec for automated/headless invocation. missing for 10: any CLI/SDK for headless execution, CI-pipeline integration docs, or public API reference enabling automation.

   • [claimed-docs] “no custom code required”
   • [claimed-docs] “with no custom code required”
   • [probe] “PROBE openapi: all candidate paths 404 (https://decagon.ai/openapi.json, https://decagon.ai/swagger.json, https://decagon.ai/api/openapi.jso…”

   proof ↗⚑ flag

   Pylon~partialprobed5/10

   Pylon exposes a REST API, webhooks, and triggers that allow programmatic, non-UI interaction with the platform, which supports automation-style usage outside the web UI (pylon-docs-31, pylon-docs-32, pylon-docs-30, pylon-probe-rt-2). However there is no evidence of a CLI, headless mode, or explicit CI/CD integration story — the product is a SaaS support platform accessed via API/OAuth, not something designed to be invoked in a CI pipeline. Missing for 10: explicit CLI/headless execution mode, CI/CD pipeline examples or docs, evidence of automated/scripted runs outside a live SaaS API context.

   • [claimed-docs] “Pylon's API can be used to programmatically access and take action on data within Pylon.”
   • [claimed-docs] “Receive webhooks for various events happening in Pylon.”
   • [claimed-docs] “Set up complex workflows and automations to execute your business processes”
   • [probe] “PROBE runtime (recorded 2026-09-10): the public REST API at api.usepylon.com is live and cleanly auth-gated — a keyless GET returned HTTP 40…”

   proof ↗⚑ flag

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

   weight 3 · round to Pylon
   Decagon~partialclaimed3/10

   Decagon has a blog post explicitly about MCP ("getting the most out of MCP") describing an infrastructure layer to curate, scope, and evaluate tool usage, indicating some MCP integration capability, but there is no concrete documentation of how to actually plug an MCP server into an agent, no config steps, and no independent corroboration of it working. missing for 10: technical setup docs for adding an MCP server, list of supported MCP servers/tools, hands-on or independent verification that agents actually invoke MCP tools.

   • [claimed-docs] “Bridging that gap requires an infrastructure layer purpose-built to curate, scope, and evaluate how tools are actually used.”

   proof ↗⚑ flag

   Pylon~partialclaimed5/10

   Pylon's agent 'connectors' documentation states that if a third-party system provides an MCP server, agents can use it directly (falling back to a Custom API tool only when none exists), indicating Pylon can consume external MCP servers as tool sources for its AI agents. However, this is a single thin doc line with no setup walkthrough, supported-server list, or hands-on/runtime confirmation of actually connecting to a third-party MCP server. missing for 10: a dedicated 'add MCP server' configuration flow/UI, documentation of supported transports/auth for third-party servers, and independent or runtime evidence of a working third-party MCP connection.

   • [claimed-docs] “If a system does not provide an MCP server, an administrator can define a Custom API tool that agents can use to hit internal or third party…”

   proof ↗⚑ flag

4. ai-native userConnect an agent via an official MCP server

   weight 3 · round to Pylon
   Decagon—none0/10

   Decagon's MCP blog post (decagon-docs-3) discusses using MCP to curate/scope tool access for its own agents (i.e., Decagon as an MCP client consuming external tools), not exposing an official MCP server that lets an external AI agent connect into Decagon. No documentation, endpoint, or announcement of a first-party Decagon MCP server was found, and the OpenAPI/spec probes returned 404s with no MCP-specific server mentioned.

   • [claimed-docs] “Bridging that gap requires an infrastructure layer purpose-built to curate, scope, and evaluate how tools are actually used.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://decagon.ai/openapi.json, https://decagon.ai/swagger.json, https://decagon.ai/api/openapi.jso…”

   proof ↗⚑ flag

   Pylon✓fullprobed9/10

   Pylon is a customer-support platform (not itself an agent), and it ships a first-party MCP server documented at docs.usepylon.com/pylon-docs/integrations/pylon-mcp with OAuth 2.0 authentication, hosted at mcp.usepylon.com. Runtime probes independently confirm the server is live (proper 401/WWW-Authenticate challenge with oauth-protected-resource metadata), corroborating the docs beyond vendor claims. Missing for 10: no independent third-party hands-on report of an agent successfully completing a task via this MCP server.

   • [claimed-docs] “AI tools authenticate with your Pylon account via OAuth and can read and update issues, accounts, and contacts within the data you can see i…”
   • [probe] “official MCP server documented at https://docs.usepylon.com/pylon-docs/integrations/pylon-mcp”
   • [probe] “PROBE runtime (recorded 2026-09-10): Pylon's docs are agent-legible — https://docs.usepylon.com/pylon-docs/llms.txt serves a live '# Pylon' …”
   • [probe] “PROBE runtime (recorded 2026-09-10): the first-party MCP server is live — a keyless JSON-RPC initialize POST to https://mcp.usepylon.com ans…”

   proof ↗⚑ flag

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

   weight 3 · round to Pylon
   Decagon—none0/10

   No evidence of a documented public API; the openapi probe returned 404s across all candidate paths and no docs reference an API reference, SDK, or programmatic endpoint. Integrations are described as 'no custom code required' (docs-19, docs-26), suggesting no-code/UI-driven configuration rather than a documented API for AI-native control.

   • [probe] “PROBE openapi: all candidate paths 404 (https://decagon.ai/openapi.json, https://decagon.ai/swagger.json, https://decagon.ai/api/openapi.jso…”
   • [claimed-docs] “no custom code required”
   • [claimed-docs] “with no custom code required”

   proof ↗⚑ flag

   Pylon✓fullprobed8/10

   Pylon documents a public REST API (docs-31) and webhooks (docs-32), and runtime probes confirm the API is live and properly auth-gated (probe-rt-2). Docs also describe programmatic/agentic access patterns (Custom API tools, OAuth-based AI tool access via docs-34) reinforcing that the API is designed for agentic/programmatic drivers. missing for 10: no discoverable OpenAPI/swagger spec (probe-3 shows 404s across candidate paths) and no independent third-party corroboration of API robustness beyond Pylon's own docs.

   • [claimed-docs] “Pylon's API can be used to programmatically access and take action on data within Pylon.”
   • [claimed-docs] “Receive webhooks for various events happening in Pylon.”
   • [claimed-docs] “AI tools authenticate with your Pylon account via OAuth and can read and update issues, accounts, and contacts within the data you can see i…”
   • [probe] “PROBE runtime (recorded 2026-09-10): the public REST API at api.usepylon.com is live and cleanly auth-gated — a keyless GET returned HTTP 40…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.usepylon.com/openapi.json, https://docs.usepylon.com/swagger.json, https://docs.usepylo…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Decagon~partialclaimed4/10

   Decagon documents short-lived, scoped JWT tokens for agent access to customer systems and identity-provider (Okta/Entra) integration, which shows some least-privilege credential mechanics, but this is about the agent's own runtime access rather than a user-facing capability to explicitly issue/manage scoped API credentials for an agent. There's no evidence of an API/console feature letting an AI-native user provision, scope, or revoke discrete credentials themselves. missing for 10: user-facing credential issuance/management UI or API, granular scoping controls exposed to users, independent verification of the JWT scoping claims.

   • [claimed-docs] “Short-lived JWT tokens give AI agents real-time access to customer systems, scoped for minimal privilege and discarded after each session.”
   • [claimed-docs] “Decagon integrates with identity providers like Okta and Microsoft Entra, enabling secure access across systems without additional passwords…”

   proof ↗⚑ flag

   Pylon~partialprobed4/10

   Pylon's MCP integration uses OAuth 2.0 (via AuthKit) and the REST API requires Bearer tokens, so credentials are authenticated and gated (pylon-docs-34, pylon-probe-rt-1/2/3), and access is limited to 'the data you can see in Pylon,' giving a coarse form of least-privilege tied to the issuing user's own permissions. However there is no evidence of a dedicated mechanism to mint distinct, granularly-scoped API keys or OAuth scopes specifically for an agent (e.g., read-only vs write, per-object scoping) separate from a full user account's access. Missing for 10: documented ability to configure fine-grained scopes/permissions per API credential, evidence of agent-specific token restriction UI, and independent confirmation of least-privilege enforcement beyond basic auth gating.

   • [claimed-docs] “AI tools authenticate with your Pylon account via OAuth and can read and update issues, accounts, and contacts within the data you can see i…”
   • [probe] “PROBE runtime (recorded 2026-09-10): Pylon's docs are agent-legible — https://docs.usepylon.com/pylon-docs/llms.txt serves a live '# Pylon' …”
   • [probe] “PROBE runtime (recorded 2026-09-10): the public REST API at api.usepylon.com is live and cleanly auth-gated — a keyless GET returned HTTP 40…”
   • [probe] “PROBE runtime (recorded 2026-09-10): the first-party MCP server is live — a keyless JSON-RPC initialize POST to https://mcp.usepylon.com ans…”

   proof ↗⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round to Pylon
   Decagon—none0/10

   No evidence of official SDKs for developers; the pack shows only no-code integrations, MCP blog commentary, and a failed openapi probe (404s), with no SDK documentation or API libraries surfaced.

   • [claimed-docs] “Bridging that gap requires an infrastructure layer purpose-built to curate, scope, and evaluate how tools are actually used.”
   • [claimed-docs] “no custom code required”
   • [claimed-docs] “with no custom code required”
   • [probe] “PROBE openapi: all candidate paths 404 (https://decagon.ai/openapi.json, https://decagon.ai/swagger.json, https://decagon.ai/api/openapi.jso…”

   proof ↗⚑ flag

   Pylon~partialprobed6/10

   Pylon exposes a documented REST API, webhooks, and an OAuth-secured official MCP server (confirmed live via runtime probes), which together let AI-native developers build integrations and agents against Pylon data. However, there is no evidence of traditional language-specific client SDKs (e.g., Python/Node packages) or an OpenAPI spec (probe found 404s for openapi/swagger endpoints), so 'SDK' support is really API+MCP+webhooks rather than packaged SDKs. Missing for 10: dedicated official SDK packages, publicly discoverable OpenAPI/swagger spec, independent developer corroboration of SDK usage.

   • [claimed-docs] “Pylon's API can be used to programmatically access and take action on data within Pylon.”
   • [claimed-docs] “Receive webhooks for various events happening in Pylon.”
   • [claimed-docs] “AI tools authenticate with your Pylon account via OAuth and can read and update issues, accounts, and contacts within the data you can see i…”
   • [probe] “PROBE runtime (recorded 2026-09-10): the public REST API at api.usepylon.com is live and cleanly auth-gated — a keyless GET returned HTTP 40…”
   • [probe] “PROBE runtime (recorded 2026-09-10): the first-party MCP server is live — a keyless JSON-RPC initialize POST to https://mcp.usepylon.com ans…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.usepylon.com/openapi.json, https://docs.usepylon.com/swagger.json, https://docs.usepylo…”

   proof ↗⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round to Pylon
   Decagon—none0/10

   No evidence in the pack mentions webhooks, event subscriptions, or any push-notification mechanism; the OpenAPI probe returned 404s and no API reference documenting webhook endpoints was found. This axis applies (Decagon integrates with external systems and could plausibly offer webhooks) but there is no supporting evidence.

   • [probe] “PROBE openapi: all candidate paths 404 (https://decagon.ai/openapi.json, https://decagon.ai/swagger.json, https://decagon.ai/api/openapi.jso…”

   proof ↗⚑ flag

   Pylon✓fullclaimed7/10

   Pylon documents a dedicated webhooks feature for receiving events happening in Pylon, directly matching the story. missing for 10: no independent/hands-on corroboration of webhook delivery, no detail on event types/payload schema, or subscription management UI/API specifics.

   • [claimed-docs] “Receive webhooks for various events happening in Pylon.”
   • [claimed-docs] “Using a combination of Webhooks, API, and/or Pylon MCP, you can connect your agent to ticketing workflows in Pylon.”

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round to Decagon
   Decagon✓fullclaimed8/10

   Decagon's Insights & Reporting and Suggestions features let users ask open-ended natural-language questions (e.g. 'Why are customers requesting refunds?') and get AI-driven analysis, heatmaps, and auto-generated content drafts based on detected knowledge gaps, directly surfacing AI-generated insights from customer data. Duet further auto-generates Agent Operating Procedures from past interactions and iterates based on conversation patterns. Missing for 10: independent/hands-on validation of insight quality and no detail on underlying analytics accuracy or limitations.

   • [claimed-docs] “Ask open-ended questions like “Why are customers requesting refunds?” to instantly analyze customer conversations.”
   • [claimed-docs] “It automatically detects knowledge gaps and generates content drafts based on how your best human agents resolved those same issues, so your…”
   • [claimed-docs] “Customizable visual heatmaps... Quickly identify spikes or dips in key metrics.”
   • [claimed-docs] “It automatically detects knowledge gaps and generates content drafts based on how your best human agents resolved those same issues”
   • [claimed-docs] “Ask AI powers deeper analysis through flexible, conversational queries.”
   • [claimed-docs] “Analyze past customer interactions to automatically generate Agent Operating Procedures (AOPs) rooted in actual customer needs.”
   • [claimed-docs] “As conversations reveal gaps and new opportunities, Duet automatically iterates on your agent, from the first launch through every improveme…”

   proof ↗⚑ flag

   Pylon~partialclaimed6/10

   Pylon documents AI summarization of customer conversations synced to CRM accounts (Salesforce), AI-powered knowledge base features, and analytics dashboards, plus AI Support Agents that surface context and take action — all suggesting embedded AI insight generation. However, there's no dedicated 'insights' feature that proactively surfaces suggestions from the user's own data (e.g., trend detection, anomaly alerts) beyond conversation summarization and agent responses. Missing for 10: a first-party 'insights' or 'suggestions' dashboard feature explicitly generating recommendations from account/ticket data, and independent/hands-on validation of insight quality.

   • [claimed-docs] “Every day, Pylon scans your customer channels for conversations that were had. For every conversation, we use AI to summarize the details, a…”
   • [claimed-docs] “Pylon comes with a number of default analytics dashboards with common support metrics. All dashboards are filterable by a wide selection of …”
   • [claimed-docs] “A dedicated place to host your support content, including question-and-answer style articles, internal runbooks, and more -- all supercharge…”
   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”
   • [claimed-docs] “The issue log allows you to inspect all the issues the AI agent is associated with and inspect the outcomes and steps taken by the AI.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Decagon~partialclaimed6/10

   Decagon's Proactive Agents can carry context across sessions and autonomously initiate calls/recommendations based on customer signals, and Watchtower continuously monitors every interaction against custom criteria without manual triggering — both indicate background/autonomous operation. However, there's no explicit documentation of a general-purpose automation/scheduling framework (e.g., triggers, cron-like workflows, or arbitrary background tasks) beyond these two specific features. Missing for 10: a dedicated automation/scheduler product surface, independent/hands-on verification of autonomous behavior, and broader configurability beyond proactive outreach and monitoring.

   • [claimed-docs] “Carry conversation history across sessions to pick up where you left off and make proactive recommendations based on customer signals.”
   • [claimed-docs] “Initiate intelligent, on-brand calls that reliably reach customers at the right moments throughout their journey.”
   • [claimed-docs] “Maintain customer context across sessions, complementing your systems of record with data portability and control.”
   • [claimed-docs] “Whether you're monitoring for compliance risks, negative sentiment, or upsell signals, Watchtower reviews every interaction against your cus…”

   proof ↗⚑ flag

   Pylon~partialclaimed6/10

   Pylon documents triggers/automations to execute business processes, webhooks, API access, and AI agents that autonomously handle issues assigned to them with monitoring via issue logs, supporting background autonomous automation. However, evidence is mostly first-party docs with no independent/hands-on confirmation of unattended reliability or long-running autonomy at scale. Missing for 10: independent/hands-on verification of autonomous background execution, detail on failure handling/retries in triggers, and third-party confirmation of agent autonomy in production.

   • [claimed-docs] “Set up complex workflows and automations to execute your business processes”
   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”
   • [claimed-docs] “You can assign them to issues you'd like them to take a look at. This means you have full control of which customer issues your AI agent int…”
   • [claimed-docs] “The issue log allows you to inspect all the issues the AI agent is associated with and inspect the outcomes and steps taken by the AI.”
   • [claimed-docs] “Receive webhooks for various events happening in Pylon.”
   • [claimed-docs] “Pylon's API can be used to programmatically access and take action on data within Pylon.”

   proof ↗⚑ flag

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

   weight 3 · round to Pylon
   Decagon~partialclaimed5/10

   Decagon's Duet acts as an in-product AI helper that lets (non-technical) users delegate specific tasks — auto-generating Agent Operating Procedures from past conversations, drafting tests, and producing content suggestions — which is a form of delegating work to a built-in assistant, but it's narrowly scoped to agent-configuration/QA tasks rather than a general-purpose assistant for arbitrary user tasks. missing for 10: evidence of a general-purpose in-product assistant handling open-ended user requests beyond AOP/test/content generation, independent/hands-on validation of Duet's delegation quality, and detail on how broadly tasks can be delegated versus templated workflows.

   • [claimed-docs] “Non-technical teams can architect and iterate on agent logic with Agent Operating Procedures (AOPs) and Duet”
   • [claimed-docs] “Analyze past customer interactions to automatically generate Agent Operating Procedures (AOPs) rooted in actual customer needs.”
   • [claimed-docs] “Use Duet to easily generate tests covering diverse pathways that verify whether agents respond accurately, follow policies, and reflect your…”
   • [claimed-docs] “It automatically detects knowledge gaps and generates content drafts based on how your best human agents resolved those same issues, so your…”

   proof ↗⚑ flag

   Pylon✓fullclaimed8/10

   Pylon ships built-in AI Support Agents that users can build, assign to issues, give runbooks/skills, and monitor outcomes—clearly a built-in assistant users delegate tasks to (assign issues, define workflows, review AI-taken actions). Missing for 10: independent/third-party hands-on validation of assistant task quality and no user-facing UI screenshots/demos beyond docs.

   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”
   • [claimed-docs] “Build your swarm of AI Agents to help augment your team.”
   • [claimed-docs] “Write instructions in natural language to help your AI Agent handle specific scenarios.”
   • [claimed-docs] “You can assign them to issues you'd like them to take a look at. This means you have full control of which customer issues your AI agent int…”
   • [claimed-docs] “The issue log allows you to inspect all the issues the AI agent is associated with and inspect the outcomes and steps taken by the AI.”
   • [claimed-docs] “Skills are reusable instructions that teach Pylon agents how to handle specific workflows consistently.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Decagon~partialclaimed6/10

   Decagon lets operators define agent behavior, flagging criteria, and analytics queries via natural language (AOPs, Watchtower, Ask AI), which supports natural-language operation of the product for configuration/analysis purposes. However, this is primarily aimed at business/support-ops users configuring an agent, not a general 'AI-native user' issuing arbitrary natural-language commands to control the whole product end-to-end. missing for 10: evidence of natural-language command interface for broader product operations (e.g., admin tasks, integrations setup, deployment) beyond AOPs/Watchtower/Insights, and independent/hands-on verification of this capability.

   • [claimed-docs] “Define what matters using natural language. From "mentions of frustration" to "violations of data privacy policy," Watchtower understands yo…”
   • [claimed-docs] “you can define agent behavior in natural language, the same way you train human agents with SOPs”
   • [claimed-docs] “Define what matters using natural language. From "mentions of frustration" to "violations of data privacy policy," Watchtower understands yo…”
   • [claimed-docs] “Ask AI powers deeper analysis through flexible, conversational queries.”
   • [claimed-docs] “Ask open-ended questions like “Why are customers requesting refunds?” to instantly analyze customer conversations.”

   proof ↗⚑ flag

   Pylon~partialprobed6/10

   Pylon exposes a live first-party MCP server (confirmed by runtime probes) that lets AI tools authenticate via OAuth and read/update issues, accounts, and contacts, effectively letting an AI-native user drive Pylon via natural-language-mediated agent actions; runbooks and skills also let admins encode natural-language instructions for agent behavior. However, this is achieved through external AI-tool/agent integration rather than a native in-app NL command interface for end users. Missing for 10: evidence of a built-in chat/command-bar UI where a human directly issues natural-language commands to operate Pylon itself, and independent confirmation of real-world NL-driven task completion.

   • [claimed-docs] “AI tools authenticate with your Pylon account via OAuth and can read and update issues, accounts, and contacts within the data you can see i…”
   • [claimed-docs] “Write instructions in natural language to help your AI Agent handle specific scenarios.”
   • [claimed-docs] “Skills are reusable instructions that teach Pylon agents how to handle specific workflows consistently.”
   • [probe] “PROBE runtime (recorded 2026-09-10): Pylon's docs are agent-legible — https://docs.usepylon.com/pylon-docs/llms.txt serves a live '# Pylon' …”
   • [probe] “PROBE runtime (recorded 2026-09-10): the first-party MCP server is live — a keyless JSON-RPC initialize POST to https://mcp.usepylon.com ans…”
   • [claimed-docs] “Using a combination of Webhooks, API, and/or Pylon MCP, you can connect your agent to ticketing workflows in Pylon.”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round drawn
   Decagon—none0/10

   No evidence of an interactive API reference or runnable examples; the openapi probe returned 404 across all candidate paths and no docs mention API documentation with runnable examples. Missing for 10: any API reference page, SDK/runnable code samples, interactive docs like Swagger/Redoc, or developer sandbox.

   • [probe] “PROBE openapi: all candidate paths 404 (https://decagon.ai/openapi.json, https://decagon.ai/swagger.json, https://decagon.ai/api/openapi.jso…”

   proof ↗⚑ flag

   Pylon—none0/10

   Pylon documents a REST API and webhooks (pylon-docs-31, pylon-docs-32) but there is no evidence of an interactive API reference with runnable/try-it examples — probes explicitly found no OpenAPI/Swagger spec at any candidate path (pylon-probe-3), only static markdown docs.

   • [claimed-docs] “Pylon's API can be used to programmatically access and take action on data within Pylon.”
   • [claimed-docs] “Receive webhooks for various events happening in Pylon.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.usepylon.com/openapi.json, https://docs.usepylon.com/swagger.json, https://docs.usepylo…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Decagon—none0/10

   Probe explicitly checked common OpenAPI/swagger endpoints and all returned 404, and no documentation references a downloadable machine-readable API spec; only an llms.txt file was found, which is not an API spec.

   • [probe] “PROBE openapi: all candidate paths 404 (https://decagon.ai/openapi.json, https://decagon.ai/swagger.json, https://decagon.ai/api/openapi.jso…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://decagon.ai/llms.txt # Decagon Decagon is an enterprise-grade AI platform revolutionizing customer suppo…”

   proof ↗⚑ flag

   Pylon—none0/10

   Pylon has a REST API and docs, but explicit probes for OpenAPI/Swagger spec files at standard paths all returned 404, and no evidence anywhere shows a downloadable machine-readable spec (OpenAPI, JSON Schema, etc.) for its API.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.usepylon.com/openapi.json, https://docs.usepylon.com/swagger.json, https://docs.usepylo…”
   • [claimed-docs] “Pylon's API can be used to programmatically access and take action on data within Pylon.”
   • [probe] “PROBE runtime (recorded 2026-09-10): the public REST API at api.usepylon.com is live and cleanly auth-gated — a keyless GET returned HTTP 40…”

   proof ↗⚑ flag

3. ai-native userTest against a sandbox environment without touching production data

   weight 1 · round to Decagon
   Decagon~partialclaimed5/10

   Decagon's Testing & QA product describes 'Simulations' that validate agent behavior 'before deploying to production and with every subsequent update' (decagon-docs-29) and Duet-generated test suites (decagon-docs-11), implying a pre-production testing environment. However, there is no explicit documentation of a dedicated sandbox with isolated/non-production data, and the Experiments feature explicitly runs live in production (decagon-docs-7), which cuts against a clear sandbox-vs-production separation. Missing for 10: explicit description of sandbox data isolation, confirmation that test/simulation environments don't touch live customer data, and independent verification of this claim.

   • [claimed-docs] “Simulations, Decagon's integrated testing suite, help teams validate agent behavior across channels before deploying to production and with …”
   • [claimed-docs] “Use Duet to easily generate tests covering diverse pathways that verify whether agents respond accurately, follow policies, and reflect your…”
   • [claimed-docs] “Define your variable and traffic split, then measure results against a stable control group directly in production.”

   proof ↗⚑ flag

   Pylon~partialclaimed3/10

   Pylon's Support Agent docs mention a 'test' feature to simulate interactions with the AI without deploying it live (pylon-docs-17), which suggests some sandboxed testing before touching real customer issues, but there's no documented sandbox environment, staging API, or test dataset separate from production data. Missing for 10: explicit sandbox/staging environment, test API keys or test accounts isolated from production, and confirmation that simulated interactions don't touch real customer/production data.

   • [claimed-docs] “Simulate an interaction with the AI and see how it handles different questions.”
   • [claimed-docs] “You can assign them to issues you'd like them to take a look at. This means you have full control of which customer issues your AI agent int…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Decagon—none0/10

   No evidence of a public/versioned API, API changelog, or deprecation policy; the openapi probe returned 404s across all candidate paths and no docs mention API versioning or deprecation practices.

   • [probe] “PROBE openapi: all candidate paths 404 (https://decagon.ai/openapi.json, https://decagon.ai/swagger.json, https://decagon.ai/api/openapi.jso…”

   proof ↗⚑ flag

   Pylon—none0/10

   Evidence shows Pylon has a REST API, webhooks, and MCP server, but no documentation of API versioning scheme or a deprecation policy anywhere in docs/changelog; openapi spec probes 404 and no version headers or changelog entries reference API deprecations. Missing for 10: versioning scheme (e.g., v1/v2 paths), documented deprecation timeline/policy, changelog entries about breaking changes.

   • [claimed-docs] “Pylon's API can be used to programmatically access and take action on data within Pylon.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.usepylon.com/openapi.json, https://docs.usepylon.com/swagger.json, https://docs.usepylo…”
   • [probe] “PROBE runtime (recorded 2026-09-10): the public REST API at api.usepylon.com is live and cleanly auth-gated — a keyless GET returned HTTP 40…”

   proof ↗⚑ flag

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

   weight 2 · round to Pylon
   Decagon—none0/10

   No evidence describes a bulk-operations feature (e.g., batch editing, bulk tagging, bulk export/import of tickets or conversations) for AI-native users; the closest items describe aggregate analysis (Watchtower reviewing every interaction, Insights analyzing many conversations) rather than user-driven bulk actions across items.

   ⚑ flag

   Pylon~partialprobed5/10

   Pylon's API (pylon-docs-31), MCP server (pylon-docs-34, pylon-probe-rt-1/3), and triggers/automations (pylon-docs-30) give AI agents and scripts programmatic read/update access to issues, accounts, and contacts, which could be used to script bulk changes, but no evidence describes a dedicated bulk-edit/bulk-action UI or batch-endpoint for acting on many items in one call. Missing for 10: an explicit bulk-update/bulk-action API or UI feature, and any documentation or demo of multi-item batch operations rather than single-record CRUD via API/MCP.

   • [claimed-docs] “Pylon's API can be used to programmatically access and take action on data within Pylon.”
   • [claimed-docs] “AI tools authenticate with your Pylon account via OAuth and can read and update issues, accounts, and contacts within the data you can see i…”
   • [claimed-docs] “Set up complex workflows and automations to execute your business processes”
   • [probe] “PROBE runtime (recorded 2026-09-10): Pylon's docs are agent-legible — https://docs.usepylon.com/pylon-docs/llms.txt serves a live '# Pylon' …”
   • [probe] “PROBE runtime (recorded 2026-09-10): the first-party MCP server is live — a keyless JSON-RPC initialize POST to https://mcp.usepylon.com ans…”

   proof ↗⚑ flag

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

   weight 3 · round to Pylon
   Decagon~partialclaimed5/10

   Decagon offers Watchtower, which monitors conversations against natural-language criteria and can flag/surface events (compliance risks, sentiment, etc.), and Proactive Agents that act on customer signals (e.g., initiating calls, recommendations) — both function as event-triggered automation. However, there is no explicit documentation of a general-purpose rule-builder (if-event-then-action) framework that an AI-native user could configure directly; the evidence describes narrower, product-specific triggering mechanisms rather than a flexible automation-rules engine. Missing for 10: explicit rule/condition builder UI or API, documentation of arbitrary event types and action bindings, and independent verification of how these triggers are configured.

   • [claimed-docs] “Define what matters using natural language. From "mentions of frustration" to "violations of data privacy policy," Watchtower understands yo…”
   • [claimed-docs] “Define what matters using natural language. From "mentions of frustration" to "violations of data privacy policy," Watchtower understands yo…”
   • [claimed-docs] “Whether you're monitoring for compliance risks, negative sentiment, or upsell signals, Watchtower reviews every interaction against your cus…”
   • [claimed-docs] “Carry conversation history across sessions to pick up where you left off and make proactive recommendations based on customer signals.”
   • [claimed-docs] “Initiate intelligent, on-brand calls that reliably reach customers at the right moments throughout their journey.”
   • [claimed-docs] “you can define agent behavior in natural language, the same way you train human agents with SOPs”

   proof ↗⚑ flag

   Pylon✓fullprobed8/10

   Pylon has a dedicated Triggers platform docs page describing setting up complex workflows/automations tied to business processes, plus webhooks for events and an API to programmatically act on data, enabling event-driven automated actions. This directly matches rule-based automation triggering actions on events, with runtime probes confirming the API/webhook infrastructure is live. Missing for 10: detailed trigger-rule syntax/examples, independent hands-on validation of complex trigger logic, and explicit AI-agent-specific trigger configuration beyond general workflow automation.

   • [claimed-docs] “Set up complex workflows and automations to execute your business processes”
   • [claimed-docs] “Pylon's API can be used to programmatically access and take action on data within Pylon.”
   • [claimed-docs] “Receive webhooks for various events happening in Pylon.”
   • [probe] “PROBE runtime (recorded 2026-09-10): the public REST API at api.usepylon.com is live and cleanly auth-gated — a keyless GET returned HTTP 40…”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Decagon—none0/10

   Decagon's evidence covers customer-support agent features (chat, voice, email, analytics, testing, proactive outreach) but nothing addresses scheduling recurring jobs or workflows in the AI-native/automation-depth sense; proactive agents mention initiating calls at 'right moments' but no scheduling/cron-like mechanism is documented. missing for 10: any scheduler, cron/recurring trigger config, or workflow automation timing controls.

   ⚑ flag

   Pylon—none0/10

   Pylon's docs mention 'triggers' for building automations and workflows (pylon-docs-30) plus API/webhooks for programmatic action, but nothing in the evidence pack specifies time-based or recurring scheduling (e.g., cron-like jobs, scheduled runs) as opposed to event-triggered automations. No mention of a scheduler, recurring job configuration, or interval-based execution.

   • [claimed-docs] “Set up complex workflows and automations to execute your business processes”
   • [claimed-docs] “Pylon's API can be used to programmatically access and take action on data within Pylon.”
   • [claimed-docs] “Receive webhooks for various events happening in Pylon.”

   proof ↗⚑ flag

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

   weight 1 · round to Decagon
   Decagon~partialclaimed4/10

   Decagon offers some adjacent controls—technical teams retain 'visibility and control over guardrails, integrations, and versioning' and Simulations/testing validate agent behavior 'before deploying to production and with every subsequent update'—suggesting some change-management workflow exists, but there's no explicit documentation of version history browsing, diffing, review/approval workflows, or a rollback mechanism to a prior automation state. missing for 10: explicit versioning UI/history, review/approval workflow for changes, documented rollback mechanism, independent confirmation of these capabilities in use.

   • [claimed-docs] “technical teams retain full visibility and control over guardrails, integrations, and versioning”
   • [claimed-docs] “Non-technical teams can architect and iterate on agent logic with Agent Operating Procedures (AOPs) and Duet, while technical teams retain f…”
   • [claimed-docs] “Simulations, Decagon's integrated testing suite, help teams validate agent behavior across channels before deploying to production and with …”

   proof ↗⚑ flag

   Pylon—none0/10

   Pylon has automations/triggers, agent runbooks, and issue logs for monitoring outcomes, but there is no evidence of version history, diffing, review workflows, or rollback capability for automations/triggers/skills/runbooks. Missing for 10: version history for triggers/runbooks, change review/approval process, rollback to a prior automation version.

   • [claimed-docs] “Set up complex workflows and automations to execute your business processes”
   • [claimed-docs] “Write instructions in natural language to help your AI Agent handle specific scenarios.”
   • [claimed-docs] “The issue log allows you to inspect all the issues the AI agent is associated with and inspect the outcomes and steps taken by the AI.”

   proof ↗⚑ flag

Channels

1. support leaderOne agent covers chat, email, and in-app, plus the channels my customers actually use — Slack, WhatsApp, social

   weight 2 · round drawn
   Decagon~partialclaimed5/10

   Decagon clearly offers a unified agent across chat (web, mobile, messaging platforms), email, and voice, suggesting broad channel reach [decagon-docs-13][decagon-docs-14][decagon-docs-15], with proactive/session-continuity features tying channels together [decagon-docs-22][decagon-docs-28]. However, the evidence never names specific channels like Slack, WhatsApp, or social media explicitly — only generic 'messaging platforms' is mentioned. Missing for 10: explicit documentation naming Slack, WhatsApp, and social media integrations as supported channels, plus any customer proof of omnichannel handoff across these specific channels.

   • [claimed-docs] “Flexible, on-brand chat built for conversations across web, mobile, and messaging platforms.”
   • [claimed-docs] “Voice AI agents built for natural, multilingual conversations and customized to your brand.”
   • [claimed-docs] “Intelligent email that understands context, stays on brand, and handles complex customer threads.”
   • [claimed-docs] “Carry conversation history across sessions to pick up where you left off and make proactive recommendations based on customer signals.”
   • [claimed-docs] “Maintain customer context across sessions, complementing your systems of record with data portability and control.”

   proof ↗⚑ flag

   Pylon~partialclaimed5/10

   Pylon clearly supports one-agent omnichannel routing across chat, email, and in-app (chat widget, Slack, email integrations, omnichannel-support doc), but the evidence pack never explicitly documents WhatsApp or social-media channel integrations, which the story specifically calls out. missing for 10: explicit WhatsApp integration docs, explicit social media (e.g. Twitter/Instagram) channel support, and confirmation these route into the same unified agent workflow as chat/email/Slack.

   • [claimed-docs] “Pylon can support you wherever you interact with your customers.”
   • [claimed-docs] “Pylon watches for customer issues in connected customer Slack channels and automatically bundles together relevant messages and creates trac…”
   • [claimed-docs] “Connect your email addresses with Pylon to track and response to support requests over email.”
   • [claimed-docs] “Fully customizable colors, branding, and workflows * Multiple separate chat widgets with different branding and workflows”
   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”

   proof ↗⚑ flag

Languages

1. support leaderThe agent supports customers in many languages, even where my knowledge base exists only in English

   weight 2 · round to Decagon
   Decagon~partialclaimed4/10

   Only the Voice product page explicitly claims multilingual capability ('built for natural, multilingual conversations'); there is no evidence that Chat or Email channels support multiple languages, nor any documentation of translating or drawing from an English-only knowledge base to serve other languages. Missing for 10: explicit multilingual support claims for chat/email channels, description of how KB content is translated/localized, and independent verification of multilingual quality.

   • [claimed-docs] “Voice AI agents built for natural, multilingual conversations and customized to your brand.”
   • [claimed-docs] “Flexible, on-brand chat built for conversations across web, mobile, and messaging platforms.”
   • [claimed-docs] “Intelligent email that understands context, stays on brand, and handles complex customer threads.”

   proof ↗⚑ flag

   Pylon—none0/10

   No evidence in the pack mentions multilingual support, language detection, translation of knowledge base content, or the AI agent responding in customer languages other than English; docs cover agent building, knowledge base, and integrations but never address language coverage.

   ⚑ flag

Voice

1. support leaderThe agent handles phone calls — speech in, speech out — with the same knowledge and actions as chat

   weight 2 · round to Decagon
   Decagon~partialclaimed6/10

   Decagon explicitly offers a Voice product for 'natural, multilingual conversations' and can 'initiate intelligent, on-brand calls,' and its platform architecture (AOPs, integrations, guardrails) is shared across channels including chat, implying shared knowledge/actions. However, there's no explicit vendor statement confirming full parity of knowledge/actions between voice and chat, no technical detail on speech-to-speech quality, and no independent/hands-on corroboration of call handling. Missing for 10: explicit parity confirmation between voice and chat agent logic, technical/latency details of the voice pipeline, independent or customer testimonial evidence of voice call handling in production.

   • [claimed-docs] “Voice AI agents built for natural, multilingual conversations and customized to your brand.”
   • [claimed-docs] “Initiate intelligent, on-brand calls that reliably reach customers at the right moments throughout their journey.”
   • [claimed-docs] “Flexible, on-brand chat built for conversations across web, mobile, and messaging platforms.”
   • [claimed-docs] “you can define agent behavior in natural language, the same way you train human agents with SOPs”
   • [claimed-docs] “Non-technical teams can architect and iterate on agent logic with Agent Operating Procedures (AOPs) and Duet, while technical teams retain f…”

   proof ↗⚑ flag

   Pylon—none0/10

   Pylon's evidence covers omnichannel support (chat, email, Slack), AI support agents, knowledge bases, and MCP/API integrations, but nothing describes voice/phone call handling with speech-in/speech-out capability. The omnichannel doc (pylon-docs-24) is generic and doesn't mention telephony or voice at all.

   ⚑ flag

Handoff

1. support leaderWhen the agent escalates, the human gets the full conversation, a summary, and collected details — the customer never repeats themselves

   weight 3 · round to Pylon
   Decagon—none0/10

   The evidence pack contains no mention of escalation-to-human handoff, conversation summaries handed to agents, or collected-details transfer preventing repetition. Related items about cross-session context (decagon-docs-22, decagon-docs-28) address agent-to-customer continuity, not human-agent handoff, so the specific story is unevidenced despite being a plausible capability for a support AI platform.

   ⚑ flag

   Pylon~partialclaimed5/10

   Pylon's AI agent operates within the same ticket/issue thread that a human later takes over, and the issue log records the agent's steps and outcomes (pylon-docs-19), while the agent explicitly gathers internal context for the team (pylon-docs-13) and elsewhere Pylon auto-summarizes conversations for CRM sync (pylon-docs-33), suggesting summarization capability exists. However, there is no explicit documentation of an escalation-specific handoff package (conversation + AI summary + structured collected details) being automatically attached to a ticket when an agent escalates to a human. missing for 10: explicit escalation-handoff feature docs, evidence the summary/details are surfaced to the human agent at hand-off time, confirmation customer doesn't need to repeat themselves.

   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”
   • [claimed-docs] “The issue log allows you to inspect all the issues the AI agent is associated with and inspect the outcomes and steps taken by the AI.”
   • [claimed-docs] “Every day, Pylon scans your customer channels for conversations that were had. For every conversation, we use AI to summarize the details, a…”
   • [claimed-docs] “You can assign them to issues you'd like them to take a look at. This means you have full control of which customer issues your AI agent int…”

   proof ↗⚑ flag

Rules

1. support ops leadI configure when the agent must hand off — by topic, sentiment, customer tier, or explicit request — and it reliably obeys

   weight 2 · round drawn
   Decagon~partialclaimed4/10

   Decagon's AOPs let teams define agent behavior in natural language (like SOPs), which could include escalation logic, and Watchtower can flag sentiment/compliance signals, but no evidence explicitly describes configuring handoff triggers by topic, sentiment, customer tier, or explicit request, nor confirms reliable adherence to such rules. Simulations/testing-QA claims validating 'policies' are generic and don't specifically address handoff reliability. Missing for 10: explicit documentation of handoff/escalation configuration options, tier-based routing, and evidence of reliable handoff obedience (e.g., test results or case studies on escalation accuracy).

   • [claimed-docs] “you can define agent behavior in natural language, the same way you train human agents with SOPs”
   • [claimed-docs] “Define what matters using natural language. From "mentions of frustration" to "violations of data privacy policy," Watchtower understands yo…”
   • [claimed-docs] “Define what matters using natural language. From "mentions of frustration" to "violations of data privacy policy," Watchtower understands yo…”
   • [claimed-docs] “Whether you're monitoring for compliance risks, negative sentiment, or upsell signals, Watchtower reviews every interaction against your cus…”
   • [claimed-docs] “Non-technical teams can architect and iterate on agent logic with Agent Operating Procedures (AOPs) and Duet, while technical teams retain f…”
   • [claimed-docs] “Simulations, Decagon's integrated testing suite, help teams validate agent behavior across channels before deploying to production and with …”

   proof ↗⚑ flag

   Pylon~partialclaimed4/10

   Pylon's Support Agent framework lets admins write natural-language runbooks for 'specific scenarios' and assign only certain issues to the agent, plus monitor outcomes via the issue log — this could be used to script handoff conditions, but there is no explicit documentation of built-in triggers for topic, sentiment, or customer-tier-based escalation, nor any evidence about reliability/guardrails ensuring the agent 'reliably obeys' handoff rules. Missing for 10: dedicated sentiment/tier/topic escalation configuration UI, explicit-request handoff trigger documentation, and evidence (docs or hands-on) of enforcement reliability.

   • [claimed-docs] “Write instructions in natural language to help your AI Agent handle specific scenarios.”
   • [claimed-docs] “You can assign them to issues you'd like them to take a look at. This means you have full control of which customer issues your AI agent int…”
   • [claimed-docs] “The issue log allows you to inspect all the issues the AI agent is associated with and inspect the outcomes and steps taken by the AI.”
   • [claimed-docs] “Skills are reusable instructions that teach Pylon agents how to handle specific workflows consistently.”
   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”

   proof ↗⚑ flag

Hallucination

1. ai-native userGuardrails stop the agent from inventing policies, prices, or promises — off-knowledge questions get a safe decline, not a guess

   weight 3 · round to Decagon
   Decagon~partialclaimed4/10

   Decagon provides AOPs to define agent behavior/policies in natural language and a testing suite (Simulations/Duet) that verifies agents 'respond accurately, follow policies' plus Watchtower monitoring for compliance violations, which are the building blocks for guardrails — but no evidence explicitly describes a safe-decline behavior for off-knowledge questions versus fabricating answers. missing for 10: explicit documentation or examples of the agent refusing/declining out-of-scope questions rather than hallucinating, and independent verification that guardrails actually prevent invented prices/policies in practice.

   • [claimed-docs] “you can define agent behavior in natural language, the same way you train human agents with SOPs”
   • [claimed-docs] “Use Duet to easily generate tests covering diverse pathways that verify whether agents respond accurately, follow policies, and reflect your…”
   • [claimed-docs] “Simulations, Decagon's integrated testing suite, help teams validate agent behavior across channels before deploying to production and with …”
   • [claimed-docs] “Define what matters using natural language. From "mentions of frustration" to "violations of data privacy policy," Watchtower understands yo…”
   • [claimed-docs] “Whether you're monitoring for compliance risks, negative sentiment, or upsell signals, Watchtower reviews every interaction against your cus…”

   proof ↗⚑ flag

   Pylon~partialclaimed3/10

   Pylon's Support Agent is grounded in a curated knowledge base and runbooks/skills that define scenario-specific instructions, which implicitly limits it to trained content rather than free invention, and 'deflect using content' suggests answers are content-bound. However, there is no explicit documentation of a safe-decline behavior for off-knowledge questions, confidence thresholds, or anti-hallucination guardrails around prices/policies. Missing for 10: explicit safe-decline/escalation mechanism for unknown questions, documentation of hallucination prevention, and evidence of guardrails specifically around prices/policies/promises.

   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”
   • [claimed-docs] “Write instructions in natural language to help your AI Agent handle specific scenarios.”
   • [claimed-docs] “Skills are reusable instructions that teach Pylon agents how to handle specific workflows consistently.”
   • [claimed-docs] “A dedicated place to host your support content, including question-and-answer style articles, internal runbooks, and more -- all supercharge…”

   proof ↗⚑ flag

Supervision

1. support ops leadLaunch in a supervised mode where the agent drafts replies for human approval before anything reaches a customer

   weight 2 · round drawn
   Decagon—none0/10

   Decagon's evidence covers testing/simulation (Simulations, Duet), experiments, guardrails, and monitoring (Watchtower), but nothing describes a supervised/human-in-the-loop 'draft-for-approval' mode where a human must approve each reply before it reaches a customer. Testing/QA and experiments happen pre-production or on traffic splits, not as a live approval queue for individual replies.

   ⚑ flag

   Pylon—none0/10

   Pylon's docs describe agent deployment controls (assigning which issues the agent handles, testing/simulating responses, and an issue log for post-hoc review) but nowhere document a supervised 'draft-for-human-approval-before-send' mode; the language instead emphasizes agents 'taking action' autonomously once deployed.

   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”
   • [claimed-docs] “You can assign them to issues you'd like them to take a look at. This means you have full control of which customer issues your AI agent int…”
   • [claimed-docs] “The issue log allows you to inspect all the issues the AI agent is associated with and inspect the outcomes and steps taken by the AI.”
   • [claimed-docs] “Simulate an interaction with the AI and see how it handles different questions.”

   proof ↗⚑ flag

Topic controls

1. support ops leadI mark topics as human-only — legal threats, cancellations, security — and the agent never freelances on them

   weight 2 · round to Decagon
   Decagon~partialclaimed5/10

   Decagon's AOPs let teams define agent behavior/escalation rules in natural language, and 'guardrails' are described as retained under technical team control, which could support marking certain topics as human-only; Watchtower can flag legal/compliance/sentiment topics for review. However, there's no explicit documentation of a dedicated 'human-only topic' or hard-escalation feature, nor any evidence (hands-on or audit) confirming the agent never engages on flagged categories. Missing for 10: explicit human-only/topic-exclusion configuration feature, proof/testing that the agent reliably refuses or escalates on those topics, and independent verification of enforcement.

   • [claimed-docs] “technical teams retain full visibility and control over guardrails, integrations, and versioning”
   • [claimed-docs] “you can define agent behavior in natural language, the same way you train human agents with SOPs”
   • [claimed-docs] “Non-technical teams can architect and iterate on agent logic with Agent Operating Procedures (AOPs) and Duet, while technical teams retain f…”
   • [claimed-docs] “Define what matters using natural language. From "mentions of frustration" to "violations of data privacy policy," Watchtower understands yo…”
   • [claimed-docs] “Define what matters using natural language. From "mentions of frustration" to "violations of data privacy policy," Watchtower understands yo…”
   • [claimed-docs] “Whether you're monitoring for compliance risks, negative sentiment, or upsell signals, Watchtower reviews every interaction against your cus…”

   proof ↗⚑ flag

   Pylon~partialclaimed4/10

   Pylon documents assignment-based control—agents only interact with issues explicitly assigned to them, giving admins 'full control of which customer issues your AI agent interacts with'—which could be used to withhold sensitive categories from the agent, and runbooks/skills let you write natural-language handling instructions. But there is no documented feature for marking specific topics (legal threats, cancellations, security) as categorically human-only or any guardrail that blocks the agent from acting on flagged topic types. Missing for 10: an explicit topic/category exclusion or block-list mechanism, enforcement guarantees against agent 'freelancing' on excluded topics, and independent verification that assignment-based control reliably prevents agent action on sensitive categories.

   • [claimed-docs] “You can assign them to issues you'd like them to take a look at. This means you have full control of which customer issues your AI agent int…”
   • [claimed-docs] “Write instructions in natural language to help your AI Agent handle specific scenarios.”
   • [claimed-docs] “The issue log allows you to inspect all the issues the AI agent is associated with and inspect the outcomes and steps taken by the AI.”
   • [claimed-docs] “Skills are reusable instructions that teach Pylon agents how to handle specific workflows consistently.”

   proof ↗⚑ flag

Analytics

1. support leaderDashboards show resolution rate, CSAT, handoff rate, and cost per resolution — the numbers I report to my exec team

   weight 3 · round drawn
   Decagon~partialclaimed5/10

   Decagon's Insights & Reporting product includes customizable dashboards, visual heatmaps for key metrics, and 'Ask AI' conversational analytics for querying conversation trends, which supports general exec-reporting use cases. However, the evidence never explicitly names resolution rate, CSAT, handoff rate, or cost-per-resolution as tracked/reported metrics. missing for 10: explicit confirmation that CSAT, resolution rate, handoff rate, and cost-per-resolution are specific dashboard metrics; independent/customer corroboration of these exact KPIs being reported to execs.

   • [claimed-docs] “Ask open-ended questions like “Why are customers requesting refunds?” to instantly analyze customer conversations.”
   • [claimed-docs] “Customizable visual heatmaps... Quickly identify spikes or dips in key metrics.”
   • [claimed-docs] “Ask AI powers deeper analysis through flexible, conversational queries.”

   proof ↗⚑ flag

   Pylon~partialclaimed5/10

   Pylon docs confirm built-in analytics dashboards with 'common support metrics' filterable by attributes, supporting general resolution/ticket reporting, but no evidence explicitly names CSAT, handoff rate, or cost-per-resolution as tracked metrics. missing for 10: explicit documentation of CSAT scoring, handoff-rate metric, and cost-per-resolution calculation in dashboards.

   • [claimed-docs] “Pylon comes with a number of default analytics dashboards with common support metrics. All dashboards are filterable by a wide selection of …”

   proof ↗⚑ flag

Insights

1. support leaderThe platform clusters conversations by topic and surfaces emerging product issues before they spike ticket volume

   weight 1 · round to Decagon
   Decagon~partialclaimed7/10

   Decagon's Insights & Reporting and Watchtower products support natural-language querying of conversations (e.g., 'Why are customers requesting refunds?'), heatmaps to spot spikes/dips in key metrics, and custom flagging criteria across every interaction, which together enable topic-level pattern detection and early issue surfacing. However, the evidence never explicitly describes automated topic clustering or a proactive 'before ticket volume spikes' alerting mechanism—these are inferred from adjacent features. Missing for 10: explicit description of automatic conversation clustering by topic, independent/hands-on evidence of early trend detection preventing ticket spikes, and case-study proof of this specific insight workflow in production.

   • [claimed-docs] “Ask open-ended questions like “Why are customers requesting refunds?” to instantly analyze customer conversations.”
   • [claimed-docs] “Customizable visual heatmaps... Quickly identify spikes or dips in key metrics.”
   • [claimed-docs] “Ask AI powers deeper analysis through flexible, conversational queries.”
   • [claimed-docs] “Whether you're monitoring for compliance risks, negative sentiment, or upsell signals, Watchtower reviews every interaction against your cus…”
   • [claimed-docs] “Define what matters using natural language. From "mentions of frustration" to "violations of data privacy policy," Watchtower understands yo…”
   • [claimed-docs] “It automatically detects knowledge gaps and generates content drafts based on how your best human agents resolved those same issues, so your…”

   proof ↗⚑ flag

   Pylon—none0/10

   Evidence shows generic analytics dashboards with filterable metrics (pylon-docs-29) and AI summarization of Slack conversations synced to Salesforce (pylon-docs-33), but nothing describes topic clustering of conversations or proactive surfacing of emerging product issues before ticket volume spikes.

   • [claimed-docs] “Pylon comes with a number of default analytics dashboards with common support metrics. All dashboards are filterable by a wide selection of …”
   • [claimed-docs] “Every day, Pylon scans your customer channels for conversations that were had. For every conversation, we use AI to summarize the details, a…”

   proof ↗⚑ flag

Helpdesk

1. developerThe agent runs inside my existing helpdesk — Zendesk, Salesforce, Intercom — or standalone, syncing tickets and context both ways

   weight 3 · round to Decagon
   Decagon~partialclaimed4/10

   Decagon's integrations page claims no-code integrations and system-of-record data portability, and Browser Actions/MCP posts describe connecting to arbitrary systems including ones without native integrations, implying support for helpdesk platforms like Zendesk/Salesforce/Intercom, but no evidence explicitly names these tools or describes ticket-level two-way sync. Missing for 10: named connectors/case studies for Zendesk, Salesforce, or Intercom, explicit description of bidirectional ticket-context syncing, and confirmation of standalone deployment mode.

   • [claimed-docs] “no custom code required”
   • [claimed-docs] “with no custom code required”
   • [claimed-docs] “Decagon integrates with identity providers like Okta and Microsoft Entra, enabling secure access across systems without additional passwords…”
   • [claimed-docs] “Maintain customer context across sessions, complementing your systems of record with data portability and control.”
   • [claimed-docs] “Browser Actions gives your agent a way through computer use. It extends the agent you've already built so it can log in, navigate, and compl…”
   • [claimed-docs] “lets your Decagon agent access and complete tasks inside systems where there isn’t a traditional integration available”
   • [claimed-docs] “Bridging that gap requires an infrastructure layer purpose-built to curate, scope, and evaluate how tools are actually used.”

   proof ↗⚑ flag

   Pylon~partialclaimed3/10

   Evidence shows a one-way sync of AI-summarized conversations into Salesforce Accounts and general 'omnichannel' support language, but there is no evidence of the AI agent embedding inside Zendesk or Intercom, nor of two-way ticket/context syncing with any named helpdesk — Pylon's docs otherwise position it as the standalone system of record. Missing for 10: Zendesk/Intercom integration evidence, bidirectional ticket sync (not just one-way conversation summaries), and confirmation the agent itself operates 'inside' another helpdesk's UI/workflow.

   • [claimed-docs] “Every day, Pylon scans your customer channels for conversations that were had. For every conversation, we use AI to summarize the details, a…”
   • [claimed-docs] “Pylon can support you wherever you interact with your customers.”
   • [claimed-docs] “Using a combination of Webhooks, API, and/or Pylon MCP, you can connect your agent to ticketing workflows in Pylon.”

   proof ↗⚑ flag

Freshness

1. support ops leadKnowledge stays current automatically — the agent re-syncs sources on a schedule or on change, not via manual re-uploads

   weight 2 · round to Pylon
   Decagon—none0/10

   The evidence pack covers knowledge gap detection and content suggestions (docs-10/18), integrations without custom code, and agent iteration via Duet, but nowhere mentions automatic re-syncing of knowledge sources on a schedule or on change — the closest analog (Suggestions) generates draft content for humans to review/publish, not an automated re-sync pipeline. Missing for 10: any mention of scheduled/triggered re-ingestion of source documents, sync frequency, or change-detection on connected knowledge bases.

   • [claimed-docs] “It automatically detects knowledge gaps and generates content drafts based on how your best human agents resolved those same issues, so your…”
   • [claimed-docs] “It automatically detects knowledge gaps and generates content drafts based on how your best human agents resolved those same issues”

   proof ↗⚑ flag

   Pylon~partialclaimed4/10

   Pylon's knowledge base and training-data docs mention connecting external knowledge sources (pylon-docs-22, pylon-docs-23), and product-data sync can be disabled mid-run (pylon-docs-8), implying some sync mechanism exists, but there is no documentation of a re-sync schedule, change-detection triggers, or automatic re-indexing cadence for knowledge sources. missing for 10: explicit scheduling/frequency controls for knowledge source re-sync, change-detection or webhook-triggered re-sync of external knowledge, and any evidence contradicting or confirming this works hands-on.

   • [claimed-docs] “Make them even more powerful by connecting any external sources of knowledge you have!”
   • [claimed-docs] “A dedicated place to host your support content, including question-and-answer style articles, internal runbooks, and more -- all supercharge…”
   • [claimed-docs] “Disabling a product-data sync now stops any run already in progress”

   proof ↗⚑ flag

Gaps

1. support ops leadThe platform surfaces knowledge gaps and conflicting content that cause the agent to miss or fumble questions

   weight 1 · round to Decagon
   Decagon✓fullclaimed7/10

   Decagon's Suggestions product explicitly automates detection of knowledge gaps and drafts content based on how top human agents resolved similar issues, directly addressing the story's core need, and Insights/Watchtower let ops teams query conversations to surface where the agent struggles or conflicts arise. Missing for 10: independent/hands-on verification of gap detection accuracy, and no explicit mention of surfacing 'conflicting content' across knowledge sources rather than just gaps.

   • [claimed-docs] “It automatically detects knowledge gaps and generates content drafts based on how your best human agents resolved those same issues, so your…”
   • [claimed-docs] “It automatically detects knowledge gaps and generates content drafts based on how your best human agents resolved those same issues”
   • [claimed-docs] “Ask open-ended questions like “Why are customers requesting refunds?” to instantly analyze customer conversations.”
   • [claimed-docs] “Define what matters using natural language. From "mentions of frustration" to "violations of data privacy policy," Watchtower understands yo…”
   • [claimed-docs] “Customizable visual heatmaps... Quickly identify spikes or dips in key metrics.”

   proof ↗⚑ flag

   Pylon—none0/10

   Pylon documents training-data ingestion, a knowledge base, agent simulation/testing, and issue logs for reviewing agent outcomes, but nothing in the evidence describes a feature that proactively surfaces knowledge gaps or flags conflicting content driving agent misses. This is a fair axis for a support-agent platform (comparable products ship content-quality/coverage analytics), so absence of evidence yields 'none' rather than 'na'.

   • [claimed-docs] “The issue log allows you to inspect all the issues the AI agent is associated with and inspect the outcomes and steps taken by the AI.”
   • [claimed-docs] “Simulate an interaction with the AI and see how it handles different questions.”
   • [claimed-docs] “Make them even more powerful by connecting any external sources of knowledge you have!”
   • [claimed-docs] “A dedicated place to host your support content, including question-and-answer style articles, internal runbooks, and more -- all supercharge…”

   proof ↗⚑ flag

Grounding

1. ai-native userEvery answer is grounded in my own content and shows which article or source it drew from

   weight 3 · round to Pylon
   Decagon—none0/10

   Decagon's evidence describes knowledge-gap detection, AOP generation, and content suggestions (docs-10, docs-18) but nothing shows that end-user-facing answers actually cite or display the specific article/source they were grounded in. Missing for 10: any documentation of inline citations, source attribution UI, or 'view source' feature in chat/voice/email responses.

   • [claimed-docs] “It automatically detects knowledge gaps and generates content drafts based on how your best human agents resolved those same issues, so your…”
   • [claimed-docs] “It automatically detects knowledge gaps and generates content drafts based on how your best human agents resolved those same issues”
   • [claimed-docs] “Flexible, on-brand chat built for conversations across web, mobile, and messaging platforms.”

   proof ↗⚑ flag

   Pylon~partialclaimed5/10

   Pylon's Support Agents are documented to answer/deflect using a dedicated Knowledge Base and connected external knowledge sources (pylon-docs-13, pylon-docs-22, pylon-docs-23), which supports grounding in the user's own content, but there is no evidence that responses explicitly cite or display which specific article/source was used to generate an answer. missing for 10: explicit citation/source-attribution UI in agent answers, evidence of per-answer source linking, independent confirmation of grounding accuracy.

   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”
   • [claimed-docs] “Make them even more powerful by connecting any external sources of knowledge you have!”
   • [claimed-docs] “A dedicated place to host your support content, including question-and-answer style articles, internal runbooks, and more -- all supercharge…”
   • [claimed-docs] “Skills are reusable instructions that teach Pylon agents how to handle specific workflows consistently.”

   proof ↗⚑ flag

Ingestion

1. support ops leadThe agent ingests my help center, docs, past tickets, and internal wikis as knowledge sources without manual re-authoring

   weight 3 · round to Pylon
   Decagon~partialclaimed4/10

   Decagon's integrations page claims 'no custom code required' connections (docs-19/26) and its Suggestions product analyzes help-center content and past agent resolutions to fill knowledge gaps (docs-10/18), implying some ingestion of existing content, but there is no explicit documentation naming help center, internal wikis, docs, and past tickets as ingestible knowledge sources without re-authoring. missing for 10: explicit list/documentation of supported knowledge source connectors (help center, wikis, ticket systems), evidence of automatic re-indexing without manual content rewriting, and independent confirmation of successful multi-source ingestion.

   • [claimed-docs] “It automatically detects knowledge gaps and generates content drafts based on how your best human agents resolved those same issues, so your…”
   • [claimed-docs] “It automatically detects knowledge gaps and generates content drafts based on how your best human agents resolved those same issues”
   • [claimed-docs] “no custom code required”
   • [claimed-docs] “with no custom code required”

   proof ↗⚑ flag

   Pylon~partialclaimed5/10

   Pylon documents a 'training-data' page for connecting external knowledge sources and a Knowledge Base feature for hosting support content and runbooks, suggesting some support for knowledge grounding, but there is no concrete evidence of automated ingestion of help center content, past tickets, or internal wikis without manual re-authoring. Missing for 10: explicit documentation of connectors for help center/docs platforms, wiki integrations (Confluence/Notion), automatic ticket-history ingestion, and any hands-on evidence confirming these sources sync without manual re-entry.

   • [claimed-docs] “Make them even more powerful by connecting any external sources of knowledge you have!”
   • [claimed-docs] “A dedicated place to host your support content, including question-and-answer style articles, internal runbooks, and more -- all supercharge…”
   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”

   proof ↗⚑ flag

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

   weight 2 · round to Pylon
   Decagon—none0/10

   No evidence of a public API at all — the openapi probe returned 404 across all candidate paths, and none of the docs describe an API that mirrors UI capabilities like AOP configuration, Duet, Watchtower, or experiments. Absence of evidence for this applicable capability yields none.

   • [probe] “PROBE openapi: all candidate paths 404 (https://decagon.ai/openapi.json, https://decagon.ai/swagger.json, https://decagon.ai/api/openapi.jso…”

   proof ↗⚑ flag

   Pylon~partialprobed5/10

   Pylon documents a public REST API and webhooks for programmatically accessing/acting on issues, accounts, and contacts (pylon-docs-31, pylon-docs-32, pylon-docs-4), plus an MCP server that lets AI tools read/update the same core objects (pylon-docs-34, pylon-probe-rt-3). However, there's no evidence the API/MCP surface covers the full breadth of UI capabilities shown in the changelog (custom object forms, analytics dashboards, chat widget branding/customization, knowledge base authoring, triggers/automation config) — these appear UI-only in the evidence pack. Missing for 10: documented API/MCP parity for analytics dashboards, chat widget customization, knowledge base management, and workflow/trigger configuration.

   • [claimed-docs] “Pylon's API can be used to programmatically access and take action on data within Pylon.”
   • [claimed-docs] “Receive webhooks for various events happening in Pylon.”
   • [claimed-docs] “Added a GET /task-statuses API endpoint for enumerating configured task statuses”
   • [claimed-docs] “AI tools authenticate with your Pylon account via OAuth and can read and update issues, accounts, and contacts within the data you can see i…”
   • [probe] “PROBE runtime (recorded 2026-09-10): the public REST API at api.usepylon.com is live and cleanly auth-gated — a keyless GET returned HTTP 40…”
   • [probe] “PROBE runtime (recorded 2026-09-10): the first-party MCP server is live — a keyless JSON-RPC initialize POST to https://mcp.usepylon.com ans…”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Decagon—none0/10

   Decagon's evidence pack contains no documented data-export feature, open-format export tooling, or account-deletion/portability workflow; the only tangential mention ("data portability and control" in decagon-docs-28) is vague marketing language about maintaining conversation context, not a concrete export/exit mechanism, and the probe shows no public API/OpenAPI spec that could support programmatic data extraction.

   • [claimed-docs] “Maintain customer context across sessions, complementing your systems of record with data portability and control.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://decagon.ai/openapi.json, https://decagon.ai/swagger.json, https://decagon.ai/api/openapi.jso…”

   proof ↗⚑ flag

   Pylon—none0/10

   Evidence shows a REST API and webhooks for programmatic access to issues/accounts/contacts, but nothing documents a bulk data-export feature, open-format dump, or data-portability/account-closure workflow that would let a user extract all their data and leave.

   • [claimed-docs] “Pylon's API can be used to programmatically access and take action on data within Pylon.”
   • [claimed-docs] “Receive webhooks for various events happening in Pylon.”
   • [probe] “PROBE runtime (recorded 2026-09-10): the public REST API at api.usepylon.com is live and cleanly auth-gated — a keyless GET returned HTTP 40…”

   proof ↗⚑ flag

Pricing

1. support leaderPricing is outcome-based and published — I pay per resolution with caps and controls, not an opaque enterprise quote

   weight 2 · round drawn
   Decagon—none0/10

   No evidence pack item mentions pricing, resolution-based billing, caps, controls, or published pricing pages — all evidence concerns product features (AOPs, Duet, Watchtower, integrations, security) rather than pricing model. Absence of evidence for this applicable axis yields 'none'. Missing for 10: published pricing page, resolution-based billing structure, caps/controls documentation, any pricing transparency claims.

   ⚑ flag

   Pylon—none0/10

   No evidence anywhere in the pack of outcome-based or per-resolution pricing, published pricing tiers, caps, or usage-based billing controls; Pylon's documentation covers product features, agents, and APIs but is silent on pricing model or billing transparency.

   ⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round drawn
   Decagon—none0/10

   No evidence pack item mentions data residency, region selection, or storage location controls; security page content covers JWTs and SSO but not data residency options. Missing for 10: any mention of regional data storage, residency compliance (e.g., EU/US hosting options), or customer-facing controls to choose storage location.

   ⚑ flag

   Pylon—none0/10

   No evidence anywhere in the pack mentions data residency, region selection, or storage location options; only compliance/certification via Vanta is mentioned, which does not address data residency choice. Missing for 10: any mention of regional data centers, residency options, or ability to select storage location.

   • [claimed-docs] “Our compliance and certification are managed by Vanta and our incredible audit partners.”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Decagon—none0/10

   No evidence in the pack addresses data usage for AI model training or an opt-out/no-training policy; the security page covers JWT tokens and SSO but not training data practices.

   ⚑ flag

   Pylon—none0/10

   Evidence pack mentions Pylon's compliance is managed via Vanta (SOC2-type certification) but there is no mention of any AI-training data opt-out, data usage policy for model training, or controls letting users prevent their data from being used to train AI models. Missing for 10: explicit AI-training opt-out/data-usage policy, contractual or product-level control preventing training use, and any documentation addressing this specific privacy concern.

   • [claimed-docs] “Our compliance and certification are managed by Vanta and our incredible audit partners.”

   proof ↗⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to Decagon
   Decagon~partialclaimed3/10

   Decagon only vaguely references 'data portability and control' alongside customer context retention, and short-lived JWT tokens discarded after each session, but there is no explicit documentation of configurable data retention periods, deletion APIs, or user-facing controls to purge stored customer data. missing for 10: explicit retention policy/settings, a documented deletion mechanism or API, and independent verification that deletion requests are honored.

   • [claimed-docs] “Maintain customer context across sessions, complementing your systems of record with data portability and control.”
   • [claimed-docs] “Short-lived JWT tokens give AI agents real-time access to customer systems, scoped for minimal privilege and discarded after each session.”

   proof ↗⚑ flag

   Pylon—none0/10

   The evidence pack shows security/compliance certification via Vanta and general data handling but contains no documentation of data retention periods, deletion policies, or user/admin controls to delete or export data. Missing for 10: retention policy documentation, deletion/export controls, data lifecycle settings.

   • [claimed-docs] “Our compliance and certification are managed by Vanta and our incredible audit partners.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Decagon—none0/10

   No evidence in the pack addresses telemetry/usage-tracking opt-out controls; the security and product pages cover access control, JWT tokens, and SSO but never mention analytics/telemetry opt-out settings for end users. Missing for 10: any documentation of a telemetry toggle, data-collection opt-out mechanism, or privacy settings page.

   ⚑ flag

   Pylon—none0/10

   No evidence Pylon offers any telemetry opt-out or usage-tracking controls; evidence only covers compliance certification (Vanta) and product features, not telemetry settings.

   ⚑ flag

Personalization

1. support leaderAnswers use the customer's live data — plan, order status, account history — not just generic help articles

   weight 2 · round drawn
   Decagon~partialclaimed6/10

   Decagon's docs describe real-time, scoped access to customer systems via short-lived JWTs, MCP-based tool integrations, and Browser Actions that let agents log into and pull data from any system (including those without native integrations), which supports live-data-driven answers rather than static help content. However, there is no concrete example or case study showing an actual answer surfacing a customer's plan, order status, or account history — the evidence is architectural/capability-level rather than demonstrated output. Missing for 10: a documented example or case study showing live plan/order/account data appearing in an actual customer-facing answer, and independent verification that this works in production.

   • [claimed-docs] “Short-lived JWT tokens give AI agents real-time access to customer systems, scoped for minimal privilege and discarded after each session.”
   • [claimed-docs] “Bridging that gap requires an infrastructure layer purpose-built to curate, scope, and evaluate how tools are actually used.”
   • [claimed-docs] “Browser Actions gives your agent a way through computer use. It extends the agent you've already built so it can log in, navigate, and compl…”
   • [claimed-docs] “lets your Decagon agent access and complete tasks inside systems where there isn’t a traditional integration available”
   • [claimed-docs] “no custom code required”
   • [claimed-docs] “Decagon integrates with identity providers like Okta and Microsoft Entra, enabling secure access across systems without additional passwords…”

   proof ↗⚑ flag

   Pylon~partialclaimed6/10

   Pylon documents product-data syncs, Account Fields, custom objects, and Connectors/Custom API tools/MCP that let AI Support Agents pull in live account/product data (e.g., pylon-docs-8, pylon-docs-21, pylon-docs-22, pylon-docs-33) rather than relying solely on the knowledge base, and Skills/Runbooks let agents act on that data during resolution (pylon-docs-13, pylon-docs-20). However there's no first-party or independent case study showing an actual generated answer citing live plan/order-status/account-history data in a real resolution. Missing for 10: concrete example/transcript of an AI answer referencing live order status or plan data, and independent verification that synced data is actually surfaced in agent responses rather than just accessible to admins.

   • [claimed-docs] “Disabling a product-data sync now stops any run already in progress”
   • [claimed-docs] “If a system does not provide an MCP server, an administrator can define a Custom API tool that agents can use to hit internal or third party…”
   • [claimed-docs] “Make them even more powerful by connecting any external sources of knowledge you have!”
   • [claimed-docs] “Every day, Pylon scans your customer channels for conversations that were had. For every conversation, we use AI to summarize the details, a…”
   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”
   • [claimed-docs] “Skills are reusable instructions that teach Pylon agents how to handle specific workflows consistently.”
   • [claimed-docs] “AI tools authenticate with your Pylon account via OAuth and can read and update issues, accounts, and contacts within the data you can see i…”

   proof ↗⚑ flag

Reasoning

1. support leaderThe agent asks clarifying questions and works through multi-step troubleshooting instead of dumping one canned answer

   weight 2 · round drawn
   Decagon~partialclaimed5/10

   Decagon docs describe AOPs that define multi-step agent behavior like human SOPs and mention agents carrying context across sessions and taking multi-step actions (browser actions, integrations), which implies some troubleshooting flow, but there is no direct documentation or example showing the agent asking clarifying questions or walking through iterative multi-step troubleshooting dialogues. missing for 10: concrete example/transcript of clarifying-question behavior, documentation explicitly describing multi-turn troubleshooting logic, independent/hands-on evidence confirming this behavior in practice.

   • [claimed-docs] “you can define agent behavior in natural language, the same way you train human agents with SOPs”
   • [claimed-docs] “Carry conversation history across sessions to pick up where you left off and make proactive recommendations based on customer signals.”
   • [claimed-docs] “lets your Decagon agent access and complete tasks inside systems where there isn’t a traditional integration available”

   proof ↗⚑ flag

   Pylon~partialclaimed5/10

   Pylon's Support Agent docs describe multi-step behavior—runbooks with natural-language instructions for specific scenarios, skills as reusable workflow instructions, gathering internal context, and taking action—plus an issue log showing 'outcomes and steps taken by the AI' (pylon-docs-13, pylon-docs-15, pylon-docs-20, pylon-docs-19). However, there is no explicit documentation that the agent proactively asks clarifying questions to the customer rather than issuing a single canned reply; the story's core 'asks clarifying questions' behavior is only implied, not confirmed. Missing for 10: explicit product documentation or example of the agent asking clarifying follow-up questions mid-conversation, and independent/hands-on evidence of multi-turn troubleshooting flows in practice.

   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”
   • [claimed-docs] “Write instructions in natural language to help your AI Agent handle specific scenarios.”
   • [claimed-docs] “Skills are reusable instructions that teach Pylon agents how to handle specific workflows consistently.”
   • [claimed-docs] “The issue log allows you to inspect all the issues the AI agent is associated with and inspect the outcomes and steps taken by the AI.”
   • [claimed-docs] “Simulate an interaction with the AI and see how it handles different questions.”

   proof ↗⚑ flag

Resolution

1. support leaderThe agent fully resolves a meaningful share of conversations end-to-end — measured as resolutions, not mere deflections or bounces

   weight 3 · round to Decagon
   Decagon~partialclaimed4/10

   Decagon's docs emphasize automation infrastructure (AOPs, Duet, Browser Actions, integrations) and analytics (Watchtower, Insights) but provide no quantified resolution-rate metrics, no third-party benchmark, and the one customer quote (Duolingo) speaks to maintenance effort, not resolution outcomes. Missing for 10: independent or customer-reported resolution-rate figures, a clear definition/measurement of 'resolution' vs deflection, and case studies quantifying end-to-end conversation completion rather than agent capability lists.

   • [claimed-docs] “Browser Actions gives your agent a way through computer use. It extends the agent you've already built so it can log in, navigate, and compl…”
   • [claimed-docs] “lets your Decagon agent access and complete tasks inside systems where there isn’t a traditional integration available”
   • [claimed-docs] “With the previous vendor, at least half my week was dedicated to maintaining their system. With Decagon, it’s been a night-and-day differenc…”
   • [claimed-docs] “Define what matters using natural language. From "mentions of frustration" to "violations of data privacy policy," Watchtower understands yo…”
   • [claimed-docs] “Whether you're monitoring for compliance risks, negative sentiment, or upsell signals, Watchtower reviews every interaction against your cus…”

   proof ↗⚑ flag

   Pylon~partialclaimed3/10

   Pylon's own docs describe the Support Agent primarily in terms of 'deflecting' questions and taking actions, with an issue log to inspect outcomes/steps, but there is no first-party or independent metric quantifying full end-to-end resolutions distinct from deflections or bounces. missing for 10: quantified resolution-rate reporting, evidence distinguishing true resolutions from deflections, independent/customer validation of resolution outcomes.

   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”
   • [claimed-docs] “You can assign them to issues you'd like them to take a look at. This means you have full control of which customer issues your AI agent int…”
   • [claimed-docs] “The issue log allows you to inspect all the issues the AI agent is associated with and inspect the outcomes and steps taken by the AI.”
   • [claimed-docs] “Pylon comes with a number of default analytics dashboards with common support metrics. All dashboards are filterable by a wide selection of …”

   proof ↗⚑ flag

Voice

1. support leaderI control the agent's tone and brand voice, and it stays consistent across topics and languages

   weight 1 · round to Decagon
   Decagon~partialclaimed7/10

   Decagon's docs show brand-voice consistency built into multiple surfaces: chat, voice (multilingual), and email are all described as 'on-brand', and AOPs let support leaders define agent behavior/tone in natural language like SOPs (docs-13,14,15,16). Testing/QA and Experiments explicitly validate tone/brand across pathways and let leaders 'refine tone' safely before and after deployment (docs-11,29,32). Missing for 10: independent/hands-on evidence that tone actually stays consistent across many topics and languages in production, and no explicit mention of cross-language consistency for chat/email (only voice is called multilingual).

   • [claimed-docs] “Flexible, on-brand chat built for conversations across web, mobile, and messaging platforms.”
   • [claimed-docs] “Voice AI agents built for natural, multilingual conversations and customized to your brand.”
   • [claimed-docs] “Intelligent email that understands context, stays on brand, and handles complex customer threads.”
   • [claimed-docs] “you can define agent behavior in natural language, the same way you train human agents with SOPs”
   • [claimed-docs] “Use Duet to easily generate tests covering diverse pathways that verify whether agents respond accurately, follow policies, and reflect your…”
   • [claimed-docs] “Simulations, Decagon's integrated testing suite, help teams validate agent behavior across channels before deploying to production and with …”
   • [claimed-docs] “Whether you’re refining tone, adjusting refund logic, or trialing a new onboarding experience, experimentation makes it safe to test, learn,…”

   proof ↗⚑ flag

   Pylon~partialclaimed3/10

   Pylon's AI Agent can be configured with natural-language runbooks and reusable 'skills' that dictate how it handles specific scenarios, which could be used to encode tone/brand-voice guidance, but the docs never explicitly mention persona/tone control or consistency across languages. missing for 10: explicit tone/brand-voice configuration settings, evidence of multilingual consistency, and any customer/independent proof the agent's voice stays consistent across topics.

   • [claimed-docs] “Write instructions in natural language to help your AI Agent handle specific scenarios.”
   • [claimed-docs] “Skills are reusable instructions that teach Pylon agents how to handle specific workflows consistently.”
   • [claimed-docs] “Support Agents can deflect customer questions using content, gather internal context for your team, and take action.”

   proof ↗⚑ flag

Qa

1. support ops leadAI conversations get ongoing QA — scored samples, flagged failures, and a review loop that feeds fixes back into the agent

   weight 1 · round to Decagon
   Decagon✓fullclaimed8/10

   Decagon documents a dedicated Testing & QA suite (Simulations) that validates agent behavior pre-deploy and on updates, plus Watchtower which reviews every live interaction against custom flagging criteria (compliance, sentiment, frustration) and surfaces failures, and Duet which auto-generates tests/AOPs and iterates on the agent based on conversation gaps — together covering scored/flagged QA and a feedback loop into agent fixes. missing for 10: no independent/hands-on corroboration of scoring accuracy or the closed-loop fix cycle, and no explicit description of 'sampling' methodology for QA review.

   • [claimed-docs] “Define what matters using natural language. From "mentions of frustration" to "violations of data privacy policy," Watchtower understands yo…”
   • [claimed-docs] “Use Duet to easily generate tests covering diverse pathways that verify whether agents respond accurately, follow policies, and reflect your…”
   • [claimed-docs] “Define what matters using natural language. From "mentions of frustration" to "violations of data privacy policy," Watchtower understands yo…”
   • [claimed-docs] “Simulations, Decagon's integrated testing suite, help teams validate agent behavior across channels before deploying to production and with …”
   • [claimed-docs] “As conversations reveal gaps and new opportunities, Duet automatically iterates on your agent, from the first launch through every improveme…”
   • [claimed-docs] “Whether you're monitoring for compliance risks, negative sentiment, or upsell signals, Watchtower reviews every interaction against your cus…”

   proof ↗⚑ flag

   Pylon~partialclaimed5/10

   Pylon documents a monitor-and-iterate loop: a 'test' simulation mode to probe agent behavior, an issue log to inspect outcomes/steps taken by the AI, and runbooks/skills that let ops feed corrections back into the agent's instructions. However, there's no evidence of structured QA scoring of samples or a formal flagged-failure workflow with review states — it's more free-form inspection than a scored QA/review pipeline. Missing for 10: sample scoring/rubrics, dedicated failure-flagging workflow with reviewer roles, and quantitative QA metrics tied back to agent training.

   • [claimed-docs] “Simulate an interaction with the AI and see how it handles different questions.”
   • [claimed-docs] “You can assign them to issues you'd like them to take a look at. This means you have full control of which customer issues your AI agent int…”
   • [claimed-docs] “The issue log allows you to inspect all the issues the AI agent is associated with and inspect the outcomes and steps taken by the AI.”
   • [claimed-docs] “Write instructions in natural language to help your AI Agent handle specific scenarios.”
   • [claimed-docs] “Skills are reusable instructions that teach Pylon agents how to handle specific workflows consistently.”

   proof ↗⚑ flag

Simulation

1. support ops leadI test the agent against historical tickets or simulated conversations before it faces real customers

   weight 2 · round to Decagon
   Decagon✓fullclaimed8/10

   Decagon's Simulations product is explicitly described as an integrated testing suite that validates agent behavior across channels before production deployment and on every update, and Duet can generate diverse test pathways to check accuracy, policy adherence, and brand voice. Missing for 10: no explicit mention of testing against historical ticket logs specifically, and no independent/hands-on evidence corroborating the testing suite's effectiveness beyond vendor docs.

   • [claimed-docs] “Simulations, Decagon's integrated testing suite, help teams validate agent behavior across channels before deploying to production and with …”
   • [claimed-docs] “Use Duet to easily generate tests covering diverse pathways that verify whether agents respond accurately, follow policies, and reflect your…”
   • [claimed-docs] “Analyze past customer interactions to automatically generate Agent Operating Procedures (AOPs) rooted in actual customer needs.”

   proof ↗⚑ flag

   Pylon~partialclaimed6/10

   Pylon's docs explicitly describe a test/simulate feature ('Simulate an interaction with the AI and see how it handles different questions') plus an issue log to inspect outcomes, which supports pre-deployment validation and monitoring. However, there's no explicit mention of testing against historical ticket datasets in bulk, regression testing, or scoring accuracy across a corpus of past conversations. missing for 10: bulk/historical-ticket backtesting workflow, quantitative accuracy/regression metrics from test runs, independent/hands-on confirmation of the simulate feature's depth.

   • [claimed-docs] “Simulate an interaction with the AI and see how it handles different questions.”
   • [claimed-docs] “You can assign them to issues you'd like them to take a look at. This means you have full control of which customer issues your AI agent int…”
   • [claimed-docs] “The issue log allows you to inspect all the issues the AI agent is associated with and inspect the outcomes and steps taken by the AI.”
   • [claimed-docs] “Write instructions in natural language to help your AI Agent handle specific scenarios.”

   proof ↗⚑ flag