Pylon vs Lorikeet

Actions

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

   weight 3 · round to Lorikeet
   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

   Lorikeet✓fullclaimed7/10

   Docs explicitly state the agent 'takes action through your APIs and MCP servers' (docs-28), give concrete examples like refund workflows and order-status tool tests (docs-19, docs-24, docs-43), and describe workflow-scoped tool access, server-side identity validation, and hard execution caps enforced in code rather than prompts (docs-34). This directly matches the story of scoped, real-world API actions like refunds/order changes/subscriptions. Missing for 10: independent/hands-on verification of the auth-scoping mechanism, and more granular detail on how 'per action' scopes are configured/enforced beyond high-level guardrails language.

   • [claimed-docs] “The agent takes action through your APIs and MCP servers inside natural-language and deterministic workflows”
   • [claimed-docs] “Customer isolation, server-side identity validation, workflow-scoped tool access and hard execution caps are enforced in code rather than pr…”
   • [claimed-docs] “Test the 'get-order-status' tool with order ID 98765 and check if the response matches what we expect.”
   • [claimed-docs] “/lorikeet:create-simulations build simulations for the refund workflow”
   • [claimed-docs] “Automate disputes, loan inquiries, payments and compliance cases across every customer channel”
   • [claimed-docs] “Connect Lorikeet in seconds to your ticketing system, knowledge base, and internal tools to seamlessly ingest data and take action for your …”

   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 Lorikeet
   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

   Lorikeet✓fullclaimed7/10

   Lorikeet explicitly supports training agents on SOPs (docs-25) and building workflows with 'natural-language and deterministic workflows' plus 'pockets of determinism for regulated steps' (docs-28, docs-32), with workflow-scoped tool access and hard execution caps enforced in code (docs-34), directly matching the deterministic-branching SOP story. Missing for 10: independent/hands-on validation of branching logic in practice and more detail on how branching conditions are authored beyond natural-language workflow builder claims.

   • [claimed-docs] “train the agent on your business context, brand guidelines, help docs and standard operating procedures”
   • [claimed-docs] “The agent takes action through your APIs and MCP servers inside natural-language and deterministic workflows”
   • [claimed-docs] “Lorikeet coordinates a team of specialist agents, with pockets of determinism for regulated steps, to handle multi-party, multi-system workf…”
   • [claimed-docs] “Customer isolation, server-side identity validation, workflow-scoped tool access and hard execution caps are enforced in code rather than pr…”
   • [claimed-docs] “Build workflows - create and iterate on workflows using natural language”
   • [claimed-docs] “Build, edit, and deploy workflows using natural language”

   proof ↗⚑ flag

Agent access

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

   weight 2 · round to Lorikeet
   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

   Lorikeet✓fullprobed9/10

   Direct probe evidence confirms Lorikeet serves an llms.txt file at docs.lorikeetcx.ai/llms.txt returning HTTP 200 with structured agent-oriented reference links, and documentation is further organized around MCP/agent access. Missing for 10: no independent third-party report of an agent successfully consuming this llms.txt in practice.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.lorikeetcx.ai/llms.txt # Reference - [Lorikeet MCP Server](https://docs.lorikeetcx.ai/mcp/mcp-serv…”
   • [probe] “official MCP server documented at https://docs.lorikeetcx.ai/mcp/mcp-server”
   • [claimed-docs] “Connect to your Lorikeet account from ChatGPT, Claude, Claude Code, and MintMCP using the Model Context Protocol.”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   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

   Lorikeet~partialclaimed5/10

   Lorikeet's docs state the agent 'takes action through your APIs and MCP servers inside natural-language and deterministic workflows' (lorikeet-docs-28), indicating it can consume external MCP servers as tool sources, but the bulk of the MCP evidence pack actually describes the reverse direction — Lorikeet exposing its own MCP server for external clients like Claude/ChatGPT to connect to (lorikeet-docs-1, lorikeet-docs-46, lorikeet-probe-1/2). Missing for 10: dedicated documentation on how a user configures/adds third-party MCP servers into Lorikeet, a list of supported MCP integrations, and independent confirmation of this client-side tool-use capability.

   • [claimed-docs] “The agent takes action through your APIs and MCP servers inside natural-language and deterministic workflows”
   • [claimed-docs] “Connect Lorikeet in seconds to your ticketing system, knowledge base, and internal tools to seamlessly ingest data and take action for your …”

   proof ↗⚑ flag

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

   weight 3 · round to Pylon
   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

   Lorikeet✓fullprobed7/10

   Lorikeet publishes an official MCP server (docs.lorikeetcx.ai/mcp/mcp-server) that lets Claude, ChatGPT, Claude Code, Codex, and MintMCP connect directly to a Lorikeet account, with documented capabilities like diagnosing tickets, auditing knowledge bases, building workflows, testing tools, and running simulations via MCP. This is confirmed live (HTTP 200) via probe evidence, not just marketing copy. Missing for 10: independent/hands-on third-party verification of the MCP server working end-to-end, and no community reports corroborating reliability.

   • [claimed-docs] “The Lorikeet MCP server lets you interact with your Lorikeet account directly from Claude Code, Claude.ai, ChatGPT, and Codex.”
   • [claimed-docs] “Diagnose tickets - trace workflow execution and identify root causes”
   • [claimed-docs] “Audit knowledge bases - analyze articles at scale, find gaps, and spot quality issues”
   • [claimed-docs] “Build workflows - create and iterate on workflows using natural language”
   • [claimed-docs] “Test tools - run and validate tool configurations directly from your AI assistant”
   • [claimed-docs] “Connect to your Lorikeet account from ChatGPT, Claude, Claude Code, and MintMCP using the Model Context Protocol.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.lorikeetcx.ai/llms.txt # Reference - [Lorikeet MCP Server](https://docs.lorikeetcx.ai/mcp/mcp-serv…”
   • [probe] “official MCP server documented at https://docs.lorikeetcx.ai/mcp/mcp-server”

   proof ↗⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round drawn
   Pylon—none0/10

   No evidence of an official Pylon CLI anywhere in docs, changelog, or probes; Pylon offers REST API, webhooks, and an MCP server but no CLI tool is mentioned. missing for 10: any mention of a CLI, CLI installation instructions, or CLI command reference.

   ⚑ flag

   Lorikeet—none0/10

   Lorikeet is a customer-support AI platform; the story asks for an official CLI for AI-native workflows. Evidence shows an MCP server and Claude-code skills/slash commands but no standalone CLI tool is documented anywhere in the pack. missing for 10: any mention of a CLI binary/tool, installation instructions, or CLI command reference.

   • [claimed-docs] “The Lorikeet MCP server lets you interact with your Lorikeet account directly from Claude Code, Claude.ai, ChatGPT, and Codex.”
   • [claimed-docs] “/lorikeet:create-simulations build simulations for the refund workflow”
   • [probe] “official MCP server documented at https://docs.lorikeetcx.ai/mcp/mcp-server”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   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

   Lorikeet✓fullprobed8/10

   Lorikeet publishes a documented MCP server (docs.lorikeetcx.ai/mcp/mcp-server) that lets AI-native users drive the product directly from Claude, ChatGPT, Codex, and Claude Code — diagnosing tickets, auditing knowledge bases, building workflows, testing tools, and running simulations, all documented with concrete examples and even slash-command skills. This is a genuine documented programmatic interface built for AI agents, not just human UI docs. Missing for 10: no separate traditional REST/GraphQL API reference beyond MCP, and no independent third-party corroboration of the API's reliability.

   • [claimed-docs] “The Lorikeet MCP server lets you interact with your Lorikeet account directly from Claude Code, Claude.ai, ChatGPT, and Codex.”
   • [claimed-docs] “Diagnose tickets - trace workflow execution and identify root causes”
   • [claimed-docs] “Audit knowledge bases - analyze articles at scale, find gaps, and spot quality issues”
   • [claimed-docs] “Build workflows - create and iterate on workflows using natural language”
   • [claimed-docs] “Test tools - run and validate tool configurations directly from your AI assistant”
   • [claimed-docs] “Test the 'get-order-status' tool with order ID 98765 and check if the response matches what we expect.”
   • [claimed-docs] “Explore your setup - inspect workflows, tools, and integrations”
   • [claimed-docs] “Connect to your Lorikeet account from ChatGPT, Claude, Claude Code, and MintMCP using the Model Context Protocol.”
   • [claimed-docs] “Run simulations - test workflows against different customer scenarios”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.lorikeetcx.ai/llms.txt # Reference - [Lorikeet MCP Server](https://docs.lorikeetcx.ai/mcp/mcp-serv…”
   • [probe] “official MCP server documented at https://docs.lorikeetcx.ai/mcp/mcp-server”

   proof ↗⚑ flag

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

   weight 2 · round to Pylon
   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

   Lorikeet~partialclaimed3/10

   Lorikeet's guardrails page mentions 'workflow-scoped tool access' and 'server-side identity validation' enforced in code, suggesting some access scoping, but there is no explicit documentation of issuing or managing scoped/least-privilege API credentials or tokens for agents. Missing for 10: explicit credential/token issuance mechanism, documentation of API key scoping or permission granularity, and any user-facing controls for creating least-privilege credentials.

   • [claimed-docs] “Customer isolation, server-side identity validation, workflow-scoped tool access and hard execution caps are enforced in code rather than pr…”

   proof ↗⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round to Pylon
   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

   Lorikeet—none0/10

   Evidence only documents an MCP server and integrations/APIs for connecting tools, but there is no mention of an official SDK (e.g., Python/JS client library) for developers to build against. Missing for 10: any documented official SDK, its language support, or developer-facing library docs.

   ⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round to Pylon
   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

   Lorikeet—none0/10

   The evidence pack covers Lorikeet's MCP server, simulations, coach, and guardrails features, but contains no mention of webhooks or event subscription mechanisms for AI-native users to receive push notifications on events.

   ⚑ flag

Agentic features

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

   weight 2 · round to Lorikeet
   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

   Lorikeet✓fullclaimed8/10

   Lorikeet's Coach and MCP-server capabilities generate AI-driven insights directly from customer data: ticket quality scoring across 100% of conversations, knowledge-base gap/quality audits, root-cause diagnosis of tickets, and analytics on resolution quality, satisfaction, and revenue impact, with Coach able to 'implement improvements... or make suggestions for you to action yourself.' This is all first-party documentation without independent hands-on corroboration. Missing for 10: independent/third-party validation of insight quality and real-world usage examples beyond vendor docs.

   • [claimed-docs] “Coach's Ticket Quality Score reviews 100% of conversations against your quality standards, AI and human alike, replacing manual spot checks …”
   • [claimed-docs] “Audit your entire knowledge base for gaps, outdated articles, and quality issues”
   • [claimed-docs] “Diagnose tickets by tracing workflow execution and identifying root causes”
   • [claimed-docs] “Track resolution quality, customer satisfaction, revenue impact, and operational efficiency with industry-leading analytics.”
   • [claimed-docs] “Coach can implement improvements on your behalf, or make suggestions for you to action yourself.”
   • [claimed-docs] “Coach reviews 100% of tickets against your quality standards and turns findings into fixes, so your AI agent improves every week instead of …”
   • [claimed-docs] “Scale and optimize with conversational insights and analytics from Lorikeet Coach”

   proof ↗⚑ flag

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

   weight 2 · round to Lorikeet
   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

   Lorikeet~partialclaimed7/10

   Lorikeet's core product is an autonomous agent that resolves tickets end-to-end across channels and coordinates specialist agents for multi-step workflows, and Outbound campaigns run on scheduled cadences without human intervention, while Coach can autonomously implement improvements. However, the evidence centers on the vendor's own agent running in background rather than a user-configurable 'automation' builder with triggers/schedules exposed as a general-purpose feature. Missing for 10: explicit user-facing scheduling/trigger configuration UI or API for arbitrary automations, and independent/hands-on confirmation that these automations run unattended reliably.

   • [claimed-docs] “one agent that resolves issues end-to-end across chat, email, voice and SMS”
   • [claimed-docs] “Lorikeet coordinates a team of specialist agents, with pockets of determinism for regulated steps, to handle multi-party, multi-system workf…”
   • [claimed-docs] “campaign cadences with scheduling windows control when outreach happens”
   • [claimed-docs] “Coach can implement improvements on your behalf, or make suggestions for you to action yourself.”
   • [claimed-docs] “The agent takes action through your APIs and MCP servers inside natural-language and deterministic workflows”

   proof ↗⚑ flag

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

   weight 3 · round to Pylon
   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

   Lorikeet✓fullclaimed7/10

   Lorikeet's 'Coach' is a built-in AI assistant accessible directly inside the Lorikeet platform (as well as via Slack/Claude/ChatGPT/MCP) that users can delegate tasks to — diagnosing tickets, auditing knowledge bases, building workflows via natural language, running simulations, and even implementing improvements automatically on the user's behalf. This is well documented across multiple first-party pages describing concrete delegated actions (e.g. doc-48 'Coach can implement improvements on your behalf'). missing for 10: independent/hands-on verification of Coach's assistant behavior, and clearer distinction between autonomous action vs. suggestion-only mode.

   • [claimed-docs] “Coach's Ticket Quality Score reviews 100% of conversations against your quality standards, AI and human alike, replacing manual spot checks …”
   • [claimed-docs] “Talk to Coach wherever you work, whether in Lorikeet, Slack, Claude, ChatGPT, or via MCP.”
   • [claimed-docs] “Diagnose tickets by tracing workflow execution and identifying root causes”
   • [claimed-docs] “Audit your entire knowledge base for gaps, outdated articles, and quality issues”
   • [claimed-docs] “Build, edit, and deploy workflows using natural language”
   • [claimed-docs] “Coach reviews 100% of tickets against your quality standards and turns findings into fixes, so your AI agent improves every week instead of …”
   • [claimed-docs] “Coach can implement improvements on your behalf, or make suggestions for you to action yourself.”

   proof ↗⚑ flag

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

   weight 2 · round to Lorikeet
   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

   Lorikeet✓fullprobed8/10

   Lorikeet ships an MCP server plus Claude/ChatGPT/Codex integrations that let users build workflows, diagnose tickets, audit knowledge bases, and run simulations using natural-language commands (e.g. 'Build workflows - create and iterate on workflows using natural language', example prompts like 'Test the get-order-status tool...'), and even exposes slash-command skills like /lorikeet:create-simulations. This is first-party documentation only, with no independent/hands-on corroboration of the NL command experience. Missing for 10: independent user reports or demos validating the natural-language MCP workflow in practice.

   • [claimed-docs] “The Lorikeet MCP server lets you interact with your Lorikeet account directly from Claude Code, Claude.ai, ChatGPT, and Codex.”
   • [claimed-docs] “Build workflows - create and iterate on workflows using natural language”
   • [claimed-docs] “Build, edit, and deploy workflows using natural language”
   • [claimed-docs] “Test the 'get-order-status' tool with order ID 98765 and check if the response matches what we expect.”
   • [claimed-docs] “/lorikeet:create-simulations build simulations for the refund workflow”
   • [claimed-docs] “Connect to your Lorikeet account from ChatGPT, Claude, Claude Code, and MintMCP using the Model Context Protocol.”
   • [probe] “official MCP server documented at https://docs.lorikeetcx.ai/mcp/mcp-server”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round drawn
   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

   Lorikeet—none0/10

   No evidence of a downloadable OpenAPI spec or machine-readable API documentation; evidence only covers MCP server integration, workflows, and product features, not a formal API spec artifact.

   ⚑ flag

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

   weight 1 · round to Lorikeet
   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

   Lorikeet~partialclaimed5/10

   Evidence shows robust simulation/testing tooling (replay historical tickets, synthetic scenarios, guardrail adversarial tests) that approximates sandbox-style testing, but no explicit claim of an isolated sandbox environment distinct from production. missing for 10: explicit documentation of a dedicated sandbox/staging environment, confirmation that simulations do not touch or affect live production data/systems, and independent verification of this isolation.

   • [claimed-docs] “Generate simulations straight from your actual tickets and run them in bulk batches, so every workflow change is tested against the conversa…”
   • [claimed-docs] “Run simulation batches to test workflows against different customer scenarios”
   • [claimed-docs] “Replay historical tickets and synthetic scenarios in bulk to see projected resolution quality and knowledge gaps, then deploy on the topics …”
   • [claimed-docs] “Replay historical tickets and synthetic scenarios in bulk to see projected resolution quality and knowledge gaps”
   • [claimed-docs] “Author adversarial scenarios such as false authority claims, mid-conversation goal switches and prompt injection attempts, then run them as …”
   • [claimed-docs] “Run simulations - test workflows against different customer scenarios”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Lorikeet—none0/10

   No evidence pack item mentions API versioning, version numbers, or a deprecation policy for Lorikeet's APIs or MCP server; the docs discuss features and integrations but not API lifecycle/versioning commitments. Missing for 10: any documented API version scheme, changelog of breaking changes, or stated deprecation/support timeline.

   ⚑ flag

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

   weight 2 · round to Lorikeet
   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

   Lorikeet✓fullclaimed7/10

   Lorikeet documents multiple bulk operations available to AI-native users via its MCP server and product surfaces: running simulations in bulk batches across hundreds of scenarios, auditing entire knowledge bases at scale, and reviewing 100% of conversations for quality (not manual spot checks). These are explicitly framed as batch/bulk actions accessible through natural-language or MCP-driven workflows. Missing for 10: independent/hands-on verification of bulk operation scale and performance, and no explicit example of bulk edits/updates to many tickets or records simultaneously (only bulk testing/auditing/review are documented).

   • [claimed-docs] “Generate simulations straight from your actual tickets and run them in bulk batches, so every workflow change is tested against the conversa…”
   • [claimed-docs] “Side-by-side batch comparisons show how a workflow edit changed outcomes across hundreds of scenarios, with per-conversation drill-downs whe…”
   • [claimed-docs] “Audit knowledge bases - analyze articles at scale, find gaps, and spot quality issues”
   • [claimed-docs] “Audit your entire knowledge base for gaps, outdated articles, and quality issues”
   • [claimed-docs] “Coach's Ticket Quality Score reviews 100% of conversations against your quality standards, AI and human alike, replacing manual spot checks …”
   • [claimed-docs] “Coach’s Ticket Quality Score reviews 100% of conversations against your quality standards, AI and human alike, replacing manual spot checks …”
   • [claimed-docs] “Replay historical tickets and synthetic scenarios in bulk to see projected resolution quality and knowledge gaps, then deploy on the topics …”
   • [claimed-docs] “Replay historical tickets and synthetic scenarios in bulk to see projected resolution quality and knowledge gaps”
   • [claimed-docs] “Side-by-side batch comparisons show how a workflow edit changed outcomes across hundreds of scenarios, with per-conversation drill-downs”

   proof ↗⚑ flag

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

   weight 3 · round to Pylon
   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

   Lorikeet~partialclaimed6/10

   Lorikeet's workflows and guardrails encode conditional, event-triggered actions (e.g., prompt-injection detection triggers block/rewrite/escalate, bad QA scores trigger refunds, campaign cadences control scheduled outreach, escalation triggers hand off to humans), and workflows can be built/edited via natural language including deterministic steps. However this is more built-in platform logic than a general-purpose rule-definition interface for arbitrary custom events an AI-native user could freely wire up. Missing for 10: a documented general rules/automation engine or API letting users define arbitrary trigger-condition-action rules beyond the platform's fixed guardrail/workflow/outbound features, and independent confirmation of this working in practice.

   • [claimed-docs] “Customer isolation, server-side identity validation, workflow-scoped tool access and hard execution caps are enforced in code rather than pr…”
   • [claimed-docs] “Incoming messages pass a prompt-injection classifier and bad-actor checks, while response guardrails screen what the agent says for groundin…”
   • [claimed-docs] “When Coach gives a conversation a bad score, we refund the AI portion of that interaction.”
   • [claimed-docs] “campaign cadences with scheduling windows control when outreach happens”
   • [claimed-docs] “When a case requires a specialist or regulatory review, it escalates with full interaction history so your team picks up mid-conversation.”
   • [claimed-docs] “Lorikeet coordinates a team of specialist agents, with pockets of determinism for regulated steps, to handle multi-party, multi-system workf…”
   • [claimed-docs] “The agent takes action through your APIs and MCP servers inside natural-language and deterministic workflows”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round to Lorikeet
   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

   Lorikeet~partialclaimed3/10

   The only relevant evidence is outbound campaign cadences with 'scheduling windows' controlling when outreach happens, which implies some recurring/scheduled automation but is narrowly scoped to outbound messaging rather than general recurring jobs or workflow runs. Missing for 10: explicit cron-like or recurring workflow scheduling for MCP-driven tasks (simulations, audits, diagnostics), documentation of scheduling frequency/config options, and any independent confirmation of recurring job execution.

   • [claimed-docs] “campaign cadences with scheduling windows control when outreach happens”

   proof ↗⚑ flag

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

   weight 1 · round to Lorikeet
   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

   Lorikeet~partialclaimed4/10

   Lorikeet's docs show workflow building/iteration via natural language and strong review tooling (simulations, batch comparisons showing how an edit changed outcomes across scenarios), which covers the 'review' part of the story. However, there is no explicit mention of a version history or a rollback/undo mechanism for automations. missing for 10: explicit versioning/change-history feature, explicit rollback/undo capability, evidence of restoring a prior workflow state.

   • [claimed-docs] “Build workflows - create and iterate on workflows using natural language”
   • [claimed-docs] “Build, edit, and deploy workflows using natural language”
   • [claimed-docs] “Side-by-side batch comparisons show how a workflow edit changed outcomes across hundreds of scenarios, with per-conversation drill-downs whe…”
   • [claimed-docs] “Side-by-side batch comparisons show how a workflow edit changed outcomes across hundreds of scenarios, with per-conversation drill-downs”
   • [claimed-docs] “Generate simulations straight from your actual tickets and run them in bulk batches, so every workflow change is tested against the conversa…”

   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 to Lorikeet
   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

   Lorikeet~partialclaimed6/10

   Lorikeet documents one agent resolving issues across chat, email, voice, SMS and WhatsApp (docs-31, docs-49), and mentions Slack as a place to interact with Coach (docs-10), but this is Coach access, not evidence that the customer-facing agent itself operates in Slack or social channels. missing for 10: explicit confirmation that the customer-facing support agent (not just Coach) handles Slack and social media channels, and independent/hands-on validation of omnichannel deployment.

   • [claimed-docs] “one agent that resolves issues end-to-end across chat, email, voice and SMS”
   • [claimed-docs] “resolve customer problems end-to-end across their lifecycle - via phone, SMS, chat, email, and WhatsApp”
   • [claimed-docs] “Talk to Coach wherever you work, whether in Lorikeet, Slack, Claude, ChatGPT, or via MCP.”
   • [claimed-docs] “When the AI concierge can't resolve a conversation, a human agent steps in directly inside the same platform”

   proof ↗⚑ flag

Languages

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

   weight 2 · round drawn
   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

   Lorikeet—none0/10

   No evidence in the pack addresses multilingual support or the ability to serve customers in languages other than English despite an English-only knowledge base; nothing about translation, language detection, or multilingual training is mentioned.

   ⚑ 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 Lorikeet
   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

   Lorikeet~partialclaimed4/10

   Lorikeet's marketing claims 'one agent that resolves issues end-to-end across chat, email, voice and SMS' and lists phone/voice among supported channels, implying the same agent handles calls. However, there is no detail on speech-in/speech-out mechanics, telephony integration, or evidence that voice interactions carry the same knowledge/actions/guardrails as chat beyond a generic channel list. missing for 10: specifics on speech recognition/TTS, call-handling architecture, latency/quality benchmarks, and confirmation that voice shares the same knowledge base and action set as chat.

   • [claimed-docs] “one agent that resolves issues end-to-end across chat, email, voice and SMS”
   • [claimed-docs] “resolve customer problems end-to-end across their lifecycle - via phone, SMS, chat, email, and WhatsApp”

   proof ↗⚑ 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 Lorikeet
   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

   Lorikeet~partialclaimed6/10

   Lorikeet documents human handoff happening 'inside the same platform' when AI can't resolve, and specifically claims escalations carry 'full interaction history so your team picks up mid-conversation' (financial-services vertical) — directly supporting no-repeat handoff. However, evidence doesn't explicitly confirm a generated summary or structured 'collected details' package accompanying every escalation across all verticals, only interaction history. Missing for 10: explicit documentation of an auto-generated conversation summary at escalation, structured collected-details extraction, and independent/customer verification that customers never repeat themselves in practice.

   • [claimed-docs] “When the AI concierge can't resolve a conversation, a human agent steps in directly inside the same platform”
   • [claimed-docs] “When a case requires a specialist or regulatory review, it escalates with full interaction history so your team picks up mid-conversation.”
   • [claimed-docs] “Enforce required disclosures and data handling standards through built-in guardrails that balance conversational flexibility with structured…”

   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 to Lorikeet
   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

   Lorikeet~partialclaimed5/10

   Docs show human handoff when the AI can't resolve a ticket, escalation for regulatory/specialist cases with full context, guardrails that can 'escalate' on policy violations, and deployment scoped to trained topics — supporting topic-based and inability/explicit-need escalation. However there is no explicit mention of configuring handoff by sentiment or customer tier, nor independent verification that these rules are 'reliably obeyed'. Missing for 10: explicit sentiment-based trigger config, explicit customer-tier-based trigger config, and independent/hands-on evidence of reliability.

   • [claimed-docs] “When the AI concierge can't resolve a conversation, a human agent steps in directly inside the same platform”
   • [claimed-docs] “deploy on the topics the agent is trained for and leave the rest with your team”
   • [claimed-docs] “Incoming messages pass a prompt-injection classifier and bad-actor checks, while response guardrails screen what the agent says for groundin…”
   • [claimed-docs] “When a case requires a specialist or regulatory review, it escalates with full interaction history so your team picks up mid-conversation.”
   • [claimed-docs] “Outbound runs on recorded consent that is enforced when messages are sent, with opt-out handling and escalation paths for sensitive situatio…”

   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 Lorikeet
   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

   Lorikeet✓fullclaimed8/10

   Lorikeet documents explicit guardrails that enforce grounding and policy compliance in code rather than prompts, including response screening for grounding/policy with block/rewrite/escalate actions, and adversarial simulation testing for false authority claims and prompt injection to validate safe-decline behavior before deployment. This directly targets stopping invented policies/prices/promises via server-side enforcement rather than relying on model honesty. Missing for 10: independent/third-party verification or a concrete hands-on example showing an off-knowledge question actually triggering a safe decline rather than a hallucinated answer.

   • [claimed-docs] “Customer isolation, server-side identity validation, workflow-scoped tool access and hard execution caps are enforced in code rather than pr…”
   • [claimed-docs] “Incoming messages pass a prompt-injection classifier and bad-actor checks, while response guardrails screen what the agent says for groundin…”
   • [claimed-docs] “every event lands in your analytics as a tracked outcome your QA team can review”
   • [claimed-docs] “Author adversarial scenarios such as false authority claims, mid-conversation goal switches and prompt injection attempts, then run them as …”
   • [claimed-docs] “Enforce required disclosures and data handling standards through built-in guardrails that balance conversational flexibility with structured…”

   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
   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

   Lorikeet—none0/10

   Lorikeet's documented model is autonomous resolution with post-hoc QA (Coach reviews 100% of tickets after the fact) and escalation to humans only when the AI can't resolve a case, not a pre-send draft-for-approval workflow. No evidence describes a mode where every agent reply is queued for human sign-off before reaching a customer. Missing for 10: any mention of a draft/approve workflow, human-in-the-loop send gating, or a configurable 'supervised' launch mode.

   • [claimed-docs] “When the AI concierge can't resolve a conversation, a human agent steps in directly inside the same platform”
   • [claimed-docs] “Incoming messages pass a prompt-injection classifier and bad-actor checks, while response guardrails screen what the agent says for groundin…”
   • [claimed-docs] “Coach’s Ticket Quality Score reviews 100% of conversations against your quality standards, AI and human alike, replacing manual spot checks …”
   • [claimed-docs] “When a case requires a specialist or regulatory review, it escalates with full interaction history so your team picks up mid-conversation.”

   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 Lorikeet
   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

   Lorikeet~partialclaimed5/10

   Lorikeet documents topic-scoped deployment ("deploy on the topics the agent is trained for and leave the rest with your team"), workflow-scoped tool access with hard execution caps enforced in code, and escalation paths for regulated/specialist cases with full history handoff — all consistent with restricting the agent from acting on sensitive topics. However, there's no explicit documentation of a UI/config for support-ops to designate specific topics (e.g., legal threats, cancellations, security) as strictly human-only with enforced non-freelancing. Missing for 10: explicit topic-tagging/human-only designation feature, confirmation that agent cannot even attempt those topics (vs. escalating mid-conversation), and independent verification of this behavior in production.

   • [claimed-docs] “deploy on the topics the agent is trained for and leave the rest with your team”
   • [claimed-docs] “Lorikeet coordinates a team of specialist agents, with pockets of determinism for regulated steps, to handle multi-party, multi-system workf…”
   • [claimed-docs] “Customer isolation, server-side identity validation, workflow-scoped tool access and hard execution caps are enforced in code rather than pr…”
   • [claimed-docs] “When a case requires a specialist or regulatory review, it escalates with full interaction history so your team picks up mid-conversation.”
   • [claimed-docs] “Enforce required disclosures and data handling standards through built-in guardrails that balance conversational flexibility with structured…”

   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
   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

   Lorikeet~partialclaimed5/10

   Lorikeet claims analytics tracking 'resolution quality, customer satisfaction, revenue impact, and operational efficiency' and that 'every event lands in your analytics as a tracked outcome,' which loosely maps to resolution rate, CSAT, and cost metrics, but there is no explicit mention of a handoff-rate metric or a dedicated exec-facing dashboard view combining these four numbers. missing for 10: explicit handoff-rate metric, dedicated dashboard UI/screenshot evidence, cost-per-resolution specifics, and independent corroboration of dashboard usability.

   • [claimed-docs] “Track resolution quality, customer satisfaction, revenue impact, and operational efficiency with industry-leading analytics.”
   • [claimed-docs] “Scale and optimize with conversational insights and analytics from Lorikeet Coach”
   • [claimed-docs] “every event lands in your analytics as a tracked outcome your QA team can review”

   proof ↗⚑ flag

Insights

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

   weight 1 · round drawn
   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

   Lorikeet—none0/10

   Evidence shows general analytics and quality-review features (e.g., 'Track resolution quality, customer satisfaction... with industry-leading analytics', Coach reviewing 100% of conversations) but no mention of topic clustering of conversations or proactive surfacing of emerging product issues before ticket-volume spikes. missing for 10: topic clustering of conversations, trend/anomaly detection for emerging issues, ticket-volume spike prediction or alerting.

   • [claimed-docs] “Track resolution quality, customer satisfaction, revenue impact, and operational efficiency with industry-leading analytics.”
   • [claimed-docs] “Scale and optimize with conversational insights and analytics from Lorikeet Coach”
   • [claimed-docs] “Coach's Ticket Quality Score reviews 100% of conversations against your quality standards, AI and human alike, replacing manual spot checks …”

   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 Lorikeet
   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

   Lorikeet~partialclaimed5/10

   Docs claim Lorikeet works 'alongside your existing tools' and connects 'in seconds to your ticketing system' via integrations, implying helpdesk co-existence, but there is no specific evidence of named Zendesk/Salesforce/Intercom connectors or two-way ticket/context sync — the pack focuses on MCP client integrations (Claude, ChatGPT) rather than helpdesk platforms. missing for 10: named Zendesk/Salesforce/Intercom integration docs, evidence of bidirectional ticket sync, standalone-mode confirmation, independent corroboration of integration reliability.

   • [claimed-docs] “No migration required: Lorikeet works alongside your existing tools.”
   • [claimed-docs] “Connect Lorikeet in seconds to your ticketing system, knowledge base, and internal tools to seamlessly ingest data and take action for your …”
   • [claimed-docs] “When the AI concierge can't resolve a conversation, a human agent steps in directly inside the same platform”
   • [claimed-docs] “The agent takes action through your APIs and MCP servers inside natural-language and deterministic workflows”

   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
   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

   Lorikeet—none0/10

   Evidence shows Lorikeet ingests knowledge bases and can audit them for gaps/outdated articles, and connects to ticketing/knowledge sources 'in seconds', but there is no mention of scheduled or change-triggered re-syncing of sources without manual re-upload. missing for 10: explicit scheduled/webhook-based re-sync mechanism, evidence of automatic detection of source updates, any documentation of sync cadence or on-change triggers.

   • [claimed-docs] “Audit knowledge bases - analyze articles at scale, find gaps, and spot quality issues”
   • [claimed-docs] “Connect Lorikeet in seconds to your ticketing system, knowledge base, and internal tools to seamlessly ingest data and take action for your …”
   • [claimed-docs] “Audit your entire knowledge base for gaps, outdated articles, and quality issues”
   • [claimed-docs] “train the agent on your business context, brand guidelines, help docs and standard operating procedures”

   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 Lorikeet
   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

   Lorikeet✓fullclaimed8/10

   Lorikeet explicitly documents auditing knowledge bases at scale to find gaps and quality issues, and its simulation/replay tooling surfaces knowledge gaps by replaying historical tickets and synthetic scenarios to project resolution quality before deployment. Coach's Ticket Quality Score also reviews 100% of conversations to catch fumbled answers and feed fixes back. Missing for 10: independent/hands-on validation of the gap-detection accuracy and no explicit mention of detecting 'conflicting' content specifically (only gaps/outdated/quality issues).

   • [claimed-docs] “Audit knowledge bases - analyze articles at scale, find gaps, and spot quality issues”
   • [claimed-docs] “Audit your entire knowledge base for gaps, outdated articles, and quality issues”
   • [claimed-docs] “Replay historical tickets and synthetic scenarios in bulk to see projected resolution quality and knowledge gaps, then deploy on the topics …”
   • [claimed-docs] “Replay historical tickets and synthetic scenarios in bulk to see projected resolution quality and knowledge gaps”
   • [claimed-docs] “Coach's Ticket Quality Score reviews 100% of conversations against your quality standards, AI and human alike, replacing manual spot checks …”
   • [claimed-docs] “Coach’s Ticket Quality Score reviews 100% of conversations against your quality standards, AI and human alike, replacing manual spot checks …”
   • [claimed-docs] “Coach reviews 100% of tickets against your quality standards and turns findings into fixes, so your AI agent improves every week instead of …”

   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
   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

   Lorikeet—none0/10

   Lorikeet documents training its agent on 'business context, brand guidelines, help docs and standard operating procedures' (docs-25) and mentions 'grounding' as a guardrail check (docs-35), but there is no evidence that end-user-facing answers cite or display the specific article/source used to generate a response. Missing for 10: any documented citation/source-attribution UI or API in agent responses, and independent confirmation that answers reference specific knowledge-base articles.

   • [claimed-docs] “train the agent on your business context, brand guidelines, help docs and standard operating procedures”
   • [claimed-docs] “Incoming messages pass a prompt-injection classifier and bad-actor checks, while response guardrails screen what the agent says for groundin…”
   • [claimed-docs] “Audit your entire knowledge base for gaps, outdated articles, and quality issues”

   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 Lorikeet
   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

   Lorikeet✓fullclaimed7/10

   Lorikeet explicitly claims to 'seamlessly ingest data' from ticketing systems and knowledge bases (docs-13), to train the agent on 'business context, brand guidelines, help docs and standard operating procedures' (docs-25), to audit the entire knowledge base for gaps/outdated content (docs-3, docs-16), and to replay historical tickets to surface knowledge gaps (docs-21, docs-26) — covering help center, docs, and past tickets without manual re-authoring. Internal wikis are not explicitly named as a source type, and all evidence is first-party vendor documentation with no independent/hands-on corroboration of ingestion working end-to-end. Missing for 10: explicit mention of internal wiki ingestion, and independent verification of the ingestion pipeline's fidelity/accuracy.

   • [claimed-docs] “Connect Lorikeet in seconds to your ticketing system, knowledge base, and internal tools to seamlessly ingest data and take action for your …”
   • [claimed-docs] “train the agent on your business context, brand guidelines, help docs and standard operating procedures”
   • [claimed-docs] “Audit knowledge bases - analyze articles at scale, find gaps, and spot quality issues”
   • [claimed-docs] “Audit your entire knowledge base for gaps, outdated articles, and quality issues”
   • [claimed-docs] “Replay historical tickets and synthetic scenarios in bulk to see projected resolution quality and knowledge gaps, then deploy on the topics …”
   • [claimed-docs] “Replay historical tickets and synthetic scenarios in bulk to see projected resolution quality and knowledge gaps”

   proof ↗⚑ flag

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

   weight 2 · round to Lorikeet
   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

   Lorikeet~partialprobed6/10

   Lorikeet's MCP server exposes a broad set of actions also available in the UI—diagnosing tickets, auditing knowledge bases, building/testing workflows, running simulations—letting AI-native users act via Claude/ChatGPT/Codex instead of the dashboard. However, there's no evidence of a general-purpose REST/GraphQL API or explicit claim of full UI/API parity (e.g., outbound campaign management, guardrail configuration, analytics dashboards aren't shown as MCP-accessible). Missing for 10: explicit full API parity statement, broader API coverage beyond MCP-listed actions, independent confirmation of completeness.

   • [claimed-docs] “The Lorikeet MCP server lets you interact with your Lorikeet account directly from Claude Code, Claude.ai, ChatGPT, and Codex.”
   • [claimed-docs] “Diagnose tickets - trace workflow execution and identify root causes”
   • [claimed-docs] “Audit knowledge bases - analyze articles at scale, find gaps, and spot quality issues”
   • [claimed-docs] “Build workflows - create and iterate on workflows using natural language”
   • [claimed-docs] “Test tools - run and validate tool configurations directly from your AI assistant”
   • [claimed-docs] “Explore your setup - inspect workflows, tools, and integrations”
   • [claimed-docs] “Run simulations - test workflows against different customer scenarios”
   • [claimed-docs] “The agent takes action through your APIs and MCP servers inside natural-language and deterministic workflows”
   • [probe] “official MCP server documented at https://docs.lorikeetcx.ai/mcp/mcp-server”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   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

   Lorikeet—none0/10

   No evidence pack items mention data export, open data formats, or account/data portability for leaving the platform; the docs cover MCP integrations, workflows, simulations, and guardrails but nothing about exporting or migrating data out. Missing for 10: any documentation of export functionality, supported open formats (CSV/JSON), or data portability/exit process.

   ⚑ flag

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

   weight 2 · round drawn
   Pylon—none0/10

   Pylon is a closed-source SaaS product; no evidence of any open-source license or public source repository is present in the pack—only product docs, API/MCP references, and security/compliance pages. missing for 10: any open-source license, public source code repository, or licensing statement.

   ⚑ flag

   Lorikeet—none0/10

   Lorikeet is a closed commercial SaaS customer-support platform; no evidence of any open-source license or public source code repository is provided anywhere in the evidence pack.

   ⚑ 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 to Lorikeet
   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

   Lorikeet~partialclaimed3/10

   The only evidence touching pricing-economics is the refund policy tying billing to Coach's quality score ('When Coach gives a conversation a bad score, we refund the AI portion of that interaction'), which shows some outcome-linkage in billing, but there is no published price list, per-resolution rate, cap structure, or self-serve pricing page. Missing for 10: a published price sheet or rate card, explicit per-resolution cost, spend/volume caps, and any evidence pricing is transparent versus custom enterprise quoting.

   • [claimed-docs] “When Coach gives a conversation a bad score, we refund the AI portion of that interaction.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Lorikeet—none0/10

   The evidence covers compliance/trust items (Vanta certifications, zero-data-retention with model vendors) but no mention of data residency or region-selection options for storage. Missing for 10: any documentation of regional data storage choices, residency guarantees, or data localization controls.

   ⚑ flag

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

   weight 3 · round to Lorikeet
   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

   Lorikeet✓fullclaimed7/10

   Lorikeet explicitly states zero-data-retention agreements with all model vendors and no fine-tuning on customer data, directly addressing the story's request to prevent data from being used for AI training. This is backed by independently verified trust/compliance reports on their Vanta Trust Center. Missing for 10: independent hands-on verification or third-party audit confirmation of this specific claim, and no detail on user-level opt-out controls or granularity of enforcement.

   • [claimed-docs] “Zero-data-retention agreements with all model vendors and no fine-tuning on customer data.”
   • [claimed-docs] “All four are independently verified, published on our public Vanta Trust Center with reports downloadable under NDA, and refreshed annually.”

   proof ↗⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to Lorikeet
   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

   Lorikeet~partialclaimed4/10

   Lorikeet mentions zero-data-retention agreements with model vendors and no fine-tuning on customer data, plus SOC2-style independently verified reports on a trust center, which touches data retention posture at the vendor-model level. However, there is no evidence of user-facing controls letting an AI-native user configure or request deletion/retention of their own conversation or account data within Lorikeet itself. Missing for 10: explicit customer-data deletion/export controls, retention period configuration, and user-initiated deletion workflows.

   • [claimed-docs] “All four are independently verified, published on our public Vanta Trust Center with reports downloadable under NDA, and refreshed annually.”
   • [claimed-docs] “Zero-data-retention agreements with all model vendors and no fine-tuning on customer data.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Lorikeet—none0/10

   Lorikeet is a customer-support AI platform, and telemetry opt-out for the product itself is a fair privacy-posture question, but none of the evidence mentions any telemetry/usage-tracking opt-out mechanism for users of the product; it only discusses data retention with model vendors and consent handling for outbound customer messaging, which is unrelated to product telemetry opt-out.

   • [claimed-docs] “All four are independently verified, published on our public Vanta Trust Center with reports downloadable under NDA, and refreshed annually.”
   • [claimed-docs] “Zero-data-retention agreements with all model vendors and no fine-tuning on customer data.”

   proof ↗⚑ flag

Personalization

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

   weight 2 · round to Lorikeet
   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

   Lorikeet✓fullclaimed7/10

   Lorikeet's docs describe connecting to ticketing systems, knowledge bases, and internal tools/APIs to 'ingest data and take action for your customers' (lorikeet-docs-13, lorikeet-docs-28, lorikeet-docs-29), with concrete examples like testing a 'get-order-status' tool with a real order ID (lorikeet-docs-19) and financial-services use cases like disputes/loan inquiries requiring account-specific data (lorikeet-docs-43, lorikeet-docs-44). This shows the agent is designed to pull and act on live customer data rather than just static help content. missing for 10: independent/hands-on verification that responses actually reflect real-time account state in production, and more detail on latency/freshness guarantees for live data lookups.

   • [claimed-docs] “Connect Lorikeet in seconds to your ticketing system, knowledge base, and internal tools to seamlessly ingest data and take action for your …”
   • [claimed-docs] “Test the 'get-order-status' tool with order ID 98765 and check if the response matches what we expect.”
   • [claimed-docs] “The agent takes action through your APIs and MCP servers inside natural-language and deterministic workflows”
   • [claimed-docs] “Build your customer Concierge to take actions inside the tools your team already uses”
   • [claimed-docs] “Automate disputes, loan inquiries, payments and compliance cases across every customer channel”
   • [claimed-docs] “When a case requires a specialist or regulatory review, it escalates with full interaction history so your team picks up mid-conversation.”

   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 to Lorikeet
   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

   Lorikeet~partialclaimed6/10

   Lorikeet's docs describe workflows that coordinate multi-step, multi-system troubleshooting (e.g. 'coordinates a team of specialist agents... to handle multi-party, multi-system workflows end-to-end' and 'diagnose tickets by tracing workflow execution') rather than single canned replies, and its agent resolves issues 'end-to-end' across channels. However, there is no explicit documentation showing the agent proactively asking clarifying questions mid-conversation or examples of dialogue-based troubleshooting turns. Missing for 10: explicit examples/transcripts of clarifying-question behavior, documentation describing conversational back-and-forth troubleshooting logic rather than just workflow/tool orchestration.

   • [claimed-docs] “Lorikeet coordinates a team of specialist agents, with pockets of determinism for regulated steps, to handle multi-party, multi-system workf…”
   • [claimed-docs] “one agent that resolves issues end-to-end across chat, email, voice and SMS”
   • [claimed-docs] “Diagnose tickets by tracing workflow execution and identifying root causes”
   • [claimed-docs] “Build, edit, and deploy workflows using natural language”
   • [claimed-docs] “The agent takes action through your APIs and MCP servers inside natural-language and deterministic workflows”

   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 Lorikeet
   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

   Lorikeet~partialclaimed6/10

   Lorikeet's docs repeatedly claim end-to-end resolution (chat, email, voice, SMS), with escalation to humans when it can't resolve, plus QA scoring (Ticket Quality Score) and analytics tracking 'resolution quality' as an outcome metric, and even a refund-on-bad-score mechanism tied to quality. However, all evidence is vendor-authored marketing/docs; there are no independent benchmarks, customer case studies, or hard resolution-rate numbers (e.g., % of conversations fully resolved) to substantiate the claims. Missing for 10: independent/third-party resolution-rate data, customer-reported metrics, and clear definition/measurement methodology distinguishing true resolution from deflection.

   • [claimed-docs] “one agent that resolves issues end-to-end across chat, email, voice and SMS”
   • [claimed-docs] “resolve customer problems end-to-end across their lifecycle - via phone, SMS, chat, email, and WhatsApp”
   • [claimed-docs] “When the AI concierge can't resolve a conversation, a human agent steps in directly inside the same platform”
   • [claimed-docs] “Track resolution quality, customer satisfaction, revenue impact, and operational efficiency with industry-leading analytics.”
   • [claimed-docs] “Coach’s Ticket Quality Score reviews 100% of conversations against your quality standards, AI and human alike, replacing manual spot checks …”
   • [claimed-docs] “When Coach gives a conversation a bad score, we refund the AI portion of that interaction.”
   • [claimed-docs] “Coach's Ticket Quality Score reviews 100% of conversations against your quality standards, AI and human alike, replacing manual spot checks …”

   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 Lorikeet
   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

   Lorikeet~partialclaimed6/10

   Lorikeet docs show the agent can be trained on 'business context, brand guidelines, help docs and standard operating procedures' (lorikeet-docs-25), and Coach's Ticket Quality Score reviews 100% of conversations against quality standards to catch drift (lorikeet-docs-9, lorikeet-docs-38), supporting brand-voice control and consistency monitoring. However, there is no explicit evidence of multi-language tone consistency or dedicated brand-voice/style configuration tooling beyond general training inputs. Missing for 10: explicit multilingual consistency support, dedicated tone/voice configuration UI, and independent evidence of voice consistency across topics/languages.

   • [claimed-docs] “train the agent on your business context, brand guidelines, help docs and standard operating procedures”
   • [claimed-docs] “Coach's Ticket Quality Score reviews 100% of conversations against your quality standards, AI and human alike, replacing manual spot checks …”
   • [claimed-docs] “Coach’s Ticket Quality Score reviews 100% of conversations against your quality standards, AI and human alike, replacing manual spot checks …”
   • [claimed-docs] “deploy on the topics the agent is trained for and leave the rest with your team”

   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 Lorikeet
   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

   Lorikeet✓fullclaimed8/10

   Lorikeet's Coach product directly addresses this story: it reviews 100% of conversations against quality standards (not just samples), scores them via a Ticket Quality Score, flags failures (bad scores trigger refunds), and turns findings into fixes that feed back into the agent so it 'improves every week instead of drifting.' Simulations complement this with batch testing and adversarial scenario scoring tied to guardrails and analytics tracking. Missing for 10: independent/hands-on verification of the review loop in practice and more detail on how flagged failures are triaged/assigned to human reviewers.

   • [claimed-docs] “Coach's Ticket Quality Score reviews 100% of conversations against your quality standards, AI and human alike, replacing manual spot checks …”
   • [claimed-docs] “Coach reviews 100% of tickets against your quality standards and turns findings into fixes, so your AI agent improves every week instead of …”
   • [claimed-docs] “Coach’s Ticket Quality Score reviews 100% of conversations against your quality standards, AI and human alike, replacing manual spot checks …”
   • [claimed-docs] “When Coach gives a conversation a bad score, we refund the AI portion of that interaction.”
   • [claimed-docs] “Coach can implement improvements on your behalf, or make suggestions for you to action yourself.”
   • [claimed-docs] “every event lands in your analytics as a tracked outcome your QA team can review”
   • [claimed-docs] “Generate simulations straight from your actual tickets and run them in bulk batches, so every workflow change is tested against the conversa…”
   • [claimed-docs] “Author adversarial scenarios such as false authority claims, mid-conversation goal switches and prompt injection attempts, then run them as …”

   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 Lorikeet
   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

   Lorikeet✓fullclaimed9/10

   Lorikeet's Simulations product directly supports this story: it generates simulations from actual historical tickets and runs them in bulk batches before workflow changes go live, with side-by-side batch comparisons and per-conversation drill-downs, plus authored adversarial/guardrail scenarios to pre-test against tricky real-world behavior. Docs also describe replaying historical tickets and synthetic scenarios in bulk to project resolution quality before deploying on trained topics. Missing for 10: independent/hands-on corroboration beyond first-party docs.

   • [claimed-docs] “Generate simulations straight from your actual tickets and run them in bulk batches, so every workflow change is tested against the conversa…”
   • [claimed-docs] “Side-by-side batch comparisons show how a workflow edit changed outcomes across hundreds of scenarios, with per-conversation drill-downs whe…”
   • [claimed-docs] “Author adversarial scenarios such as false authority claims, mid-conversation goal switches and prompt injection attempts, then run them as …”
   • [claimed-docs] “Replay historical tickets and synthetic scenarios in bulk to see projected resolution quality and knowledge gaps, then deploy on the topics …”
   • [claimed-docs] “Replay historical tickets and synthetic scenarios in bulk to see projected resolution quality and knowledge gaps”
   • [claimed-docs] “Run simulations - test workflows against different customer scenarios”

   proof ↗⚑ flag