Decagon vs Sierra

Actions

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

   weight 3 · round to Decagon
   Decagon~partialclaimed6/10

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

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

   proof ↗⚑ flag

   Sierra~partialcommunity5/10

   Sierra's Agent SDK/Studio docs show agents can call customer APIs to execute actions (order changes, refunds implied by 'internal APIs' use), with guardrails, release governance, and human-in-the-loop approval, and a HN commenter confirms it wires directly into a customer's internal APIs. However there's no explicit documentation of per-action scoped auth/permissioning model for API calls. missing for 10: explicit scoped-auth/permission model per action, concrete refund/subscription action examples, independent confirmation of granular auth scoping.

   • [claimed-docs] “write customer journeys as code, track changes, and build sophisticated logic without giving up our development workflows”
   • [claimed-docs] “Understand and rapidly adjust agent behavior by inspecting API calls, logic traces, and more.”
   • [claimed-docs] “Agent Checks and Simulations catching problems proactively, merge approval workflows putting a person in the loop, and split traffic release…”
   • [community] “Having seen this set up for a customer, what is interesting is how it works with internal APIs for customers. It's all point and click in a …”

   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 Sierra
   Decagon✓fullclaimed7/10

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

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

   proof ↗⚑ flag

   Sierra✓fullcommunity8/10

   Sierra's Agent SDK/Studio explicitly supports authoring step-by-step journeys ('workflows') as code or no-code, with branching logic ('sophisticated logic'), SOP ingestion via Ghostwriter, and simulation/testing to verify deterministic behavior across scenarios. This directly matches encoding SOPs with deterministic branching for known issue types. missing for 10: independent/hands-on verification of deterministic branching behavior specifically (community evidence is generic, not focused on SOP branching), and docs are login-gated so full workflow-editor detail isn't independently viewable.

   • [claimed-docs] “write customer journeys as code, track changes, and build sophisticated logic without giving up our development workflows”
   • [claimed-docs] “Define step-by-step workflows for your agent from scratch, or use AI to instantly generate journeys from your existing operating procedures.”
   • [claimed-docs] “Upload SOPs, raw transcripts, or even audio interviews of subject matter experts to create customer journeys from scratch.”
   • [claimed-docs] “Verify your agent performs as expected across a wide range of scenarios and avoid regressions.”
   • [community] “Having seen this set up for a customer, what is interesting is how it works with internal APIs for customers. It's all point and click in a …”

   proof ↗⚑ flag

Agent access

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

   weight 2 · round to Decagon
   Decagon~partialprobed6/10

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

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

   proof ↗⚑ flag

   Sierra—none0/10

   Direct probes show no llms.txt at sierra.ai (404) and docs.sierra.ai/llms.txt merely resolves to the login SPA HTML shell rather than an actual plain-text agent-oriented index; the real docs are login-gated to contracted customers, so an agent cannot be pointed at a genuine llms.txt or open agent-oriented docs.

   • [probe] “PROBE llms.txt: HTTP 404 at https://sierra.ai/llms.txt”
   • [probe] “PROBE runtime finding (recorded 2026-09-10): docs.sierra.ai has no agent-legible surface — /llms.txt resolves (HTTP 200) to the login SPA's …”

   proof ↗⚑ flag

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

   weight 2 · round to Sierra
   Decagon—none0/10

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

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

   proof ↗⚑ flag

   Sierra~partialprobed4/10

   Sierra's Agent SDK is described as code-based with dev workflows retained, and one blog post explicitly notes publishing to ChatGPT can be done 'via CI/CD', implying some automation/pipeline support. However there is no dedicated CLI, headless runtime docs, or CI-specific guidance, and docs/API references are login-gated (probe shows /llms.txt is a login SPA and no public OpenAPI spec), so full headless/CI operation is unconfirmed. Missing for 10: explicit CLI/headless execution docs, public API/OpenAPI spec, independent CI usage reports.

   • [claimed-docs] “write customer journeys as code, track changes, and build sophisticated logic without giving up our development workflows”
   • [claimed-docs] “Publish to ChatGPT with one click: Make your agent available on ChatGPT with the push of a button, or via CI/CD.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://sierra.ai/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://sierra.ai/openapi.json, https://sierra.ai/swagger.json, https://sierra.ai/api/openapi.json, …”
   • [probe] “PROBE runtime finding (recorded 2026-09-10): docs.sierra.ai has no agent-legible surface — /llms.txt resolves (HTTP 200) to the login SPA's …”

   proof ↗⚑ flag

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

   weight 3 · round to Decagon
   Decagon~partialclaimed3/10

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

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

   proof ↗⚑ flag

   Sierra—none0/10

   No evidence anywhere in the pack mentions MCP servers or the ability to plug external MCP tool servers into Sierra's agents; Sierra's integration mentions are about internal APIs and custom systems, not MCP. missing for 10: any mention of MCP protocol support, MCP client configuration, or third-party tool server integration via MCP.

   ⚑ flag

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

   weight 3 · round to Sierra
   Decagon—none0/10

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

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

   proof ↗⚑ flag

   Sierra~partialprobed4/10

   Sierra markets an Agent SDK for building 'customer journeys as code' with API-call inspection, implying a programmatic interface exists, but there's no publicly discoverable OpenAPI spec, llms.txt, or open API reference — docs.sierra.ai is login-gated to contracted customers rather than a documented public API. Missing for 10: publicly accessible API reference/OpenAPI spec, evidence of self-serve API keys or open documentation, independent developer confirmation of using the API without a sales contract.

   • [claimed-docs] “write customer journeys as code, track changes, and build sophisticated logic without giving up our development workflows”
   • [claimed-docs] “Understand and rapidly adjust agent behavior by inspecting API calls, logic traces, and more.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://sierra.ai/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://sierra.ai/openapi.json, https://sierra.ai/swagger.json, https://sierra.ai/api/openapi.json, …”
   • [probe] “PROBE runtime finding (recorded 2026-09-10): docs.sierra.ai has no agent-legible surface — /llms.txt resolves (HTTP 200) to the login SPA's …”

   proof ↗⚑ flag

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

   weight 2 · round to Decagon
   Decagon~partialclaimed4/10

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

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

   proof ↗⚑ flag

   Sierra—none0/10

   No evidence anywhere in the pack of scoped or least-privilege API credential/token issuance for agents; docs describe agent building, workflows, channels, and analytics but nothing about credential scoping, permissions, or API key management. Probes even show no public OpenAPI/API docs are accessible (sierra-probe-2, sierra-probe-rt-3), reinforcing the absence of evidence.

   • [probe] “PROBE openapi: all candidate paths 404 (https://sierra.ai/openapi.json, https://sierra.ai/swagger.json, https://sierra.ai/api/openapi.json, …”
   • [probe] “PROBE runtime finding (recorded 2026-09-10): docs.sierra.ai has no agent-legible surface — /llms.txt resolves (HTTP 200) to the login SPA's …”

   proof ↗⚑ flag

6. ai-native userBuild against official SDKs

   weight 2 · round to Sierra
   Decagon—none0/10

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

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

   proof ↗⚑ flag

   Sierra~partialprobed5/10

   Sierra advertises an official "Agent SDK" for writing customer journeys as code with logic traces and testing (sierra-docs-1/2/4), but runtime probes show no public OpenAPI/swagger spec and the SDK/docs reference is login-gated to contracted customers rather than openly available to any AI-native developer (sierra-probe-2, sierra-probe-rt-3). Missing for 10: publicly accessible API reference/OpenAPI spec, evidence of open sign-up or trial SDK access, and independent developer accounts of building against it outside a paid contract.

   • [claimed-docs] “write customer journeys as code, track changes, and build sophisticated logic without giving up our development workflows”
   • [claimed-docs] “Understand and rapidly adjust agent behavior by inspecting API calls, logic traces, and more.”
   • [claimed-docs] “Verify your agent performs as expected across a wide range of scenarios and avoid regressions.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://sierra.ai/openapi.json, https://sierra.ai/swagger.json, https://sierra.ai/api/openapi.json, …”
   • [probe] “PROBE runtime finding (recorded 2026-09-10): docs.sierra.ai has no agent-legible surface — /llms.txt resolves (HTTP 200) to the login SPA's …”

   proof ↗⚑ flag

7. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Decagon—none0/10

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

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

   proof ↗⚑ flag

   Sierra—none0/10

   No evidence in the pack mentions webhooks or event subscription capabilities for Sierra; docs pages describe SDK, studio, insights, voice, and channels features but nothing about outbound event notifications. Probes further show no public API spec or open documentation to confirm such a mechanism exists.

   • [probe] “PROBE openapi: all candidate paths 404 (https://sierra.ai/openapi.json, https://sierra.ai/swagger.json, https://sierra.ai/api/openapi.json, …”
   • [probe] “PROBE runtime finding (recorded 2026-09-10): docs.sierra.ai has no agent-legible surface — /llms.txt resolves (HTTP 200) to the login SPA's …”

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round drawn
   Decagon✓fullclaimed8/10

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

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

   proof ↗⚑ flag

   Sierra✓fullcommunity8/10

   Sierra's Explorer and Insights products explicitly deliver AI-generated insights: natural-language querying across conversations, automatic weekly briefings on trends/issues with recommendations, and click-to-investigate drill-downs on report data, plus explainability of agent reasoning. This is a first-party documented feature set directly matching the story, with some independent corroboration of Sierra's data-driven production use (sierra-comm-2/3). Missing for 10: independent hands-on validation of the insights/briefing feature specifically (community evidence is about agent setup, not analytics quality), and no detail on data freshness/accuracy limits.

   • [claimed-docs] “Ask any question about your customer experience in natural language, and Explorer identifies the answer across thousands of real conversatio…”
   • [claimed-docs] “Explorer automatically delivers a weekly briefing on key trends, emerging issues, and recommendations — without you having to ask.”
   • [claimed-docs] “Click any data point on a report to launch Explorer and instantly investigate what's driving that trend.”
   • [claimed-docs] “Understand the reasoning behind every agent action or answer—view knowledge sources, systems accessed, and more.”
   • [community] “Having seen this set up for a customer, what is interesting is how it works with internal APIs for customers. It's all point and click in a …”
   • [community] “The magic isn't in a new LLM technology, it is in reliably productionizing a solution for real-world problems... fill in the gap of missing …”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Decagon~partialclaimed6/10

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

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

   proof ↗⚑ flag

   Sierra~partialcommunity6/10

   Sierra's agents are built to operate autonomously across channels (chat, phone, email, SMS) once deployed, and Explorer explicitly runs in the background to deliver automatic weekly briefings and trend detection 'without you having to ask,' which is genuine unprompted automation. However, there's no documentation of user-configurable scheduled tasks/triggers beyond the always-on conversational agent and the one named automatic-briefing feature. Missing for 10: explicit support for user-defined scheduled/triggered background jobs beyond conversation handling and briefings, and independent/hands-on confirmation of autonomous background execution reliability.

   • [claimed-docs] “Explorer automatically delivers a weekly briefing on key trends, emerging issues, and recommendations — without you having to ask.”
   • [claimed-docs] “Build once and deploy across any channel—chat, phone, email, SMS, and messaging.”
   • [claimed-docs] “Guide care reps through next steps—whether in chat or on calls—automatically capturing and updating customer context as work progresses.”
   • [community] “Having seen this set up for a customer, what is interesting is how it works with internal APIs for customers. It's all point and click in a …”

   proof ↗⚑ flag

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

   weight 3 · round to Sierra
   Decagon~partialclaimed5/10

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

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

   proof ↗⚑ flag

   Sierra~partialclaimed6/10

   Sierra's Ghostwriter feature lets users delegate agent-building tasks to a built-in AI assistant via natural-language prompts (build/modify agents, generate journeys from SOPs/transcripts), fitting the 'delegate tasks to built-in AI assistant' story. However, this is vendor-only documentation with no independent/hands-on corroboration of Ghostwriter specifically; community evidence instead describes manual point-and-click agent setup, not AI-assistant delegation. Missing for 10: independent/hands-on validation of Ghostwriter's delegation capability, and detail on scope/limits of what can be delegated.

   • [claimed-docs] “Build or modify agents by describing how you want them to behave. Update workflows, systems integrations, guardrails, tone, and style with s…”
   • [claimed-docs] “Upload SOPs, raw transcripts, or even audio interviews of subject matter experts to create customer journeys from scratch.”
   • [claimed-docs] “Define step-by-step workflows for your agent from scratch, or use AI to instantly generate journeys from your existing operating procedures.”

   proof ↗⚑ flag

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

   weight 2 · round to Sierra
   Decagon~partialclaimed6/10

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

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

   proof ↗⚑ flag

   Sierra✓fullcommunity7/10

   Sierra provides explicit natural-language control surfaces: Ghostwriter lets users 'build or modify agents by describing how you want them to behave' with 'simple prompts' for workflows, integrations, guardrails, tone and style, and Explorer lets users 'ask any question about your customer experience in natural language.' This directly matches an AI-native user operating the product via NL commands rather than only clicking through UI. Missing for 10: independent hands-on corroboration of NL command reliability/scope beyond vendor docs, and no evidence of NL control over the entire platform (e.g., release governance, channel deployment) rather than just Ghostwriter/Explorer.

   • [claimed-docs] “Build or modify agents by describing how you want them to behave. Update workflows, systems integrations, guardrails, tone, and style with s…”
   • [claimed-docs] “Upload SOPs, raw transcripts, or even audio interviews of subject matter experts to create customer journeys from scratch.”
   • [claimed-docs] “Ask any question about your customer experience in natural language, and Explorer identifies the answer across thousands of real conversatio…”
   • [community] “Having seen this set up for a customer, what is interesting is how it works with internal APIs for customers. It's all point and click in a …”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round drawn
   Decagon—none0/10

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

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

   proof ↗⚑ flag

   Sierra—none0/10

   Probes show no public OpenAPI/interactive reference (404s at openapi.json paths, llms.txt returns login SPA shell), and docs are login-gated to contracted customers rather than an open interactive API reference with runnable examples.

   • [probe] “PROBE llms.txt: HTTP 404 at https://sierra.ai/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://sierra.ai/openapi.json, https://sierra.ai/swagger.json, https://sierra.ai/api/openapi.json, …”
   • [probe] “PROBE runtime finding (recorded 2026-09-10): docs.sierra.ai has no agent-legible surface — /llms.txt resolves (HTTP 200) to the login SPA's …”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Decagon—none0/10

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

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

   proof ↗⚑ flag

   Sierra—none0/10

   Direct probes show no OpenAPI/Swagger spec at common paths (all 404) and no machine-readable llms.txt index; docs are login-gated rather than publicly exposing a spec. missing for 10: publicly downloadable OpenAPI/Swagger file, any machine-readable API spec endpoint.

   • [probe] “PROBE llms.txt: HTTP 404 at https://sierra.ai/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://sierra.ai/openapi.json, https://sierra.ai/swagger.json, https://sierra.ai/api/openapi.json, …”
   • [probe] “PROBE runtime finding (recorded 2026-09-10): docs.sierra.ai has no agent-legible surface — /llms.txt resolves (HTTP 200) to the login SPA's …”

   proof ↗⚑ flag

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

   weight 1 · round drawn
   Decagon~partialclaimed5/10

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

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

   proof ↗⚑ flag

   Sierra~partialclaimed5/10

   Sierra's docs mention scenario testing and regression avoidance (sierra-docs-4) and 'Agent Checks and Simulations' for proactive problem catching (sierra-docs-18), implying some pre-production testing capability, but there is no explicit mention of a dedicated sandbox environment isolated from production data. Missing for 10: explicit sandbox/staging environment documentation, confirmation that test runs don't touch production data, and independent/hands-on verification of this separation.

   • [claimed-docs] “Verify your agent performs as expected across a wide range of scenarios and avoid regressions.”
   • [claimed-docs] “Agent Checks and Simulations catching problems proactively, merge approval workflows putting a person in the loop, and split traffic release…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Decagon—none0/10

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

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

   proof ↗⚑ flag

   Sierra—none0/10

   No evidence of a public versioned API reference or a documented deprecation policy; probes show no OpenAPI spec and docs are login-gated, and llms.txt/openapi.json all 404 or resolve to a login shell rather than API docs.

   • [probe] “PROBE llms.txt: HTTP 404 at https://sierra.ai/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://sierra.ai/openapi.json, https://sierra.ai/swagger.json, https://sierra.ai/api/openapi.json, …”
   • [probe] “PROBE runtime finding (recorded 2026-09-10): docs.sierra.ai has no agent-legible surface — /llms.txt resolves (HTTP 200) to the login SPA's …”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Decagon—none0/10

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

   ⚑ flag

   Sierra—none0/10

   No evidence describes bulk operations across many items (e.g., batch editing knowledge entries, mass workflow updates, or bulk conversation actions). The docs describe individual agent building, knowledge editing, and analytics tools, but nothing about performing actions at scale across many items simultaneously.

   ⚑ flag

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

   weight 3 · round drawn
   Decagon~partialclaimed5/10

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

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

   proof ↗⚑ flag

   Sierra~partialclaimed5/10

   Sierra supports building workflows/journeys and guardrail-based release governance (e.g., agent checks, split traffic, merge approval) which implies some rule-based triggering, and Ghostwriter/Agent Studio let users define step-by-step logic, but there's no explicit documentation of an event-driven 'if X happens, trigger Y automatically' rules engine for AI-native users to configure independently. missing for 10: explicit event-trigger/rules-engine documentation, API/SDK examples of automated action-on-event configuration, independent verification of this specific automation capability.

   • [claimed-docs] “Define step-by-step workflows for your agent from scratch, or use AI to instantly generate journeys from your existing operating procedures.”
   • [claimed-docs] “Agent Checks and Simulations catching problems proactively, merge approval workflows putting a person in the loop, and split traffic release…”
   • [claimed-docs] “Initiate workflows directly from a conversation—no tab-switching, no referencing instructions, no lost context.”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Decagon—none0/10

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

   ⚑ flag

   Sierra—none0/10

   Sierra's evidence covers agent building, workflows, channels, analytics, and release governance, but nothing describes scheduling recurring jobs/workflows (e.g., cron-like triggers or timed automation runs) for AI-native users. Missing for 10: any documentation of scheduled/recurring job execution, trigger-based automation, or timer-based workflow runs.

   ⚑ flag

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

   weight 1 · round to Sierra
   Decagon~partialclaimed4/10

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

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

   proof ↗⚑ flag

   Sierra~partialprobed5/10

   Sierra's Agent SDK is described as 'journeys as code' with change tracking, and release-governance docs mention merge approval, agent checks/simulations, and split-traffic gradual rollouts — pointing to versioned, reviewable release workflows. However, no explicit rollback/revert mechanism is documented, and docs are login-gated so no independent confirmation exists. missing for 10: explicit rollback capability, independent/hands-on confirmation of version history and revert function.

   • [claimed-docs] “write customer journeys as code, track changes, and build sophisticated logic without giving up our development workflows”
   • [claimed-docs] “Agent Checks and Simulations catching problems proactively, merge approval workflows putting a person in the loop, and split traffic release…”
   • [probe] “PROBE runtime finding (recorded 2026-09-10): docs.sierra.ai has no agent-legible surface — /llms.txt resolves (HTTP 200) to the login SPA's …”

   proof ↗⚑ flag

Channels

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

   weight 2 · round drawn
   Decagon~partialclaimed5/10

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

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

   proof ↗⚑ flag

   Sierra~partialclaimed5/10

   Sierra's docs confirm one agent can be built once and deployed across chat, phone, email, SMS, and messaging channels (sierra-docs-3), with channel-specific tuning like Voice Personas (sierra-docs-16) and even ChatGPT publishing (sierra-docs-17), showing broad omnichannel intent. However, none of the evidence explicitly names Slack, WhatsApp, or social media as supported channels, leaving the specific channels support leaders care about unconfirmed. Missing for 10: explicit documentation or independent confirmation that Slack, WhatsApp, and social platforms are supported channels, plus hands-on evidence of a single agent operating consistently across these specific channels.

   • [claimed-docs] “Build once and deploy across any channel—chat, phone, email, SMS, and messaging.”
   • [claimed-docs] “Use Voice Personas to design how your agent sounds, speaks, and connects, powered by a constellation of models tuned across 59 languages.”
   • [claimed-docs] “Publish to ChatGPT with one click: Make your agent available on ChatGPT with the push of a button, or via CI/CD.”

   proof ↗⚑ flag

Languages

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

   weight 2 · round to Sierra
   Decagon~partialclaimed4/10

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

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

   proof ↗⚑ flag

   Sierra~partialclaimed6/10

   Sierra documents multilingual voice capability explicitly ('Voice Personas... tuned across 59 languages') and general multi-channel deployment, implying broad language coverage for customer-facing conversations. However, there is no direct evidence about handling a knowledge base that exists only in English—no mention of automatic translation/grounding of English-only content into other languages, so the specific claim in the story (KB gap bridging) is unevidenced. missing for 10: explicit documentation on cross-language grounding from English-only knowledge base, independent verification of multilingual quality beyond voice.

   • [claimed-docs] “Use Voice Personas to design how your agent sounds, speaks, and connects, powered by a constellation of models tuned across 59 languages.”
   • [claimed-docs] “Build once and deploy across any channel—chat, phone, email, SMS, and messaging.”

   proof ↗⚑ 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 Sierra
   Decagon~partialclaimed6/10

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

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

   proof ↗⚑ flag

   Sierra✓fullclaimed8/10

   Sierra explicitly markets voice as a first-class channel with the same agent logic/knowledge as chat ('Build once and deploy across any channel—chat, phone, email, SMS'), plus voice-specific features like Voice Personas across 59 languages, replacing IVR with empathetic voice agents, and phone payments without IVR handoff. Missing for 10: independent/hands-on verification that voice calls actually share identical knowledge/actions with chat in production (only vendor docs, no community confirmation of phone-specific parity).

   • [claimed-docs] “Build once and deploy across any channel—chat, phone, email, SMS, and messaging.”
   • [claimed-docs] “Use Voice Personas to design how your agent sounds, speaks, and connects, powered by a constellation of models tuned across 59 languages.”
   • [claimed-docs] “Collect card and ACH payments entirely over the phone with no IVR handoff.”
   • [claimed-docs] “Replace rigid IVR menus with an empathetic voice agent that understands customer context”
   • [claimed-docs] “Guide care reps through next steps—whether in chat or on calls—automatically capturing and updating customer context as work progresses.”

   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 Sierra
   Decagon—none0/10

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

   ⚑ flag

   Sierra~partialclaimed6/10

   Sierra's Live Assist product explicitly targets escalation handoff, claiming reps are guided through next steps with automatically captured and updated customer context and can pick up conversations 'no tab-switching, no referencing instructions, no lost context' — directly addressing the no-repeat-yourself goal. However, there's no explicit mention of a generated conversation summary artifact or hands-on/independent confirmation that reps actually receive full transcript + summary + collected details in practice. Missing for 10: explicit summary-generation evidence, independent/hands-on validation of the handoff experience, confirmation reps see full conversation history alongside context.

   • [claimed-docs] “Guide care reps through next steps—whether in chat or on calls—automatically capturing and updating customer context as work progresses.”
   • [claimed-docs] “Initiate workflows directly from a conversation—no tab-switching, no referencing instructions, no lost context.”

   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 Decagon
   Decagon~partialclaimed4/10

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

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

   proof ↗⚑ flag

   Sierra~partialclaimed3/10

   Sierra's docs mention configurable guardrails, workflows, and a 'Live Assist' human-handoff product, implying some escalation mechanism exists, but no evidence describes explicit configuration of handoff triggers by topic, sentiment, customer tier, or explicit customer request, nor proof of reliable adherence to such rules. Missing for 10: documentation of specific trigger types (topic/sentiment/tier/request), configuration UI/API for these rules, and evidence (first-party or independent) that the agent reliably obeys them in production.

   • [claimed-docs] “Build or modify agents by describing how you want them to behave. Update workflows, systems integrations, guardrails, tone, and style with s…”
   • [claimed-docs] “Guide care reps through next steps—whether in chat or on calls—automatically capturing and updating customer context as work progresses.”
   • [claimed-docs] “Agent Checks and Simulations catching problems proactively, merge approval workflows putting a person in the loop, and split traffic release…”
   • [claimed-docs] “Define step-by-step workflows for your agent from scratch, or use AI to instantly generate journeys from your existing operating procedures.”

   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 drawn
   Decagon~partialclaimed4/10

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

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

   proof ↗⚑ flag

   Sierra~partialclaimed4/10

   Sierra's docs mention grounding agents in knowledge/FAQs/policies (sierra-docs-7) and general 'guardrails' as a configurable behavior via Ghostwriter (sierra-docs-8), plus release-governance guardrails like Agent Checks/Simulations (sierra-docs-18) and visibility into reasoning/knowledge sources (sierra-docs-13). However, no evidence explicitly describes a 'safe decline' mechanism for off-knowledge questions or confirms the agent won't invent prices/policies rather than guess. Missing for 10: explicit documentation or hands-on proof of decline-on-unknown behavior, third-party validation that hallucinated policies/prices are prevented, and detail on the unexplored 'trust-and-reliability' product page.

   • [claimed-docs] “View, manage, and edit knowledge data such as Help Center content, FAQs, and policies that ground your agent.”
   • [claimed-docs] “Build or modify agents by describing how you want them to behave. Update workflows, systems integrations, guardrails, tone, and style with s…”
   • [claimed-docs] “Understand the reasoning behind every agent action or answer—view knowledge sources, systems accessed, and more.”
   • [claimed-docs] “Agent Checks and Simulations catching problems proactively, merge approval workflows putting a person in the loop, and split traffic release…”

   proof ↗⚑ flag

Supervision

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

   weight 2 · round drawn
   Decagon—none0/10

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

   ⚑ flag

   Sierra—none0/10

   Sierra's evidence covers release governance (merge-approval for deploying agent changes) and Live Assist (guiding human reps in real time), but neither describes a mode where the agent drafts individual customer replies that a human must approve before they are sent. No docs or community evidence mention message-level human-in-the-loop approval for live customer conversations.

   • [claimed-docs] “Agent Checks and Simulations catching problems proactively, merge approval workflows putting a person in the loop, and split traffic release…”
   • [claimed-docs] “Guide care reps through next steps—whether in chat or on calls—automatically capturing and updating customer context as work progresses.”
   • [claimed-docs] “Initiate workflows directly from a conversation—no tab-switching, no referencing instructions, no lost context.”

   proof ↗⚑ flag

Topic controls

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

   weight 2 · round to Decagon
   Decagon~partialclaimed5/10

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

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

   proof ↗⚑ flag

   Sierra—none0/10

   Sierra's guardrail evidence covers release governance (Agent Checks, Simulations, merge approval, split traffic) and general knowledge/workflow editing, but nothing describes topic-level human-only flags for categories like legal threats, cancellations, or security that the agent is barred from handling. Live-assist shows human+AI collaboration but not a mechanism to designate certain topics as strictly human-only with enforced escalation.

   • [claimed-docs] “Agent Checks and Simulations catching problems proactively, merge approval workflows putting a person in the loop, and split traffic release…”
   • [claimed-docs] “Guide care reps through next steps—whether in chat or on calls—automatically capturing and updating customer context as work progresses.”

   proof ↗⚑ flag

Analytics

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

   weight 3 · round drawn
   Decagon~partialclaimed5/10

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

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

   proof ↗⚑ flag

   Sierra~partialclaimed5/10

   Sierra's Insights and Explorer products provide dashboards/reports with drill-down and natural-language trend analysis (sierra-docs-10, sierra-docs-11, sierra-docs-12, sierra-docs-13), showing the platform surfaces analytics for support leaders, but no evidence specifies the exact metrics named in the story (resolution rate, CSAT, handoff rate, cost per resolution). Missing for 10: explicit documentation naming these specific KPIs, screenshots/examples of the actual dashboard metrics, and independent confirmation that leaders use it for exec-level reporting.

   • [claimed-docs] “Ask any question about your customer experience in natural language, and Explorer identifies the answer across thousands of real conversatio…”
   • [claimed-docs] “Explorer automatically delivers a weekly briefing on key trends, emerging issues, and recommendations — without you having to ask.”
   • [claimed-docs] “Click any data point on a report to launch Explorer and instantly investigate what's driving that trend.”
   • [claimed-docs] “Understand the reasoning behind every agent action or answer—view knowledge sources, systems accessed, and more.”

   proof ↗⚑ flag

Insights

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

   weight 1 · round to Decagon
   Decagon~partialclaimed7/10

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

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

   proof ↗⚑ flag

   Sierra~partialclaimed6/10

   Sierra's Explorer product explicitly surfaces trends and emerging issues via natural-language querying of conversations and proactive weekly briefings, and Insights lets users drill into data points—directly matching the 'surface emerging issues before they spike' theme. However, evidence doesn't explicitly confirm topic clustering methodology, predictive spike detection, or independent/hands-on validation of this specific capability. Missing for 10: explicit description of topic-clustering mechanics, evidence of predictive alerting before ticket-volume spikes (vs. reactive weekly summaries), and independent/customer corroboration of this specific insights capability.

   • [claimed-docs] “Ask any question about your customer experience in natural language, and Explorer identifies the answer across thousands of real conversatio…”
   • [claimed-docs] “Explorer automatically delivers a weekly briefing on key trends, emerging issues, and recommendations — without you having to ask.”
   • [claimed-docs] “Click any data point on a report to launch Explorer and instantly investigate what's driving that trend.”

   proof ↗⚑ flag

Helpdesk

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

   weight 3 · round to Decagon
   Decagon~partialclaimed4/10

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

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

   proof ↗⚑ flag

   Sierra—none0/10

   No evidence pack citation mentions Zendesk, Salesforce, Intercom, or bidirectional ticket/context syncing with existing helpdesk platforms; only generic 'systems integrations' and 'internal APIs' are referenced without naming any helpdesk system or describing two-way ticket sync.

   ⚑ 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 drawn
   Decagon—none0/10

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

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

   proof ↗⚑ flag

   Sierra—none0/10

   Evidence shows Sierra lets teams manually 'view, manage, and edit knowledge data' (sierra-docs-7) but nothing describes automatic re-syncing of knowledge sources on a schedule or on-change detection; docs are login-gated so no further detail is visible.

   • [claimed-docs] “View, manage, and edit knowledge data such as Help Center content, FAQs, and policies that ground your agent.”
   • [probe] “PROBE runtime finding (recorded 2026-09-10): docs.sierra.ai has no agent-legible surface — /llms.txt resolves (HTTP 200) to the login SPA's …”

   proof ↗⚑ flag

Gaps

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

   weight 1 · round to Decagon
   Decagon✓fullclaimed7/10

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

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

   proof ↗⚑ flag

   Sierra~partialclaimed5/10

   Sierra's Explorer and Insights products surface emerging issues, trends, and the reasoning/knowledge sources behind agent answers, and Agent Studio lets teams view/manage knowledge content (FAQs, policies), which could help surface gaps — but no evidence explicitly describes detecting knowledge gaps or conflicting content as a distinct feature. Missing for 10: explicit conflicting-content/contradiction detection, explicit 'knowledge gap' flagging, and independent/hands-on confirmation that Explorer or Insights actually pinpoints such gaps rather than general conversation trends.

   • [claimed-docs] “View, manage, and edit knowledge data such as Help Center content, FAQs, and policies that ground your agent.”
   • [claimed-docs] “Ask any question about your customer experience in natural language, and Explorer identifies the answer across thousands of real conversatio…”
   • [claimed-docs] “Explorer automatically delivers a weekly briefing on key trends, emerging issues, and recommendations — without you having to ask.”
   • [claimed-docs] “Click any data point on a report to launch Explorer and instantly investigate what's driving that trend.”
   • [claimed-docs] “Understand the reasoning behind every agent action or answer—view knowledge sources, systems accessed, and more.”

   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 Sierra
   Decagon—none0/10

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

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

   proof ↗⚑ flag

   Sierra✓fullclaimed7/10

   Sierra explicitly supports grounding agent answers in customer-owned knowledge (Help Center content, FAQs, policies) via Agent Studio, and Insights lets teams 'understand the reasoning behind every agent action or answer—view knowledge sources, systems accessed' which directly maps to showing which source an answer drew from. Missing for 10: independent/hands-on verification that end-user-facing answers visibly cite specific articles, and detail on citation UX rather than just admin-side reasoning traces.

   • [claimed-docs] “View, manage, and edit knowledge data such as Help Center content, FAQs, and policies that ground your agent.”
   • [claimed-docs] “Understand the reasoning behind every agent action or answer—view knowledge sources, systems accessed, and more.”
   • [claimed-docs] “Ask any question about your customer experience in natural language, and Explorer identifies the answer across thousands of real conversatio…”

   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 Sierra
   Decagon~partialclaimed4/10

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

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

   proof ↗⚑ flag

   Sierra~partialprobed6/10

   Sierra's docs explicitly claim agent-studio lets teams 'view, manage, and edit knowledge data such as Help Center content, FAQs, and policies' and Ghostwriter can ingest SOPs, transcripts, and audio interviews to build journeys, supporting knowledge ingestion beyond just help center docs. However, there's no explicit evidence of ingesting past tickets or internal wikis specifically, and docs/reference material is login-gated so independent verification of breadth of source-type ingestion is limited. Missing for 10: documented support for tickets/wiki ingestion specifically, and independent/hands-on confirmation of the ingestion workflow beyond marketing copy.

   • [claimed-docs] “View, manage, and edit knowledge data such as Help Center content, FAQs, and policies that ground your agent.”
   • [claimed-docs] “Upload SOPs, raw transcripts, or even audio interviews of subject matter experts to create customer journeys from scratch.”
   • [probe] “PROBE runtime finding (recorded 2026-09-10): docs.sierra.ai has no agent-legible surface — /llms.txt resolves (HTTP 200) to the login SPA's …”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Decagon—none0/10

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

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

   proof ↗⚑ flag

   Sierra—none0/10

   Sierra markets an Agent SDK for code-based building alongside a separate no-code Agent Studio, but there is no evidence of API/UI feature parity — no public OpenAPI/swagger spec was found (404s), and the SDK reference docs themselves are login-gated to contracted customers, meaning even documented API scope can't be verified as matching UI capabilities.

   • [claimed-docs] “write customer journeys as code, track changes, and build sophisticated logic without giving up our development workflows”
   • [claimed-docs] “Empower teams to build and manage agents—no code required”
   • [probe] “PROBE openapi: all candidate paths 404 (https://sierra.ai/openapi.json, https://sierra.ai/swagger.json, https://sierra.ai/api/openapi.json, …”
   • [probe] “PROBE runtime finding (recorded 2026-09-10): docs.sierra.ai has no agent-legible surface — /llms.txt resolves (HTTP 200) to the login SPA's …”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Decagon—none0/10

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

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

   proof ↗⚑ flag

   Sierra—none0/10

   No evidence of any data export or portability feature for customer journeys, knowledge data, or conversation logs in open formats; probes even show docs/API surfaces are gated or unavailable (404s, login-gated /llms.txt). Missing for 10: any export functionality, data portability documentation, or open-format data dump capability.

   • [probe] “PROBE llms.txt: HTTP 404 at https://sierra.ai/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://sierra.ai/openapi.json, https://sierra.ai/swagger.json, https://sierra.ai/api/openapi.json, …”
   • [probe] “PROBE runtime finding (recorded 2026-09-10): docs.sierra.ai has no agent-legible surface — /llms.txt resolves (HTTP 200) to the login SPA's …”

   proof ↗⚑ flag

Pricing

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

   weight 2 · round drawn
   Decagon—none0/10

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

   ⚑ flag

   Sierra—none0/10

   No evidence pack item mentions pricing, resolution-based billing, caps, or published rates; docs and probes cover product features and access gating only. Sierra is widely known anecdotally for outcome-based pricing but nothing in this evidence pack substantiates published, capped, self-serve pricing terms.

   ⚑ flag

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

   weight 2 · round drawn
   Decagon—none0/10

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

   ⚑ flag

   Sierra—none0/10

   No evidence pack item addresses data residency, region selection, or storage location controls; the docs cover agent building, workflows, and channels but not data governance/residency options. missing for 10: any mention of data region selection, residency guarantees, or storage location controls.

   ⚑ flag

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

   weight 3 · round drawn
   Decagon—none0/10

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

   ⚑ flag

   Sierra—none0/10

   No evidence in the pack addresses data-training opt-out or AI model training policies; Sierra's docs focus on product features (agent building, analytics, channels) with no privacy/data-use policy statements provided.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to Decagon
   Decagon~partialclaimed3/10

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

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

   proof ↗⚑ flag

   Sierra—none0/10

   No evidence pack item addresses data retention controls, deletion policies, or user-facing data lifecycle management; docs cover agent building, analytics, and channels but never mention retention/deletion settings, and docs.sierra.ai is login-gated so no public verification exists.

   ⚑ flag

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

   weight 2 · round drawn
   Decagon—none0/10

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

   ⚑ flag

   Sierra—none0/10

   No evidence pack item discusses telemetry, usage tracking, opt-out controls, or privacy settings for AI-native/developer users; docs focus on product features and docs are gated behind login. Missing for 10: any documentation of telemetry collection practices, opt-out mechanism, or privacy controls.

   ⚑ 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 Sierra
   Decagon~partialclaimed6/10

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

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

   proof ↗⚑ flag

   Sierra~partialcommunity7/10

   Sierra's docs and community evidence show the agent integrates with customers' internal APIs and systems (not just static knowledge), with Insights explicitly noting 'systems accessed' during agent actions, and Live Assist capturing live customer context. However, no evidence explicitly confirms real-time retrieval of specifics like plan, order status, or account history. missing for 10: explicit documented example of pulling live order/plan/account data, independent verification beyond one HN anecdote.

   • [claimed-docs] “Understand and rapidly adjust agent behavior by inspecting API calls, logic traces, and more.”
   • [claimed-docs] “Understand the reasoning behind every agent action or answer—view knowledge sources, systems accessed, and more.”
   • [claimed-docs] “Guide care reps through next steps—whether in chat or on calls—automatically capturing and updating customer context as work progresses.”
   • [community] “Having seen this set up for a customer, what is interesting is how it works with internal APIs for customers. It's all point and click in a …”

   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 Sierra
   Decagon~partialclaimed5/10

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

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

   proof ↗⚑ flag

   Sierra~partialcommunity6/10

   Sierra's docs describe building step-by-step, multi-step 'customer journeys' and workflows (sierra-docs-6, sierra-docs-9) rather than single canned replies, and community commentary confirms agents are configured to work through processes with internal APIs (sierra-comm-2). However, no evidence explicitly demonstrates the agent proactively asking clarifying questions or a hands-on troubleshooting transcript showing multi-turn dialogue in practice. Missing for 10: concrete transcript/demo of clarifying-question behavior, independent evaluation of troubleshooting depth, and explicit mention of clarification-seeking as a designed capability.

   • [claimed-docs] “Define step-by-step workflows for your agent from scratch, or use AI to instantly generate journeys from your existing operating procedures.”
   • [claimed-docs] “Upload SOPs, raw transcripts, or even audio interviews of subject matter experts to create customer journeys from scratch.”
   • [community] “Having seen this set up for a customer, what is interesting is how it works with internal APIs for customers. It's all point and click in a …”

   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 Sierra
   Decagon~partialclaimed4/10

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

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

   proof ↗⚑ flag

   Sierra~partialprobed6/10

   Sierra's marketing emphasizes agent-driven end-to-end workflow execution (journeys, integrations, payments, guardrails, testing) implying resolution rather than mere deflection, and community evidence corroborates real production use handling customer processes end-to-end for at least one customer. However, no quantitative resolution-rate metrics, benchmarks, or third-party validation of 'meaningful share resolved end-to-end' are provided — tau-bench is a research benchmark, not a customer outcome metric. Missing for 10: published resolution-rate statistics, case studies with concrete resolution percentages, independent audits distinguishing resolution from deflection.

   • [claimed-docs] “Define step-by-step workflows for your agent from scratch, or use AI to instantly generate journeys from your existing operating procedures.”
   • [claimed-docs] “Upload SOPs, raw transcripts, or even audio interviews of subject matter experts to create customer journeys from scratch.”
   • [claimed-docs] “Collect card and ACH payments entirely over the phone with no IVR handoff.”
   • [claimed-docs] “Replace rigid IVR menus with an empathetic voice agent that understands customer context”
   • [community] “Having seen this set up for a customer, what is interesting is how it works with internal APIs for customers. It's all point and click in a …”
   • [community] “The magic isn't in a new LLM technology, it is in reliably productionizing a solution for real-world problems... fill in the gap of missing …”
   • [probe] “PROBE runtime (recorded 2026-09-10): Sierra's agent benchmark is genuinely open — the official sierra-research/tau-bench repository README f…”

   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 drawn
   Decagon~partialclaimed7/10

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

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

   proof ↗⚑ flag

   Sierra~partialclaimed7/10

   Sierra provides explicit tone/brand-voice controls (Ghostwriter prompts for tone and style, Voice Personas tuned across 59 languages) plus testing/simulation tools to verify agent behavior across scenarios and avoid regressions, which supports consistency claims. However, all evidence is vendor-authored with no independent or hands-on verification that voice/tone actually stays consistent across topics and languages in production. Missing for 10: independent case studies or benchmarks confirming cross-topic/cross-language tone consistency, and detail on how brand-voice guardrails are enforced at scale.

   • [claimed-docs] “Build or modify agents by describing how you want them to behave. Update workflows, systems integrations, guardrails, tone, and style with s…”
   • [claimed-docs] “Use Voice Personas to design how your agent sounds, speaks, and connects, powered by a constellation of models tuned across 59 languages.”
   • [claimed-docs] “Verify your agent performs as expected across a wide range of scenarios and avoid regressions.”
   • [claimed-docs] “Agent Checks and Simulations catching problems proactively, merge approval workflows putting a person in the loop, and split traffic release…”

   proof ↗⚑ flag

Qa

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

   weight 1 · round to Decagon
   Decagon✓fullclaimed8/10

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

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

   proof ↗⚑ flag

   Sierra~partialclaimed7/10

   Sierra documents Agent Checks and Simulations that proactively catch problems, merge-approval workflows for human review, and split-traffic releases (sierra-docs-18), plus regression testing (sierra-docs-4) and Explorer/Insights tools that surface conversation trends, flag emerging issues, and explain agent reasoning (sierra-docs-10, -11, -13). Ghostwriter lets teams feed fixes back by updating workflows/guardrails via prompts (sierra-docs-8). Missing for 10: explicit description of scored/sampled QA reviews with quantitative scoring rubrics, and independent evidence of the review loop actually closing the gap between flagged failures and shipped fixes.

   • [claimed-docs] “Verify your agent performs as expected across a wide range of scenarios and avoid regressions.”
   • [claimed-docs] “Agent Checks and Simulations catching problems proactively, merge approval workflows putting a person in the loop, and split traffic release…”
   • [claimed-docs] “Ask any question about your customer experience in natural language, and Explorer identifies the answer across thousands of real conversatio…”
   • [claimed-docs] “Explorer automatically delivers a weekly briefing on key trends, emerging issues, and recommendations — without you having to ask.”
   • [claimed-docs] “Understand the reasoning behind every agent action or answer—view knowledge sources, systems accessed, and more.”
   • [claimed-docs] “Build or modify agents by describing how you want them to behave. Update workflows, systems integrations, guardrails, tone, and style with s…”

   proof ↗⚑ flag

Simulation

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

   weight 2 · round drawn
   Decagon✓fullclaimed8/10

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

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

   proof ↗⚑ flag

   Sierra✓fullprobed8/10

   Sierra explicitly documents 'Agent Checks and Simulations' and 'verify your agent performs as expected across a wide range of scenarios and avoid regressions' (sierra-docs-4, sierra-docs-18), directly matching pre-release testing against scenarios/regressions. This is further corroborated by Sierra's public tau-bench research benchmark for evaluating conversational agents on simulated user interactions (sierra-probe-rt-1), showing real investment in simulation-based testing methodology. Missing for 10: no explicit mention of testing against historical/real ticket transcripts specifically (only 'scenarios' and simulations), and no independent hands-on customer account of the simulation workflow in practice.

   • [claimed-docs] “Verify your agent performs as expected across a wide range of scenarios and avoid regressions.”
   • [claimed-docs] “Agent Checks and Simulations catching problems proactively, merge approval workflows putting a person in the loop, and split traffic release…”
   • [probe] “PROBE runtime (recorded 2026-09-10): Sierra's agent benchmark is genuinely open — the official sierra-research/tau-bench repository README f…”

   proof ↗⚑ flag