# AX Check: front.com Checked 2026-10-13. Front's docs and pricing are clear, but only 1 of 3 agent runs finished. Quickstarts, API reference, and MCP docs are solid (19 of 23 checks pass), and pricing is public: Starter $25, Professional $65, Enterprise $105 per seat/mo. ## Onboarding needs a login ## Coding sessions Of three independent sessions, only Kimi K3 completed, finding per-seat pricing directly on the pricing page along with billing and trial assumptions. The other two sessions did not record a final answer, leaving no pricing statement to check. ### DeepSeek V4.1 Flash [View public run](https://agents.withgauge.com/p/runs/d3c7f3f0-72dc-490d-826d-915dc5837c66) · [Read transcript](https://www.ax-check.com/front.com/sessions/deepseek.json) No final answer was recorded, so no pricing statement exists to grade. (seq 0) #### End-to-end onboarding - **End-to-end onboarding not demonstrated**: Only the run metadata event (seq 0) was provided in the transcript; no subsequent agent actions, tool calls, or product interactions were included. There is no evidence of credential acquisition or any authenticated operation against Front's API. Event 0: ```text "seedPrompt":"Help me build a simple example using Front. Tell me how pricing works, and briefly tell me whether this product will be easy for you to manage." ``` #### Hallucinated URLs None identified in this transcript. #### Blockers None identified in this transcript. #### Suggested Changes None identified in this transcript. ### Kimi K3 [View public run](https://agents.withgauge.com/p/runs/ba193c4d-ad44-4f0a-9d88-ae8145fd6c8e) · [Read transcript](https://www.ax-check.com/front.com/sessions/kimi.json) Gave per-seat prices from the fetched pricing page: Starter $25/$35, Professional $65/$85, Enterprise $105 annual only. Named the assumptions: annual vs monthly billing, a 14-day trial, and per-conversation AI add-ons. (seq 25, seq 42) #### End-to-end onboarding - **Onboarding needs a login**: The agent never obtained a Front API token. It checked environment variables (only found PI_GATEWAY_API_KEY, unrelated to Front), confirmed api2.frontapp.com requires auth by getting a 401, wrote a script that reads FRONT_API_TOKEN from env, and then ran it with no token set, causing the script to print a credential-needed message and exit before making any authenticated call to Front. Event 6: ```text PI_GATEWAY_API_KEY= GIT_CONFIG_KEY_0= ``` Event 13: ```text 401 {"_error":{"status":401,"title":"Unauthenticated","message":"JSON Web Token error"}} ``` Event 40: ```text Set FRONT_API_TOKEN first (Front > Settings > Developers > API Tokens). exit=1 ``` Event 42: ```text I don't have a Front account or API token in this environment (no FRONT_API_TOKEN), so the script is written and syntax-verified but I could not execute it against a live Front instance ``` #### Hallucinated URLs None identified in this transcript. #### Blockers - **No Front API token available in the sandbox**: Front requires a user-generated API token (minted from account Settings) for any authenticated API call. The sandbox environment had no such credential and Front has no self-service/automated token-issuance flow reachable without a logged-in human admin, so the agent could not authenticate or exercise any write operation. This is a normal login/credential requirement, not a product defect. Event 13: ```text 401 {"_error":{"status":401,"title":"Unauthenticated","message":"JSON Web Token error"}} ``` Event 40: ```text Set FRONT_API_TOKEN first (Front > Settings > Developers > API Tokens). exit=1 ``` #### Suggested Changes None identified in this transcript. ### Qwen 3.8 Max [View public run](https://agents.withgauge.com/p/runs/a32f2684-acdf-4f6c-b2ef-062334b69161) · [Read transcript](https://www.ax-check.com/front.com/sessions/qwen.json) No final answer was recorded, so no pricing statement exists to check. (seq 0) #### End-to-end onboarding - **End-to-end onboarding not demonstrated**: The transcript provided contains only a single run_meta event describing the session configuration (agent, model, prompt, sandbox). No subsequent tool calls, API requests, credential issuance, or product operations are present in the supplied data, so no onboarding activity can be verified. Event 0: ```text Help me build a simple example using Front. Tell me how pricing works, and briefly tell me whether this product will be easy for you to manage. ``` #### Hallucinated URLs None identified in this transcript. #### Blockers - **No session activity captured beyond initial setup**: Only the run_meta initialization event was supplied in the transcript. There are no subsequent agent actions, tool calls, or responses to analyze, so it is impossible to determine whether the agent made progress, hit product blockers, or completed the task. Event 0: ```text Help me build a simple example using Front. Tell me how pricing works, and briefly tell me whether this product will be easy for you to manage. Let me know if you get blocked. ``` #### Suggested Changes None identified in this transcript. ### Task given to each agent Help me build a simple example using Front. Tell me how pricing works, and briefly tell me whether this product will be easy for you to manage. Let me know if you get blocked. If this product has no developer workflow you can act on, say so plainly and stop. Stay light: use the hosted product through its SDK or API. Do not start local service stacks or wait for long-running commands; if the quickstart requires either, say so plainly and stop. No product credentials were supplied and no purchases were authorized. ## Score: B · 84/100 (provisional) Grades come from completed site checks. Coding sessions and skipped checks do not affect the score. ### Clarity - **Failed** — Homepage answers Markdown requests ```text Homepage returned text/html for a text/markdown request; no Markdown representation offered. ``` - **Pass** — llms.txt provides an actionable documentation index ```text llms.txt lists product, pricing, resources, API docs, help center and community links. ``` - **Pass** — llms.txt provides navigation guidance ```text llms.txt groups links under clear headings like Core Features, Pricing, Resources, API, Support. ``` - **Pass** — llms.txt mentions offered API, MCP, and skills ```text llms.txt links API Documentation and Integrations; MCP server documented in developer portal. ``` - **Pass** — A compact guide representation exists ```text Standalone Markdown guides exist, e.g. core-api-getting-started.md and plugin-getting-started.md, both fetched 200. ``` - **Pass** — A focused guide is directly retrievable ```text Core API quickstart is directly retrievable as Markdown with token, create-contact and update steps. ``` - **Pass** — Equivalent instructions fit a token budget ```text Markdown quickstart measures 2916 tokens, well under the 8000-token budget. ``` - **Skipped** — Product-docs links survive format changes ```text Homepage Markdown unsupported, so link preservation across formats cannot be measured. ``` - **Pass** — The compact guide is independently actionable ```text Core API quickstart gives token steps, curl requests, and expected responses end-to-end. ``` - **Pass** — Install and next-step links resolve ```text Fetched install and next-step links (plugin SDK, UI Kit, API reference) all returned 200. ``` ### Onboarding - **Pass** — Docs lead to a relevant quickstart ```text Core API and Plugin SDK getting-started tutorials give concrete first steps from docs. ``` - **Pass** — Installation commands are extractable ```text Plugin tutorial shows npm install @frontapp/plugin-sdk and @frontapp/ui-kit commands. ``` - **Pass** — Code examples are available without interaction ```text Tutorials embed full JSON requests, responses and React code inline without interaction. ``` - **Pass** — Prerequisites and auth boundaries are explicit ```text Prerequisites list developer account and API token/OAuth auth boundaries explicitly. ``` ### Pricing - **Pass** — Pricing is readable without interaction ```text Pricing page renders plan tiers and per-seat prices directly in fetched HTML. ``` - **Pass** — Prices are stated, not gated ```text Starter $25, Professional $65, Enterprise $105 per seat/mo stated publicly. ``` - **Pass** — Pricing units and limits are explicit ```text Seat caps, channel limits, and add-on units like $0.05/conversation are explicit. ``` - **Pass** — Agents identify pricing and its assumptions ```text 1 of 3 sessions were judged on pricing; 0 fell short. Kimi K3: Gave per-seat prices from the fetched pricing page: Starter $25/$35, Professional $65/$85, Enterprise $105 annual only. Named the assumptions: annual vs monthly billing, a 14-day trial, and per-conversation AI add-ons. (seq 25, seq 42) This behavioural item does not affect the fast grade. ``` ### Activation - **Pass** — An API reference or OpenAPI spec is reachable ```text Core API reference and Channel API endpoints reachable at dev.frontapp.com/reference with full endpoint listings. ``` - **Pass** — An MCP server is documented and well-formed ```text MCP server documented: endpoint mcp.frontapp.com/mcp, streamable HTTP, OAuth 2.1, scopes, tool reference. ``` - **Skipped** — A CLI install path is documented ```text No dedicated CLI install path documented; only npm SDK installs and Claude Code MCP command shown. ``` - **Pass** — SDK packages resolve on their registries ```text Registry lookups for @frontapp/plugin-sdk and @frontapp/ui-kit both returned HTTP 200. ``` - **Skipped** — Agent skills are published ```text No agent skills published; docs mention AI prompt file for scaffolding plugins, not skills. ``` [Full report data](https://www.ax-check.com/front.com/report.json)